1 00:00:01,120 --> 00:00:03,520 Speaker 1: Welcome to Stuff You Should Know, a production of five 2 00:00:03,600 --> 00:00:12,760 Speaker 1: Heart Radios How Stuff Works. Hey, and welcome to the podcast. 3 00:00:12,800 --> 00:00:16,239 Speaker 1: I'm Josh Clark, and there's Charles W. Chuck Bryant over there, 4 00:00:16,239 --> 00:00:21,159 Speaker 1: and we've got the scoop. Jerry's around here somewhere, and 5 00:00:21,239 --> 00:00:24,080 Speaker 1: this is Stuff you Should Know. Off to a great start. 6 00:00:24,320 --> 00:00:27,800 Speaker 1: She's in hers, she is she's got this remote thing 7 00:00:27,880 --> 00:00:34,680 Speaker 1: going on. Uh, it's like the COVID special, that's right. Uh. 8 00:00:34,720 --> 00:00:37,680 Speaker 1: And this was this has been what I've been wanting 9 00:00:37,720 --> 00:00:43,240 Speaker 1: to do since two thousand sixteen, and why it seems 10 00:00:43,280 --> 00:00:46,839 Speaker 1: like the fire kind of went down on it and 11 00:00:46,880 --> 00:00:49,560 Speaker 1: now it's the fires back up again. In election season, 12 00:00:50,040 --> 00:00:53,479 Speaker 1: I thought no better time than to talk election polling 13 00:00:54,360 --> 00:00:58,200 Speaker 1: and this weird sort of black magic which is really 14 00:00:58,240 --> 00:01:01,360 Speaker 1: not black magic at all. And it was, um, the 15 00:01:01,400 --> 00:01:05,960 Speaker 1: polling wasn't even really that off. No, it was great. 16 00:01:06,000 --> 00:01:08,800 Speaker 1: There was a furious fear we'll talk about in a second, 17 00:01:08,800 --> 00:01:12,199 Speaker 1: but there's a furious reaction by the media just left 18 00:01:12,319 --> 00:01:16,960 Speaker 1: polling and polsters out to dry, saying like you you're terrible. 19 00:01:17,080 --> 00:01:22,440 Speaker 1: Your whole craft is is useless. As the pollsters went 20 00:01:22,480 --> 00:01:25,119 Speaker 1: back after election night on two thousand and sixteen, which, 21 00:01:25,280 --> 00:01:26,760 Speaker 1: by the way, is a bit of a surprise to 22 00:01:26,840 --> 00:01:32,120 Speaker 1: everybody involved. Um. Yeah, when the pollsters went back and 23 00:01:32,160 --> 00:01:33,800 Speaker 1: looked at their stuff, they said, wait a minute, no, 24 00:01:33,959 --> 00:01:36,800 Speaker 1: this is this is all fine. It was you guys, media, 25 00:01:37,240 --> 00:01:40,400 Speaker 1: You screwed up. You don't know what polling is or 26 00:01:40,440 --> 00:01:43,480 Speaker 1: what it does, or how to talk about it. Most importantly, Yeah, 27 00:01:43,520 --> 00:01:46,400 Speaker 1: and then you public, you have no idea what's going on. 28 00:01:46,480 --> 00:01:49,040 Speaker 1: You just see some percentages and you automatically leaked to 29 00:01:49,080 --> 00:01:51,400 Speaker 1: some conclusions and this is way off. So it's impartant 30 00:01:51,400 --> 00:01:55,120 Speaker 1: that the media was misrepresenting it. Some polls weren't very good. 31 00:01:55,480 --> 00:01:58,400 Speaker 1: And then, um, the public in general just needs to 32 00:01:58,440 --> 00:02:01,360 Speaker 1: be a bit more educated on statistics to understand what 33 00:02:01,400 --> 00:02:03,880 Speaker 1: they're hearing. And that's what we're here for. Because I 34 00:02:03,880 --> 00:02:08,120 Speaker 1: I took statistics three times in college, the same course 35 00:02:08,320 --> 00:02:11,399 Speaker 1: at Georgia. At Georgia, I took one of those classes. 36 00:02:11,600 --> 00:02:14,359 Speaker 1: I hated it, intro to statistics, right, yeah, boy, I 37 00:02:14,440 --> 00:02:17,640 Speaker 1: hated the class. The professor. Finally I walked up to 38 00:02:17,680 --> 00:02:19,520 Speaker 1: her on the last day of the third time, was 39 00:02:19,560 --> 00:02:22,480 Speaker 1: like please, and she bumped my d up to a 40 00:02:22,600 --> 00:02:25,519 Speaker 1: seat and I was I never looked back. She say 41 00:02:25,560 --> 00:02:27,760 Speaker 1: you have a one in four chance, and you're like, 42 00:02:27,840 --> 00:02:31,600 Speaker 1: but what does that mean? Right? What is four? But 43 00:02:31,760 --> 00:02:34,320 Speaker 1: so if I can understand this after doing some research, 44 00:02:34,360 --> 00:02:36,720 Speaker 1: then anybody can understand at least the gist of it 45 00:02:36,880 --> 00:02:40,280 Speaker 1: enough to understand polling and not be taken in by 46 00:02:40,639 --> 00:02:44,600 Speaker 1: bad representation of what poll results are. Yeah. So, if 47 00:02:44,639 --> 00:02:48,880 Speaker 1: you remember, in there were polsters saying or I'm sorry 48 00:02:49,320 --> 00:02:51,360 Speaker 1: and I'm gonna say that wrong over and over again. 49 00:02:51,400 --> 00:02:54,880 Speaker 1: You had media saying that Hillary Clinton is going to 50 00:02:54,960 --> 00:02:58,880 Speaker 1: win in a landslide. Um, she's got a chance to 51 00:02:58,880 --> 00:03:01,880 Speaker 1: win some set as high is ninety five, She's gonna 52 00:03:01,880 --> 00:03:05,600 Speaker 1: win the popular vote by three percentage points. Um, all 53 00:03:05,639 --> 00:03:08,919 Speaker 1: the all the battleground states in the Midwest, Um, she's 54 00:03:08,960 --> 00:03:12,639 Speaker 1: gonna win those narrowly. And it did not work out 55 00:03:12,639 --> 00:03:14,600 Speaker 1: that way. And like you said, there was a furor 56 00:03:14,639 --> 00:03:17,560 Speaker 1: over how could everyone be this wrong with the polling. 57 00:03:17,720 --> 00:03:20,839 Speaker 1: And there's man named Nate Silver, who everyone probably knows 58 00:03:20,840 --> 00:03:23,760 Speaker 1: at this point, who has made his name as a 59 00:03:23,880 --> 00:03:29,320 Speaker 1: data specialist and runs the five thirty eight blog and said, 60 00:03:29,400 --> 00:03:33,360 Speaker 1: you know what, um pulling is flawed. And that's probably 61 00:03:33,400 --> 00:03:36,360 Speaker 1: the first thing that everyone should understand is all polling 62 00:03:36,400 --> 00:03:39,360 Speaker 1: is a little bit flawed. Um, state polling is is 63 00:03:39,400 --> 00:03:42,760 Speaker 1: definitely a little more flawed than national polling. But here's 64 00:03:42,760 --> 00:03:47,560 Speaker 1: the deal, everybody, these polls from we're not only not 65 00:03:48,520 --> 00:03:51,840 Speaker 1: so far off, but historically, dating back to since nineteen 66 00:03:51,880 --> 00:03:54,880 Speaker 1: seventy two, they actually performed a little better than a 67 00:03:54,960 --> 00:03:58,480 Speaker 1: lot of elections. Yeah, and the state polling, while worse 68 00:03:58,560 --> 00:04:02,480 Speaker 1: than average, wasn't a far off from the average error rate. 69 00:04:02,640 --> 00:04:05,200 Speaker 1: So what do you what do you want? So there's 70 00:04:05,200 --> 00:04:07,080 Speaker 1: a lot of stuff, Like we said that there was 71 00:04:07,120 --> 00:04:08,880 Speaker 1: a lot of post mortem that was done on the 72 00:04:08,880 --> 00:04:11,640 Speaker 1: two thousand and sixteen polls and what what was gotten 73 00:04:11,640 --> 00:04:13,520 Speaker 1: wrong and what was gotten right, And we'll talk about 74 00:04:13,560 --> 00:04:17,720 Speaker 1: that later. But um, the point is is that overall 75 00:04:18,240 --> 00:04:21,760 Speaker 1: it wasn't that far off. And so the the idea 76 00:04:21,920 --> 00:04:24,960 Speaker 1: isn't that the polls failure, that there's something inherently flawed 77 00:04:24,960 --> 00:04:27,760 Speaker 1: with polling, or that there's even something inherently wrong with 78 00:04:27,800 --> 00:04:30,520 Speaker 1: the media. Like I want to go on record here, 79 00:04:30,640 --> 00:04:34,080 Speaker 1: especially in this climate, the media is not our enemy. 80 00:04:34,320 --> 00:04:38,960 Speaker 1: Like any healthy democracy needs a vital, robust, independent media 81 00:04:39,520 --> 00:04:43,680 Speaker 1: is free from bias as an objective to reality and 82 00:04:43,760 --> 00:04:47,720 Speaker 1: good injustice as possible. But there's also such a thing 83 00:04:47,720 --> 00:04:49,680 Speaker 1: as a twenty four hour news cycle, and you've got 84 00:04:49,680 --> 00:04:52,440 Speaker 1: to fill that. And that's given the rise of opinion 85 00:04:52,520 --> 00:04:56,240 Speaker 1: news and pundits and um and basically trying to capture 86 00:04:56,240 --> 00:04:59,240 Speaker 1: as much market share as possible, which is definitely the 87 00:04:59,279 --> 00:05:02,560 Speaker 1: wrong track for media in general. But I just want 88 00:05:02,560 --> 00:05:04,400 Speaker 1: to go on record, while we're gonna be kind of 89 00:05:04,600 --> 00:05:06,440 Speaker 1: beating the media up a little bit, that does not 90 00:05:06,560 --> 00:05:09,440 Speaker 1: mean that the media has inherently flawed or evil or 91 00:05:09,800 --> 00:05:12,600 Speaker 1: or seeks to um to to kill you and your 92 00:05:12,640 --> 00:05:16,960 Speaker 1: family and your family dog. So Silver goes back and 93 00:05:17,240 --> 00:05:19,200 Speaker 1: a bunch of people go back and look at um 94 00:05:19,440 --> 00:05:22,400 Speaker 1: history and kind of what went wrong here in as 95 00:05:22,440 --> 00:05:24,479 Speaker 1: far as the polling goes. He says, you know what, 96 00:05:24,560 --> 00:05:28,840 Speaker 1: we went back for the past twelve presidential cycles since 97 00:05:28,920 --> 00:05:31,440 Speaker 1: nineteen seventy two, and he said the polling air was 98 00:05:31,480 --> 00:05:35,600 Speaker 1: four point one. He said in that national polling air 99 00:05:35,839 --> 00:05:38,760 Speaker 1: was three point one, so technically by a full point 100 00:05:39,200 --> 00:05:42,279 Speaker 1: it was. It was a full point better. He said, Uh, 101 00:05:42,480 --> 00:05:44,800 Speaker 1: we predicted that she would win the popular vote by 102 00:05:44,839 --> 00:05:47,839 Speaker 1: three percentage points. She actually did win the popular vote 103 00:05:47,880 --> 00:05:52,320 Speaker 1: by two percentage points. Um. The state polls were the 104 00:05:52,360 --> 00:05:55,200 Speaker 1: real difference maker. They actually did underperform at a five 105 00:05:55,240 --> 00:05:59,120 Speaker 1: point to error rate, and that doesn't sound like that much. 106 00:05:59,160 --> 00:06:01,560 Speaker 1: I think the overall or rate for state poll since 107 00:06:01,640 --> 00:06:05,240 Speaker 1: nineteen four point eight, so four point eight five point 108 00:06:05,240 --> 00:06:08,120 Speaker 1: two doesn't sound like much. But if you're talking about 109 00:06:08,480 --> 00:06:11,279 Speaker 1: a percentage of error and just a handful of swing states, 110 00:06:11,960 --> 00:06:14,280 Speaker 1: that can make something look like a landslide even though 111 00:06:14,320 --> 00:06:17,400 Speaker 1: you lose a popular vote. That's exactly what happened, right, 112 00:06:17,440 --> 00:06:20,280 Speaker 1: That's exactly what happened, because you gotta remember Trump didn't 113 00:06:20,279 --> 00:06:23,240 Speaker 1: win the popular vote, he won the electoral college, and 114 00:06:23,279 --> 00:06:25,640 Speaker 1: it came down to those swing states. But the fact 115 00:06:25,680 --> 00:06:31,560 Speaker 1: that they were off just by point four points from 116 00:06:31,560 --> 00:06:34,719 Speaker 1: the average for the error rate um goes to show 117 00:06:34,760 --> 00:06:38,039 Speaker 1: you just how close that race actually was, which again 118 00:06:38,279 --> 00:06:41,560 Speaker 1: is the opposite of how it was being broadcast throughout 119 00:06:41,600 --> 00:06:44,000 Speaker 1: the election. It was supposed to be a landslide, like 120 00:06:44,160 --> 00:06:47,479 Speaker 1: Hillary Clinton might as well just be like taking measurements 121 00:06:47,520 --> 00:06:50,440 Speaker 1: for curtains in the oval office right now, Like it 122 00:06:50,480 --> 00:06:53,600 Speaker 1: was just that set So it was presented one way, 123 00:06:53,640 --> 00:06:56,280 Speaker 1: when in reality, if you really looked at the polls 124 00:06:56,279 --> 00:06:58,920 Speaker 1: and the polling results, if you looked at them with 125 00:06:59,160 --> 00:07:02,560 Speaker 1: a sober face, it was a much closer race than 126 00:07:02,600 --> 00:07:06,200 Speaker 1: it appeared or than it was being broadcast. I haven't 127 00:07:06,240 --> 00:07:11,600 Speaker 1: had a sober face since that night. So, uh, we 128 00:07:11,600 --> 00:07:14,160 Speaker 1: should talk about the margin of error. Um, in polling. 129 00:07:14,200 --> 00:07:17,440 Speaker 1: Anytime you see a poll, it's you. They talk about 130 00:07:17,480 --> 00:07:19,720 Speaker 1: the margin of air. It's usually plus plus or minus 131 00:07:19,760 --> 00:07:23,480 Speaker 1: three or four, and that is on each side. So 132 00:07:23,600 --> 00:07:26,720 Speaker 1: for each candidate's poll, uh. In other words, it could 133 00:07:26,760 --> 00:07:29,480 Speaker 1: be a potential like seven to eight point swing and 134 00:07:29,600 --> 00:07:32,480 Speaker 1: still be within that margin of error. So when Trump 135 00:07:32,600 --> 00:07:36,840 Speaker 1: is winning States by a point two percent margin or 136 00:07:36,880 --> 00:07:40,760 Speaker 1: a point five or a point seven percent margin, that's well, 137 00:07:40,840 --> 00:07:44,160 Speaker 1: well well well within the margin of error, right right, 138 00:07:44,240 --> 00:07:47,560 Speaker 1: So um, that margin of error, by the way, is 139 00:07:47,640 --> 00:07:49,600 Speaker 1: just bill tim. We'll talk about it a little more 140 00:07:49,640 --> 00:07:51,360 Speaker 1: and a little bit, but it's like there's just no 141 00:07:51,440 --> 00:07:54,080 Speaker 1: way around it. If to to get around any margin 142 00:07:54,080 --> 00:07:56,760 Speaker 1: of air, you would have to literally go through and 143 00:07:57,000 --> 00:08:01,280 Speaker 1: interview every single voter in America and then compile the 144 00:08:01,360 --> 00:08:06,480 Speaker 1: evidence or their their data perfectly without any miss keys 145 00:08:06,600 --> 00:08:09,280 Speaker 1: or anything like that. And it's just impossible. So everyone 146 00:08:09,320 --> 00:08:12,000 Speaker 1: accepts that any poll is going to have a margin error, 147 00:08:12,080 --> 00:08:14,960 Speaker 1: but you want to keep it within plus or minus 148 00:08:15,000 --> 00:08:19,560 Speaker 1: three points. Right be four. Yeah, So a little history 149 00:08:19,600 --> 00:08:25,000 Speaker 1: of polling. Um, we've always been, um, pretty spell bound 150 00:08:25,040 --> 00:08:26,960 Speaker 1: by poles in this country. We put a lot of 151 00:08:26,960 --> 00:08:30,760 Speaker 1: stock and polls, especially the presidential race. Um. The word 152 00:08:30,840 --> 00:08:32,839 Speaker 1: straw pole, if you've ever heard that, that comes from 153 00:08:32,880 --> 00:08:35,280 Speaker 1: the idea that you hold up a piece of straw 154 00:08:35,360 --> 00:08:37,400 Speaker 1: to see which way the wind is blowing. So a 155 00:08:37,440 --> 00:08:40,360 Speaker 1: straw pole is kind of like, here's how things stand 156 00:08:40,400 --> 00:08:43,240 Speaker 1: today on something like this is why the way the 157 00:08:43,240 --> 00:08:45,480 Speaker 1: wind is blowing today on this matter. Yeah, and they're 158 00:08:45,480 --> 00:08:47,560 Speaker 1: just kind of informal. They used to take them like 159 00:08:47,640 --> 00:08:50,360 Speaker 1: on train cars, as journalists would ask people who they 160 00:08:50,360 --> 00:08:52,319 Speaker 1: were on the train with, who they're going to vote for. 161 00:08:52,640 --> 00:08:55,199 Speaker 1: Nothing like formal or anything, but it it was. It 162 00:08:55,520 --> 00:08:58,480 Speaker 1: does kind of reveal how long standing our fascination with 163 00:08:58,559 --> 00:09:01,800 Speaker 1: poles really really is. Yeah, it got pretty serious in 164 00:09:01,840 --> 00:09:06,040 Speaker 1: the nineteen thirties, specifically the nineteen thirty six election, where 165 00:09:07,000 --> 00:09:09,199 Speaker 1: a literary digest it was, it was a pretty big 166 00:09:09,240 --> 00:09:13,800 Speaker 1: magazine at the time, pulled it's subscribers and it's just 167 00:09:13,880 --> 00:09:16,960 Speaker 1: kind of funny even seeing this sence they predicted a 168 00:09:17,040 --> 00:09:22,520 Speaker 1: landslide wind for Republican Republican alf landon over fd R. 169 00:09:23,400 --> 00:09:27,400 Speaker 1: So if you've never heard of alf Landon, uh, you 170 00:09:27,480 --> 00:09:31,040 Speaker 1: know I because alf Landon did not beat f DR. Uh. 171 00:09:31,080 --> 00:09:34,040 Speaker 1: And the magazine's editor said, you know what, we didn't 172 00:09:34,040 --> 00:09:36,120 Speaker 1: even think about the fact that we just pulled our 173 00:09:36,200 --> 00:09:40,360 Speaker 1: subscribers and that they're wealthy people are at least wealthier 174 00:09:40,440 --> 00:09:44,319 Speaker 1: on average, and they're probably going to vote Republicans. So um, 175 00:09:44,360 --> 00:09:47,040 Speaker 1: alf Landon was their man. Right. So if you go 176 00:09:47,120 --> 00:09:51,640 Speaker 1: out it's even today and just interview Republicans and say, hey, 177 00:09:52,200 --> 00:09:54,600 Speaker 1: who you're going to vote for, and then take that 178 00:09:54,679 --> 00:09:57,560 Speaker 1: results and apply it to the entire population of the nation, 179 00:09:57,760 --> 00:10:00,720 Speaker 1: you've got a flawed pole. And that's what Literary digested. 180 00:10:01,120 --> 00:10:04,319 Speaker 1: But in doing so, they established this kind of they 181 00:10:04,360 --> 00:10:06,800 Speaker 1: pointed out a real design flaw that now is just 182 00:10:07,200 --> 00:10:09,959 Speaker 1: one of the first basic things that anybody conducting a 183 00:10:10,040 --> 00:10:13,760 Speaker 1: pole gets rid of. That's right. Gallup came on the scene. 184 00:10:13,760 --> 00:10:18,319 Speaker 1: They galloped onto the scene. Uh so sorry, And they 185 00:10:18,320 --> 00:10:21,200 Speaker 1: were one of the first big polling companies to say, 186 00:10:21,240 --> 00:10:22,760 Speaker 1: all right, we gotta get this right. We gotta get 187 00:10:22,760 --> 00:10:25,720 Speaker 1: a representation of all of America here. So we're gonna 188 00:10:25,760 --> 00:10:27,880 Speaker 1: send our people door to door. We're gonna go to 189 00:10:27,920 --> 00:10:30,520 Speaker 1: every zip code in America, and they did that from 190 00:10:30,600 --> 00:10:35,120 Speaker 1: n to nineteen four UH and got basically within about 191 00:10:35,120 --> 00:10:38,560 Speaker 1: three percentage points, doing a pretty good job. UM, but 192 00:10:38,640 --> 00:10:40,839 Speaker 1: it was really expensive. So in the eighties, in the 193 00:10:40,880 --> 00:10:45,400 Speaker 1: mid eighties, they switched to calling people on telephone, which 194 00:10:45,640 --> 00:10:48,240 Speaker 1: which I mean that that's still today. That is the 195 00:10:48,320 --> 00:10:51,480 Speaker 1: gold standard is for a human being to dial up 196 00:10:51,520 --> 00:10:55,280 Speaker 1: another human being and ask them some questions. And we'll 197 00:10:55,320 --> 00:10:58,120 Speaker 1: talk a little more about it. But what what Gallup 198 00:10:58,280 --> 00:11:01,880 Speaker 1: does and what you does, and what a few others 199 00:11:02,160 --> 00:11:06,920 Speaker 1: UM do is it's called randomized sampling or probability sampling, 200 00:11:07,280 --> 00:11:10,520 Speaker 1: which is where you basically leave it to chance that 201 00:11:10,640 --> 00:11:14,840 Speaker 1: any voter registered voter in America is going to get 202 00:11:14,880 --> 00:11:18,320 Speaker 1: a phone call from you, So that what what Gallup 203 00:11:18,400 --> 00:11:21,720 Speaker 1: is doing and what Pew does is called randomized sampling 204 00:11:21,800 --> 00:11:26,080 Speaker 1: or probability sampling, where the any voter in America has 205 00:11:26,120 --> 00:11:29,920 Speaker 1: an equal chance of receiving a phone call from Gallop 206 00:11:30,000 --> 00:11:33,120 Speaker 1: or from Pew and being asked these questions. And it 207 00:11:33,200 --> 00:11:36,800 Speaker 1: worked pretty well for a while when they moved from 208 00:11:37,080 --> 00:11:39,960 Speaker 1: UH in person over to the phone, because they were 209 00:11:39,960 --> 00:11:43,520 Speaker 1: still asking people questions and they could still UM get 210 00:11:43,600 --> 00:11:45,559 Speaker 1: their answers and harass them, which is a big thing 211 00:11:45,640 --> 00:11:50,080 Speaker 1: is we'll see about the this type of sampling. Um, 212 00:11:50,240 --> 00:11:54,480 Speaker 1: the problem is when people started to use caller I D, 213 00:11:54,640 --> 00:11:57,600 Speaker 1: they stopped picking up the phone as much, and so 214 00:11:57,720 --> 00:12:01,520 Speaker 1: the response rate went down dramatic. Yeah, so they would 215 00:12:01,520 --> 00:12:04,679 Speaker 1: call people using random digit dialing, which is a computer 216 00:12:04,800 --> 00:12:07,880 Speaker 1: system where it fed in an area code and then 217 00:12:07,960 --> 00:12:11,439 Speaker 1: the first three digits and then randomly dialed the last four. 218 00:12:12,040 --> 00:12:13,640 Speaker 1: So you've got a pretty good start there on the 219 00:12:13,720 --> 00:12:16,840 Speaker 1: random sampling. But even then they said, you know what, 220 00:12:16,960 --> 00:12:19,280 Speaker 1: women tend to answer the phone more than men. So 221 00:12:19,360 --> 00:12:22,480 Speaker 1: to truly randomize that whenever whoever picks up the phone, 222 00:12:22,960 --> 00:12:24,600 Speaker 1: we have to then follow up and say we want 223 00:12:24,600 --> 00:12:27,040 Speaker 1: to talk to the person in the house who's had 224 00:12:27,040 --> 00:12:31,400 Speaker 1: the most recent birthday, further randomizing. Um. I got it 225 00:12:31,480 --> 00:12:34,040 Speaker 1: kind of a laugh about this because I don't know 226 00:12:34,120 --> 00:12:37,240 Speaker 1: that I've ever, literally ever seen my father pick up 227 00:12:37,280 --> 00:12:40,760 Speaker 1: a telephone in his life, or at least growing up 228 00:12:40,800 --> 00:12:42,560 Speaker 1: for the first eighteen years of my life, I don't 229 00:12:42,559 --> 00:12:44,800 Speaker 1: think I ever saw him answer the phone. It's all 230 00:12:44,880 --> 00:12:47,520 Speaker 1: ham radio, huh. Not not he went into that, but 231 00:12:48,160 --> 00:12:50,400 Speaker 1: just literally not not one time. He would just let 232 00:12:50,400 --> 00:12:52,880 Speaker 1: it ring. If no one was around if my mom 233 00:12:52,920 --> 00:12:55,720 Speaker 1: wasn't around to answer it, and granted it was usually 234 00:12:55,720 --> 00:12:57,640 Speaker 1: never for him, no one ever called to talk to him. 235 00:12:57,679 --> 00:13:00,240 Speaker 1: But I picked up on that and my friends used 236 00:13:00,280 --> 00:13:02,800 Speaker 1: to get really frustrated back before texting that I would 237 00:13:02,800 --> 00:13:06,600 Speaker 1: just never answer my phone. And I always just thought 238 00:13:06,600 --> 00:13:08,240 Speaker 1: it was an option, Like when the phone rings, it 239 00:13:08,240 --> 00:13:10,720 Speaker 1: doesn't mean you're obligated. It just means now you have 240 00:13:10,760 --> 00:13:13,160 Speaker 1: an option you can answer it or not. Well, technically 241 00:13:13,240 --> 00:13:16,480 Speaker 1: that's true. I mean like it depends no, you don't 242 00:13:16,520 --> 00:13:20,240 Speaker 1: have to answer the phone, but it depends on you know, 243 00:13:20,360 --> 00:13:23,360 Speaker 1: who in your life could possibly be calling. I didn't 244 00:13:23,360 --> 00:13:25,200 Speaker 1: think it was rude or anything. I just thought it 245 00:13:25,240 --> 00:13:28,959 Speaker 1: was literally, like, you know, I'm gonna hedge my beds here, 246 00:13:29,000 --> 00:13:30,880 Speaker 1: that one of my friends isn't stuck on the side 247 00:13:30,880 --> 00:13:33,080 Speaker 1: of the road. They can leave a message and if 248 00:13:33,080 --> 00:13:36,080 Speaker 1: they are, I'll go get them. So, UM, what you're 249 00:13:36,120 --> 00:13:40,079 Speaker 1: talking about, Chuck, is what's called a non response, and 250 00:13:40,400 --> 00:13:45,240 Speaker 1: that's factored into the response rate, which with phone pulling 251 00:13:45,320 --> 00:13:49,240 Speaker 1: from nine the nine eight until the nineteen nineties, um 252 00:13:49,240 --> 00:13:52,120 Speaker 1: it was manageable. You. I think the response rate peaked 253 00:13:52,160 --> 00:13:56,960 Speaker 1: at thirty six percent in n which is good. Now 254 00:13:57,000 --> 00:13:59,080 Speaker 1: it's down to like nine percent, because, like I said, 255 00:13:59,120 --> 00:14:01,840 Speaker 1: people have callorad D and if some unknown numbers calling, 256 00:14:01,880 --> 00:14:05,280 Speaker 1: you typically don't answer. And that actually affects things because 257 00:14:05,320 --> 00:14:07,679 Speaker 1: there is a certain kind of person who answers the 258 00:14:07,720 --> 00:14:12,000 Speaker 1: phone no matter what, and they are not like every 259 00:14:12,000 --> 00:14:16,080 Speaker 1: single American, and that actually factors into the kind of 260 00:14:16,120 --> 00:14:19,560 Speaker 1: pole you're connecting. Plus also you want like a certain 261 00:14:19,600 --> 00:14:24,120 Speaker 1: amount of responses. I think out of a sample size, 262 00:14:24,160 --> 00:14:28,200 Speaker 1: you want a minimum of eight hundred survey responses. And 263 00:14:28,360 --> 00:14:30,040 Speaker 1: back in the day, when you got a thirty six 264 00:14:30,040 --> 00:14:32,880 Speaker 1: percent response rate, meaning thirty six percent of those people 265 00:14:32,920 --> 00:14:35,200 Speaker 1: you called would answer the phone and go through all 266 00:14:35,240 --> 00:14:38,600 Speaker 1: of the questions and answer them fully and complete the survey. 267 00:14:39,080 --> 00:14:41,480 Speaker 1: Um since it was down to nine percent, you went 268 00:14:41,480 --> 00:14:45,240 Speaker 1: from having to call between two thousand people to to 269 00:14:45,560 --> 00:14:48,200 Speaker 1: up to nine thousand people now just to get eight 270 00:14:48,280 --> 00:14:51,080 Speaker 1: hundred surveys completed. And that made the whole thing a 271 00:14:51,200 --> 00:14:55,640 Speaker 1: lot more expensive. On the one hand, because it was expensive, 272 00:14:55,680 --> 00:14:57,760 Speaker 1: it meant that there were fewer and fewer companies that 273 00:14:57,800 --> 00:15:00,880 Speaker 1: could conduct these polls, which meant the polls you were 274 00:15:00,880 --> 00:15:04,120 Speaker 1: seeing were more and more legitimate. But on the other hand, 275 00:15:04,480 --> 00:15:08,000 Speaker 1: it also UM usually decreased sample size a little bit, because, 276 00:15:08,040 --> 00:15:10,680 Speaker 1: as as Gallup pointed out, like you can kind of 277 00:15:10,720 --> 00:15:13,120 Speaker 1: fiddle with the numbers a little bit with a smaller 278 00:15:13,200 --> 00:15:16,880 Speaker 1: response rate and smaller sample size. Yeah, and it also 279 00:15:16,960 --> 00:15:20,080 Speaker 1: led to robo calls because of expense, because of people 280 00:15:20,120 --> 00:15:23,440 Speaker 1: not answering their phone as much, and those systems. Uh. 281 00:15:23,600 --> 00:15:25,200 Speaker 1: I mean, I love how Dave Ruce put it. He 282 00:15:25,240 --> 00:15:28,320 Speaker 1: said they they range from okay to terrible, UM, and 283 00:15:28,360 --> 00:15:31,840 Speaker 1: how well they work online polls in these other new techniques. 284 00:15:32,480 --> 00:15:35,480 Speaker 1: But I think we should take a break and then 285 00:15:35,520 --> 00:15:39,800 Speaker 1: talk about, uh what I found the very interesting UM 286 00:15:39,920 --> 00:15:42,520 Speaker 1: way that they further randomized this thing from this point 287 00:15:42,520 --> 00:16:10,520 Speaker 1: forward right after this. All right, so we've already talked 288 00:16:10,520 --> 00:16:12,800 Speaker 1: about the fact that they randomly called someone, and then 289 00:16:12,800 --> 00:16:15,600 Speaker 1: they take one further step on that that call by saying, 290 00:16:15,640 --> 00:16:17,880 Speaker 1: let me speak with whoever had the most recent birthday, 291 00:16:18,800 --> 00:16:21,360 Speaker 1: even if it's I guess you're your three year old, right, 292 00:16:21,920 --> 00:16:23,880 Speaker 1: And and one other thing I kind of made mention 293 00:16:23,960 --> 00:16:28,000 Speaker 1: to it that I have to interject, dude, like harassing people, 294 00:16:28,320 --> 00:16:31,360 Speaker 1: like if you've been picked by this computer, if your 295 00:16:31,360 --> 00:16:33,800 Speaker 1: phone number has been picked, they're going to keep calling 296 00:16:33,840 --> 00:16:37,000 Speaker 1: you and calling you. And that is because, as a 297 00:16:37,040 --> 00:16:41,240 Speaker 1: person who doesn't normally participate in phone surveys, you are 298 00:16:41,280 --> 00:16:43,960 Speaker 1: a specific kind of person that you you can't be 299 00:16:44,080 --> 00:16:47,440 Speaker 1: left out of the population because you represent a large 300 00:16:47,560 --> 00:16:50,440 Speaker 1: number of people and they want your opinion. So part 301 00:16:50,480 --> 00:16:53,160 Speaker 1: of this phone standard of calling people is to call 302 00:16:53,240 --> 00:16:57,120 Speaker 1: them over and over and over again to basically harass 303 00:16:57,200 --> 00:16:59,920 Speaker 1: them into participating to get their answers for this serve 304 00:17:00,360 --> 00:17:03,760 Speaker 1: because it's as important, if not more important, sometimes than 305 00:17:03,840 --> 00:17:05,639 Speaker 1: the people who are like, oh, yeah, I'd love to 306 00:17:05,680 --> 00:17:10,000 Speaker 1: answer this phone survey. Two totally different kinds of people. Yeah. Absolutely. 307 00:17:10,280 --> 00:17:12,399 Speaker 1: And I was totally kidding, by the way, to the 308 00:17:12,400 --> 00:17:14,200 Speaker 1: listener when I said they will speak to a three 309 00:17:14,280 --> 00:17:16,639 Speaker 1: year old. They they asked the most recent birthday of 310 00:17:16,640 --> 00:17:19,879 Speaker 1: someone a voting age obviously, right. Um, So then you've 311 00:17:19,920 --> 00:17:22,520 Speaker 1: got a pretty pretty decent random sampling to begin with. 312 00:17:22,960 --> 00:17:27,200 Speaker 1: And then you have to start uh the process of waiting, uh, 313 00:17:27,280 --> 00:17:29,639 Speaker 1: which comes in a lot of different forms. Um. If 314 00:17:29,680 --> 00:17:32,560 Speaker 1: you want an example of like a really good political poll, 315 00:17:33,400 --> 00:17:36,280 Speaker 1: it's gonna be paid for by a neutral source. It's 316 00:17:36,320 --> 00:17:39,480 Speaker 1: not gonna be um like you know, a CNN pole 317 00:17:39,560 --> 00:17:41,840 Speaker 1: or a Fox News poll or a superpack or anything 318 00:17:41,880 --> 00:17:44,320 Speaker 1: like that. Um, you're gonna have a random sample of 319 00:17:44,359 --> 00:17:47,199 Speaker 1: the public, which we just talked about. You're gonna be 320 00:17:47,320 --> 00:17:50,960 Speaker 1: dialing cell phones and landlines these days. That's a big one. Also, 321 00:17:51,040 --> 00:17:53,199 Speaker 1: they'll ask you if you have a cell phone and 322 00:17:53,280 --> 00:17:55,480 Speaker 1: a landline, and if you say yes, I have both, 323 00:17:55,800 --> 00:17:59,399 Speaker 1: they're going to adjust your response based on the fact 324 00:17:59,440 --> 00:18:02,720 Speaker 1: that you had a higher chance of being selected because 325 00:18:03,000 --> 00:18:06,400 Speaker 1: you have two numbers that the computer could have picked right. 326 00:18:06,560 --> 00:18:08,960 Speaker 1: And another thing is, like you mentioned, they're gonna keep 327 00:18:08,960 --> 00:18:13,800 Speaker 1: calling you the best ones, use live interviewers still. And 328 00:18:13,840 --> 00:18:15,640 Speaker 1: then what they want to do, and this last one 329 00:18:15,680 --> 00:18:18,520 Speaker 1: is really important, is you're they're gonna try and improve 330 00:18:18,560 --> 00:18:21,960 Speaker 1: the accuracy of the results by waiting the response to match. 331 00:18:22,000 --> 00:18:23,560 Speaker 1: What they want to do is just match a real 332 00:18:23,600 --> 00:18:29,200 Speaker 1: world demographic, age race, your income level, your education level, 333 00:18:29,680 --> 00:18:32,360 Speaker 1: and all of that stuff is factored in, and all 334 00:18:32,400 --> 00:18:36,720 Speaker 1: the stuff is weighed out because, um, well we'll talk 335 00:18:36,760 --> 00:18:40,320 Speaker 1: about it, but you know, there are many different kinds 336 00:18:40,320 --> 00:18:42,400 Speaker 1: of Americans, and if you want a really good sampling 337 00:18:42,400 --> 00:18:45,240 Speaker 1: of different kinds of Americans, you're gonna, like, like you said, 338 00:18:45,280 --> 00:18:47,199 Speaker 1: I have to fidget with the numbers to make it 339 00:18:47,280 --> 00:18:53,280 Speaker 1: a true representative population right. So, um, because even if 340 00:18:53,280 --> 00:18:57,120 Speaker 1: you just get it exactly right demographically and waited, which, 341 00:18:57,200 --> 00:18:58,760 Speaker 1: like you said, we'll talk about some more in a second, 342 00:18:58,960 --> 00:19:01,200 Speaker 1: you still have that marge and of error. And again 343 00:19:01,240 --> 00:19:05,000 Speaker 1: that's that um, you know, plus or minus three points, 344 00:19:05,000 --> 00:19:07,320 Speaker 1: and that means that it could be cent or it 345 00:19:07,320 --> 00:19:11,920 Speaker 1: could be they don't know, but somewhere between that, most 346 00:19:11,960 --> 00:19:13,920 Speaker 1: of your answers are going to be the like, the 347 00:19:13,960 --> 00:19:17,240 Speaker 1: correct answers somewhere in there. That's what that means with 348 00:19:17,359 --> 00:19:20,080 Speaker 1: that that margin of error, And the reason that that's 349 00:19:20,119 --> 00:19:24,600 Speaker 1: built in is because it is basically impossible to perfectly 350 00:19:25,000 --> 00:19:29,400 Speaker 1: represent the larger population through random sampling. You're just not 351 00:19:29,480 --> 00:19:33,320 Speaker 1: going to pick everybody correctly just by the fact that 352 00:19:33,359 --> 00:19:36,840 Speaker 1: it's random and it's a sample. Yeah, and that's important 353 00:19:36,880 --> 00:19:39,560 Speaker 1: because um, like that's why you hear so much hay 354 00:19:39,560 --> 00:19:42,600 Speaker 1: being made over a double digit lead in a poll um, 355 00:19:42,640 --> 00:19:45,239 Speaker 1: which Biden had sort of semi recently. I know it's 356 00:19:45,280 --> 00:19:47,560 Speaker 1: it's gotten a lot tighter since then, but you know, 357 00:19:47,600 --> 00:19:50,240 Speaker 1: when Biden was up by I think like ten percentage points, 358 00:19:50,600 --> 00:19:54,280 Speaker 1: people were flipping out because you know, like we said, 359 00:19:54,320 --> 00:19:56,920 Speaker 1: it's plus or minus four for each candidate. So that's 360 00:19:56,960 --> 00:19:59,960 Speaker 1: a total of eight. And so basically the press start 361 00:20:00,119 --> 00:20:04,359 Speaker 1: screaming like he's outside of the margin of error. Everybody 362 00:20:05,480 --> 00:20:08,439 Speaker 1: like nothing can beat him, right right, yeah, But now 363 00:20:08,560 --> 00:20:11,480 Speaker 1: things are back within that margin. I saw PBS News 364 00:20:11,520 --> 00:20:15,040 Speaker 1: Our UM they interview Mark Shields and David Brooks. Um. 365 00:20:15,160 --> 00:20:18,160 Speaker 1: Brooks is a New York Times columnists and I think 366 00:20:18,160 --> 00:20:21,919 Speaker 1: Mark Shields is an independent columnist. And one of them 367 00:20:22,200 --> 00:20:25,480 Speaker 1: actually said, and this is in July, America has clearly 368 00:20:25,520 --> 00:20:27,960 Speaker 1: made up its mind on who's going to be the 369 00:20:28,000 --> 00:20:31,400 Speaker 1: next president. And I was like, this is July. Did 370 00:20:31,400 --> 00:20:34,040 Speaker 1: you not learn anything from two thousand and sixteen or 371 00:20:34,080 --> 00:20:37,760 Speaker 1: you I couldn't believe that those words, And there's a 372 00:20:38,280 --> 00:20:41,520 Speaker 1: matter of factly, yeah, it's irresponsible. And there's been studies 373 00:20:41,520 --> 00:20:45,960 Speaker 1: about this too that have suggested that that words like that, 374 00:20:45,960 --> 00:20:50,040 Speaker 1: that um polls that say chance of winning, that this 375 00:20:50,160 --> 00:20:54,639 Speaker 1: kind of stuff like actually has a negative impact on 376 00:20:54,720 --> 00:20:56,760 Speaker 1: the leader because it makes people think, well, I don't 377 00:20:56,760 --> 00:20:58,119 Speaker 1: need to go out and vote. Everybody else is going 378 00:20:58,160 --> 00:21:01,280 Speaker 1: to go vote, and the turnout might be lower than otherwise. 379 00:21:01,320 --> 00:21:03,880 Speaker 1: There's also people that just who well, there's people who 380 00:21:03,920 --> 00:21:07,919 Speaker 1: dispute that. They say, yes, it makes sense intuitively and anecdotally, 381 00:21:08,160 --> 00:21:11,240 Speaker 1: but we've yet to actually see genuine data that that 382 00:21:11,280 --> 00:21:14,720 Speaker 1: says clearly that this has this effect. But it's something 383 00:21:14,760 --> 00:21:17,680 Speaker 1: that's still being studied right now whether it actually does 384 00:21:17,800 --> 00:21:20,000 Speaker 1: or not well. And I also saw an article the 385 00:21:20,000 --> 00:21:23,520 Speaker 1: other day about the the quote unquote silent majority, and 386 00:21:23,560 --> 00:21:25,840 Speaker 1: that another reason those polls were so wrong back then 387 00:21:25,960 --> 00:21:29,240 Speaker 1: and they're saying are probably wrong now is because there 388 00:21:29,280 --> 00:21:33,240 Speaker 1: are there they They say that there's a substantial block 389 00:21:33,280 --> 00:21:37,520 Speaker 1: of voters who vary privately and secretly vote for Trump. Yeah, 390 00:21:37,560 --> 00:21:41,320 Speaker 1: they're the term for them among pollsters as shy Trump voters. 391 00:21:42,160 --> 00:21:44,440 Speaker 1: They won't admit that they're going to vote for Trump, 392 00:21:44,520 --> 00:21:46,280 Speaker 1: but they're going to vote for Trump, and that that 393 00:21:46,359 --> 00:21:50,160 Speaker 1: affects polls. I saw that that's actually not been proven 394 00:21:50,200 --> 00:21:53,880 Speaker 1: to actually exist. Um, but I think it was a Pew. 395 00:21:54,160 --> 00:21:56,359 Speaker 1: There's a really great Pew article. If this stuff is 396 00:21:56,400 --> 00:22:00,720 Speaker 1: speaking to you at all, go check out Pews Key 397 00:22:00,800 --> 00:22:03,800 Speaker 1: Things to Know about Election Polling in the US and 398 00:22:03,800 --> 00:22:05,520 Speaker 1: Now has a bunch of great links that you should 399 00:22:05,560 --> 00:22:09,720 Speaker 1: follow in there. And there's also Sideline UM. They have 400 00:22:10,040 --> 00:22:13,760 Speaker 1: Surveys and Polling, which is a guide for journalists to polling. 401 00:22:13,800 --> 00:22:15,760 Speaker 1: But I I found out you don't actually have to 402 00:22:15,760 --> 00:22:18,119 Speaker 1: be a journalist to read it online. So if you 403 00:22:18,119 --> 00:22:20,320 Speaker 1: want to go check those out, they have some great like, 404 00:22:20,480 --> 00:22:23,399 Speaker 1: um like just some breakdowns of some of the stuff 405 00:22:23,440 --> 00:22:25,919 Speaker 1: we're talking about, but also about how to read polls 406 00:22:25,960 --> 00:22:28,520 Speaker 1: and what to trust and look for in general. Uh. 407 00:22:28,560 --> 00:22:31,480 Speaker 1: And then a little known fact, PEW was actually originally 408 00:22:31,560 --> 00:22:35,720 Speaker 1: called uh pupu until six when Star Wars came out 409 00:22:36,640 --> 00:22:38,920 Speaker 1: and they're like, we gotta change our name now, guys. Yeah, 410 00:22:39,000 --> 00:22:41,879 Speaker 1: I can't do it, man, it is dant o rama 411 00:22:41,920 --> 00:22:46,400 Speaker 1: today with you. Huh. So back to the waiting thing. Um. 412 00:22:46,440 --> 00:22:48,240 Speaker 1: And by the way, we should mention that Gallup said 413 00:22:48,240 --> 00:22:52,159 Speaker 1: if they wanted to um increase that sample size and 414 00:22:52,200 --> 00:22:54,320 Speaker 1: actually get the margin of error down to like plus 415 00:22:54,400 --> 00:22:56,760 Speaker 1: our minus two, that they could do that, but that 416 00:22:56,800 --> 00:23:00,760 Speaker 1: would be like a literal increase in the cost. So like, 417 00:23:00,840 --> 00:23:03,480 Speaker 1: everyone just please live with plus or minus three or 418 00:23:03,480 --> 00:23:06,359 Speaker 1: four points. Yeah, and now everybody generally does. And and 419 00:23:06,440 --> 00:23:08,919 Speaker 1: Dave uses this really good example. Dave Russ helped us 420 00:23:08,960 --> 00:23:12,000 Speaker 1: out with this, and he said, um, this this margin 421 00:23:12,080 --> 00:23:14,760 Speaker 1: of air is best understood where if you selected a 422 00:23:14,840 --> 00:23:18,520 Speaker 1: hundred marbles UM five there's a jar five five hundred 423 00:23:18,520 --> 00:23:21,560 Speaker 1: blue marbles, and you pick out a hundred of them. Um, 424 00:23:21,720 --> 00:23:23,800 Speaker 1: you might pick out fifty of each one time. And 425 00:23:23,800 --> 00:23:29,480 Speaker 1: then what he said, five hundred marbles. Oh no, I'm sorry, 426 00:23:29,480 --> 00:23:33,439 Speaker 1: a thousand marbles. I've lost my marbles. Yes, there's a 427 00:23:33,480 --> 00:23:36,240 Speaker 1: thousand marbles. Okay, five hundred are red and five hundred 428 00:23:36,280 --> 00:23:39,040 Speaker 1: of blue. Your task, Chuck, is to pick out a hundred. 429 00:23:39,400 --> 00:23:40,960 Speaker 1: So you go to the trouble picking out a hundred 430 00:23:41,000 --> 00:23:42,800 Speaker 1: fifty or red, fifty or blue. And I say do 431 00:23:42,880 --> 00:23:46,320 Speaker 1: it again, and this time is forty seven and fifty three, 432 00:23:46,760 --> 00:23:50,320 Speaker 1: and keep saying again again, right, and I smack my 433 00:23:50,440 --> 00:23:52,840 Speaker 1: riding crop on the desk. That's that you're sitting at 434 00:23:53,960 --> 00:23:56,479 Speaker 1: times because you gets super turned on. Yeah, I did 435 00:23:56,480 --> 00:23:59,280 Speaker 1: it a hundred times because dear leader told me to. 436 00:24:00,200 --> 00:24:02,119 Speaker 1: And at the end you get a little bell curve 437 00:24:02,880 --> 00:24:07,720 Speaker 1: and basically a plus or minus four. Right, So yeah, 438 00:24:07,920 --> 00:24:12,080 Speaker 1: almost all of them, this is what's confidence involved. Almost 439 00:24:12,119 --> 00:24:15,200 Speaker 1: all of them are going to fall in that bell curve. 440 00:24:15,400 --> 00:24:17,080 Speaker 1: There's going to be some outler, it's just gonna be 441 00:24:17,119 --> 00:24:19,800 Speaker 1: that one time where it was just absolutely insane. You 442 00:24:19,800 --> 00:24:23,919 Speaker 1: actually picked one hundred red marbles randomly blindfolded from this 443 00:24:24,080 --> 00:24:28,200 Speaker 1: jar that that's that's so insignificant statistically, it's just such 444 00:24:28,240 --> 00:24:30,640 Speaker 1: an outlier. But almost all the we're gonna be in there. 445 00:24:30,680 --> 00:24:33,480 Speaker 1: So when you're pulling like this large group of people, 446 00:24:33,800 --> 00:24:38,240 Speaker 1: like American voters, and of them are falling within a 447 00:24:38,280 --> 00:24:41,840 Speaker 1: couple of percentage points of either side of this this middle, 448 00:24:42,520 --> 00:24:45,080 Speaker 1: you can pretty much feel confident about that. And that 449 00:24:45,200 --> 00:24:48,280 Speaker 1: is the basis of of election polling, of political polling, 450 00:24:48,400 --> 00:24:50,800 Speaker 1: of all polling, really that they have this built in 451 00:24:50,880 --> 00:24:54,119 Speaker 1: margin that they know exists, but everybody can live with it. 452 00:24:54,359 --> 00:24:57,160 Speaker 1: The problem is is when you're hovering around that fifty 453 00:24:57,560 --> 00:25:00,880 Speaker 1: mark and you're talking about a two party system, one 454 00:25:00,880 --> 00:25:03,800 Speaker 1: of them has like and the other one has but 455 00:25:03,840 --> 00:25:08,159 Speaker 1: there's a plus or minus of like two points. It 456 00:25:08,200 --> 00:25:11,280 Speaker 1: means we have no idea. And some people would say, well, 457 00:25:11,280 --> 00:25:14,000 Speaker 1: why even do polling, because what you're showing there is 458 00:25:14,040 --> 00:25:16,920 Speaker 1: not who's going to win. That's not the point of polling. 459 00:25:17,280 --> 00:25:19,680 Speaker 1: But the point of polling is to take a snapshot 460 00:25:19,720 --> 00:25:22,959 Speaker 1: of how America or whoever you're polling is feeling that 461 00:25:23,040 --> 00:25:26,520 Speaker 1: moment about who to elect, about what laws to pass, 462 00:25:26,560 --> 00:25:31,960 Speaker 1: about religion, about um. The Cleveland Indians. It doesn't matter, right, 463 00:25:32,520 --> 00:25:35,600 Speaker 1: like the the the that's what a poll does. But 464 00:25:35,680 --> 00:25:38,800 Speaker 1: you can pervert polls into making them talk a different 465 00:25:38,880 --> 00:25:42,159 Speaker 1: language and say, hey, he look at this percentage. You 466 00:25:42,240 --> 00:25:44,680 Speaker 1: take these polls and you convert them into something else. 467 00:25:44,760 --> 00:25:47,480 Speaker 1: Now you have something like a chance this person is 468 00:25:47,480 --> 00:25:50,600 Speaker 1: gonna win. Go shout that, Wolf Splitz heer, and Wolf 469 00:25:50,640 --> 00:25:54,920 Speaker 1: Flitzer goes and shouts it as loud as he can. So, uh, 470 00:25:54,960 --> 00:25:56,639 Speaker 1: we need to talk a little bit more about waiting. 471 00:25:56,680 --> 00:25:58,800 Speaker 1: I mentioned earlier that there's other things they do to 472 00:25:58,920 --> 00:26:02,320 Speaker 1: sort of, um tip the scale, and that sounds like 473 00:26:02,320 --> 00:26:03,960 Speaker 1: a bad term, so I guess I shouldn't say it 474 00:26:04,040 --> 00:26:06,280 Speaker 1: that way. But um things they do to make it 475 00:26:06,600 --> 00:26:11,560 Speaker 1: equitable and a true representative of the American population. For instance, UM, 476 00:26:11,640 --> 00:26:14,760 Speaker 1: African American voters make up twelve percent of voters. So 477 00:26:14,800 --> 00:26:16,520 Speaker 1: if they did a poll and in the end they 478 00:26:16,560 --> 00:26:19,480 Speaker 1: only got six percent of respondents so were African American, 479 00:26:19,920 --> 00:26:23,240 Speaker 1: then they just double it. Basically, Um, if the respondents 480 00:26:23,280 --> 00:26:27,200 Speaker 1: were overwhelmingly Caucasian, they would weight that down to their 481 00:26:27,200 --> 00:26:33,120 Speaker 1: true representative number, which is about I think sixty six percent. Yeah, 482 00:26:33,240 --> 00:26:37,800 Speaker 1: the electorate is white, and of U of white people 483 00:26:37,840 --> 00:26:40,640 Speaker 1: respond or eight percent of the people that respond are white, 484 00:26:40,680 --> 00:26:43,520 Speaker 1: then they're going to kick that down. And again, this 485 00:26:43,600 --> 00:26:46,879 Speaker 1: is just adjusting the poll to the proper weight, so 486 00:26:46,960 --> 00:26:51,520 Speaker 1: you have a really legitimate snapshot. And you know, if 487 00:26:51,520 --> 00:26:55,920 Speaker 1: it sounds crazy that there using a thousand people's responses, 488 00:26:56,680 --> 00:26:58,879 Speaker 1: uh and drawing that out to the size of the 489 00:26:58,960 --> 00:27:03,280 Speaker 1: voting population of America, it is. But if you're a statistician, 490 00:27:03,960 --> 00:27:07,520 Speaker 1: it isn't you know. I mean, you know, it reliably 491 00:27:07,560 --> 00:27:09,720 Speaker 1: works as long as you present it with plus or 492 00:27:09,720 --> 00:27:13,120 Speaker 1: minus this margin of error. Um, it's as crazy as 493 00:27:13,200 --> 00:27:15,480 Speaker 1: just an average Joe on the street. It does to 494 00:27:15,520 --> 00:27:17,439 Speaker 1: be like they ask a thousand people and we're supposed 495 00:27:17,480 --> 00:27:20,800 Speaker 1: to know and extrapolate that, and a statistician who our 496 00:27:21,040 --> 00:27:23,800 Speaker 1: number wants and data wants would say, yeah, that's exactly 497 00:27:23,840 --> 00:27:26,240 Speaker 1: what that means. Shut up, that's really all. That's really 498 00:27:26,280 --> 00:27:28,199 Speaker 1: all you need. But it really is a testimony to 499 00:27:28,359 --> 00:27:31,719 Speaker 1: the power of those those statistics in that data and 500 00:27:31,760 --> 00:27:34,679 Speaker 1: the analysis of them. Yeah, waiting is really important. It 501 00:27:34,760 --> 00:27:38,960 Speaker 1: goes far beyond just like age political party. Um. I 502 00:27:39,000 --> 00:27:42,840 Speaker 1: think gallup uses eight different variables. The New York Times 503 00:27:42,840 --> 00:27:46,399 Speaker 1: see in a college poll uses ten, like and they 504 00:27:46,440 --> 00:27:50,080 Speaker 1: include things like marital status and home ownership PU uses 505 00:27:50,160 --> 00:27:53,399 Speaker 1: twelve variables. Um. They ask things like do you have 506 00:27:53,440 --> 00:27:55,919 Speaker 1: home internet access? To you have volunteers or do you 507 00:27:56,000 --> 00:27:59,520 Speaker 1: engage in volunteerism um, And all of these things have 508 00:27:59,640 --> 00:28:02,760 Speaker 1: been owned to be associated. So like, if you're a 509 00:28:02,800 --> 00:28:07,160 Speaker 1: white woman age sixty five to seventy five who volunteers 510 00:28:07,280 --> 00:28:09,919 Speaker 1: twice a month and lives in the suburbs, you're a 511 00:28:10,040 --> 00:28:13,359 Speaker 1: very specific person where you you there's a group of 512 00:28:13,400 --> 00:28:15,959 Speaker 1: people out there who vote like a certain way, and 513 00:28:16,040 --> 00:28:18,920 Speaker 1: you represent like all those people with that. So they 514 00:28:18,960 --> 00:28:22,399 Speaker 1: they'll wait the results based on these additional questions that 515 00:28:22,400 --> 00:28:25,600 Speaker 1: you're into. They don't just ask you do you are 516 00:28:25,600 --> 00:28:27,920 Speaker 1: you going to vote for Trump or Biden? And there's 517 00:28:27,960 --> 00:28:31,560 Speaker 1: also built into that question a really important point, are 518 00:28:31,600 --> 00:28:34,120 Speaker 1: you going to vote? Yeah, that's a that's a huge 519 00:28:34,119 --> 00:28:36,000 Speaker 1: thing we haven't talked about. It's one thing to pull 520 00:28:36,160 --> 00:28:42,000 Speaker 1: registered voters. But here in America, somehow, uh, presidential elections 521 00:28:42,080 --> 00:28:47,360 Speaker 1: only get about six turnout still, which is shameful, shameful 522 00:28:47,400 --> 00:28:51,040 Speaker 1: and crazy. But um, that's another podcast. But uh so, 523 00:28:51,200 --> 00:28:53,920 Speaker 1: most of the really really good polls drilled down and 524 00:28:54,200 --> 00:28:56,560 Speaker 1: to get a real, real good representation of what might 525 00:28:56,600 --> 00:29:00,880 Speaker 1: actually happen. They try to drill down to whether or 526 00:29:00,880 --> 00:29:04,240 Speaker 1: not you're most likely to actually vote, because he cares 527 00:29:04,280 --> 00:29:06,400 Speaker 1: what your pain is if you're not gonna vote, and 528 00:29:06,440 --> 00:29:09,440 Speaker 1: they and I mean they generally take your word for 529 00:29:09,520 --> 00:29:12,960 Speaker 1: it that you're telling the truth, you know. Um yeah, 530 00:29:13,120 --> 00:29:16,840 Speaker 1: but they do have like nine I think pu Yeah, 531 00:29:16,920 --> 00:29:21,400 Speaker 1: Pew has nine questions that they basically used to establish 532 00:29:21,520 --> 00:29:23,920 Speaker 1: that you're you are planning on voting, like you're actually 533 00:29:24,000 --> 00:29:26,400 Speaker 1: going to vote, You're not full of hot air, you know. Yeah. 534 00:29:26,560 --> 00:29:28,560 Speaker 1: I don't know those questions are, but I imagine they 535 00:29:28,760 --> 00:29:31,560 Speaker 1: have to do with do you know where you're pulling places? 536 00:29:31,600 --> 00:29:34,560 Speaker 1: Do you have transportation? Stuff? Like I was thinking they 537 00:29:34,560 --> 00:29:37,600 Speaker 1: were going to be like, are you really really gonna vote? 538 00:29:37,680 --> 00:29:41,200 Speaker 1: Was like question three, and they just kept adding release 539 00:29:41,600 --> 00:29:47,080 Speaker 1: right you So, um, So you've got these these people 540 00:29:47,120 --> 00:29:50,480 Speaker 1: who have been called and they have answered these questions, 541 00:29:50,520 --> 00:29:53,360 Speaker 1: and they have participated in this survey whether they wanted 542 00:29:53,400 --> 00:29:57,960 Speaker 1: to or not, and they've they've finally done it. Built 543 00:29:58,000 --> 00:30:00,480 Speaker 1: into that margin of error built into the poll. Is 544 00:30:00,520 --> 00:30:03,000 Speaker 1: that understandable margin verror that just comes from the fact 545 00:30:03,040 --> 00:30:07,080 Speaker 1: that it's a randomized sample, right, But what PE and 546 00:30:07,160 --> 00:30:11,240 Speaker 1: any other legitimate UM group polling group will point out 547 00:30:11,360 --> 00:30:14,400 Speaker 1: is that the margin is actually greater than that. That 548 00:30:14,520 --> 00:30:17,520 Speaker 1: the margin of error for the average poll according to Pew, 549 00:30:17,680 --> 00:30:21,280 Speaker 1: is that it's something more like six points, not not 550 00:30:21,520 --> 00:30:23,960 Speaker 1: three or four, it's actually six. And the reason why 551 00:30:24,000 --> 00:30:27,760 Speaker 1: it's built on top of that margin of error that's 552 00:30:27,800 --> 00:30:30,560 Speaker 1: that's automatically part of the poll just by the virtue 553 00:30:30,600 --> 00:30:34,360 Speaker 1: of it being a randomized sample. Are things like the 554 00:30:34,400 --> 00:30:39,840 Speaker 1: person typing in the wrong key accidentally that those kind 555 00:30:39,880 --> 00:30:42,800 Speaker 1: of things add up, or that the question isn't worded 556 00:30:43,000 --> 00:30:46,880 Speaker 1: clearly enough that anybody who hears it knows the intent 557 00:30:47,000 --> 00:30:49,240 Speaker 1: and knows what their answer is, that there's some sort 558 00:30:49,240 --> 00:30:53,640 Speaker 1: of um miscommunication involved. There's also things that they can't control, 559 00:30:53,720 --> 00:30:57,000 Speaker 1: for like people who have pseudo opinions who don't want 560 00:30:57,040 --> 00:30:59,640 Speaker 1: to sound dumb, so they just answer yes or no 561 00:30:59,800 --> 00:31:02,480 Speaker 1: by sense something they really don't care about either way 562 00:31:02,600 --> 00:31:04,920 Speaker 1: UM and because they don't actually have an opinion, that 563 00:31:04,960 --> 00:31:08,360 Speaker 1: actually that that waits things the wrong way. So when 564 00:31:08,400 --> 00:31:11,280 Speaker 1: you add all these stuff these things up, UM, you 565 00:31:11,400 --> 00:31:17,240 Speaker 1: have these additional um uh errors that lead to different 566 00:31:17,400 --> 00:31:20,440 Speaker 1: to like a bias overall in in the the UM 567 00:31:20,840 --> 00:31:24,800 Speaker 1: the poll, which can affect the outcome. But again, the 568 00:31:24,880 --> 00:31:27,840 Speaker 1: companies that have the money to conduct like these genuinely 569 00:31:28,000 --> 00:31:32,560 Speaker 1: big gold standard polls, are they they know enough to 570 00:31:32,600 --> 00:31:34,920 Speaker 1: know how to kind of factor control for those as 571 00:31:34,960 --> 00:31:38,680 Speaker 1: much as possible. But still, what Pew says is, if 572 00:31:38,720 --> 00:31:40,960 Speaker 1: you're listening to a poll and somebody says plus or 573 00:31:40,960 --> 00:31:43,920 Speaker 1: minds three points, you should probably go ahead and double 574 00:31:44,000 --> 00:31:48,280 Speaker 1: that in your mind, double it in your mind, double 575 00:31:48,320 --> 00:31:52,960 Speaker 1: your W, your pleasure wr fun W, your margin error. 576 00:31:54,720 --> 00:31:56,880 Speaker 1: So let's take a break and we're gonna come back 577 00:31:56,920 --> 00:32:00,480 Speaker 1: and talk about what exactly they think went wrong with 578 00:32:00,520 --> 00:32:27,480 Speaker 1: those state polls right after this, Sorry, George, all right, 579 00:32:27,640 --> 00:32:34,000 Speaker 1: So I think it's generally acknowledged that the um and 580 00:32:34,040 --> 00:32:36,120 Speaker 1: again I want to say the polling was was off, 581 00:32:36,160 --> 00:32:38,440 Speaker 1: but apparently the pulling wasn't off, but the way it 582 00:32:38,480 --> 00:32:41,560 Speaker 1: was reported on was off. But what really happened in 583 00:32:42,120 --> 00:32:45,280 Speaker 1: seen what was off was the state polling, and what 584 00:32:45,400 --> 00:32:49,160 Speaker 1: they think they've, like you said, gone back and obsessed 585 00:32:49,240 --> 00:32:53,239 Speaker 1: over these polls since then, um, you know, because they 586 00:32:53,240 --> 00:32:56,560 Speaker 1: were already statistical walks, but when something like this happens, 587 00:32:57,000 --> 00:32:59,680 Speaker 1: they really sort of get worked into a dander and 588 00:33:00,040 --> 00:33:02,040 Speaker 1: get to the bottom of it. I mean people were 589 00:33:02,080 --> 00:33:04,480 Speaker 1: calling for the end of polling. She said it was 590 00:33:04,520 --> 00:33:08,400 Speaker 1: a failed profession. Basically, he was like, I'm getting rich 591 00:33:08,440 --> 00:33:12,560 Speaker 1: off this man. Yeah, we can't end polling. Jimmy Pugh 592 00:33:12,760 --> 00:33:16,640 Speaker 1: was like, stop stop talking like that. So what happened 593 00:33:16,640 --> 00:33:21,680 Speaker 1: in is uh they think is that uh, a lot 594 00:33:21,800 --> 00:33:26,240 Speaker 1: of non educated white people came out in big, big 595 00:33:26,320 --> 00:33:30,640 Speaker 1: numbers for Donald Trump. And that was a sort of 596 00:33:30,680 --> 00:33:34,480 Speaker 1: a new not a new factor because they had always 597 00:33:34,480 --> 00:33:38,480 Speaker 1: talked about college education, but a new factor in how 598 00:33:38,680 --> 00:33:41,160 Speaker 1: outsized of a factor that was. It had never been 599 00:33:41,200 --> 00:33:44,960 Speaker 1: that outsized. And so all these state posters they didn't 600 00:33:44,960 --> 00:33:47,200 Speaker 1: wait it and they didn't adjust their polls to reflect 601 00:33:47,600 --> 00:33:51,360 Speaker 1: this um fact that college educated people are more likely 602 00:33:51,400 --> 00:33:54,520 Speaker 1: going to respond to these surveys. So their polls were 603 00:33:54,560 --> 00:33:58,000 Speaker 1: just off. Yeah, and they knew that college educated people 604 00:33:58,000 --> 00:34:00,880 Speaker 1: were more likely to respond to the survey. That wasn't 605 00:34:00,920 --> 00:34:05,800 Speaker 1: news to them. What caught them sleeping was that they 606 00:34:05,800 --> 00:34:10,080 Speaker 1: had not picked up on the fact that this group 607 00:34:10,560 --> 00:34:15,680 Speaker 1: of people, um, non college educated white voters, We're going 608 00:34:15,719 --> 00:34:18,360 Speaker 1: to go to the polls in numbers like never before, 609 00:34:18,440 --> 00:34:21,120 Speaker 1: and that they were going to vote for Trump. They 610 00:34:21,120 --> 00:34:22,719 Speaker 1: did not pick up on that that was brand new, 611 00:34:23,000 --> 00:34:26,759 Speaker 1: like that didn't exist before. Trump basically brought up a 612 00:34:26,760 --> 00:34:31,359 Speaker 1: new electorate that helped get him elected, especially in battleground 613 00:34:31,440 --> 00:34:35,640 Speaker 1: states like Wisconsin, in Michigan, uh, in Indiana, although I 614 00:34:35,640 --> 00:34:37,440 Speaker 1: think in the enda he was a shoeing because of pens. 615 00:34:37,880 --> 00:34:40,960 Speaker 1: But the the these this group of voters that did 616 00:34:40,960 --> 00:34:44,239 Speaker 1: not exist, with this line between college educated and non 617 00:34:44,280 --> 00:34:48,320 Speaker 1: college educated white voters, that that partisan gulf hadn't existed 618 00:34:48,360 --> 00:34:51,200 Speaker 1: before election day. The pollsters didn't pick up on it, 619 00:34:51,320 --> 00:34:54,439 Speaker 1: and so they didn't wait those responses because they never 620 00:34:54,520 --> 00:34:59,000 Speaker 1: had to wait the responses before based on college education. Yeah, 621 00:34:59,080 --> 00:35:03,120 Speaker 1: so suburb exurbs and especially the rural vote counted like 622 00:35:03,200 --> 00:35:06,680 Speaker 1: it had never counted before. UM, which is obviously why 623 00:35:06,719 --> 00:35:10,560 Speaker 1: you see what's going on right now, like a very 624 00:35:10,600 --> 00:35:14,080 Speaker 1: hard pushed by the Trump campaign to um to get 625 00:35:14,239 --> 00:35:17,279 Speaker 1: these the same people out again. Uh and in the 626 00:35:17,320 --> 00:35:19,799 Speaker 1: way that they do that that is the nicest way 627 00:35:19,800 --> 00:35:23,640 Speaker 1: I can put it there, genuinely is so UM. Yeah. 628 00:35:23,840 --> 00:35:27,000 Speaker 1: So the idea that that there was all this was 629 00:35:27,080 --> 00:35:29,880 Speaker 1: already kind of a close race, a closer race than 630 00:35:30,000 --> 00:35:36,320 Speaker 1: was being broadcast. UM, that these these electoral um, huge 631 00:35:36,440 --> 00:35:41,840 Speaker 1: electoral battleground states that got flipped. Uh. That was basically 632 00:35:41,920 --> 00:35:44,520 Speaker 1: the reason that UM Trump was able to take the 633 00:35:44,560 --> 00:35:49,319 Speaker 1: electoral College. But the the idea is that these voters 634 00:35:49,560 --> 00:35:52,120 Speaker 1: kind of came out of nowhere and voted for Trump, 635 00:35:52,360 --> 00:35:54,560 Speaker 1: and that there were some other things that happened to 636 00:35:55,360 --> 00:35:59,560 Speaker 1: UM that the pollster didn't anticipate. One that the undecided voters, 637 00:35:59,600 --> 00:36:03,840 Speaker 1: people who said I'm legitimately undecided at this point a 638 00:36:03,880 --> 00:36:07,400 Speaker 1: week before the election, Uh, from whatever, they broke hard 639 00:36:07,440 --> 00:36:09,680 Speaker 1: in favor of Trump. On election date when they made 640 00:36:09,680 --> 00:36:13,960 Speaker 1: their decision, they voted for Trump that hadn't been predicted. Um. 641 00:36:14,000 --> 00:36:16,040 Speaker 1: That was another big one. And then one of the 642 00:36:16,040 --> 00:36:19,080 Speaker 1: other things too, is that the polls were just doing 643 00:36:19,120 --> 00:36:22,839 Speaker 1: what polls do, which is sometimes they're right, sometimes they're wrong. 644 00:36:24,040 --> 00:36:27,440 Speaker 1: But polls had gotten so good in the two thousand 645 00:36:27,480 --> 00:36:32,319 Speaker 1: oughts that people came to to be overconfident in their 646 00:36:32,320 --> 00:36:35,760 Speaker 1: ability to predict and pick winners. And the two thousand 647 00:36:35,719 --> 00:36:38,400 Speaker 1: and sixteen grates reminded us, like, polling is not perfect, 648 00:36:38,480 --> 00:36:42,239 Speaker 1: let's stop pretending it is. Yeah, and it's UM. A 649 00:36:42,280 --> 00:36:44,239 Speaker 1: lot of it has to do with, like we've been 650 00:36:44,320 --> 00:36:46,279 Speaker 1: kind of harping on the way the media presents it. 651 00:36:46,800 --> 00:36:48,160 Speaker 1: And then a lot of that has to do with 652 00:36:48,200 --> 00:36:52,400 Speaker 1: just our conditioned how we're conditioned to look at things 653 00:36:52,440 --> 00:36:57,040 Speaker 1: like underdogs. Um, and it's different in politics. And I 654 00:36:57,080 --> 00:37:01,880 Speaker 1: remember when these aggregators, especially at five thirty eight, Uh, 655 00:37:01,920 --> 00:37:04,520 Speaker 1: they had these predictive models, and they started talking about 656 00:37:04,560 --> 00:37:06,839 Speaker 1: the fact that and I think the Washington Post even 657 00:37:06,840 --> 00:37:10,680 Speaker 1: wrote a good comparison to sports. And you know, if 658 00:37:10,719 --> 00:37:14,000 Speaker 1: someone has a is a real big underdog going into 659 00:37:14,080 --> 00:37:17,120 Speaker 1: like a super Bowl or a World Series and they 660 00:37:17,800 --> 00:37:21,440 Speaker 1: end up winning, people don't get angry and go after 661 00:37:21,560 --> 00:37:24,280 Speaker 1: the people who said they had a fifteen or twenty 662 00:37:24,320 --> 00:37:27,040 Speaker 1: percent chance of winning. They just said, wow, what a story, 663 00:37:27,040 --> 00:37:32,400 Speaker 1: the underdog one. But there are so few presidential elections, uh, 664 00:37:32,440 --> 00:37:35,799 Speaker 1: you know, one every four years that it's it's the 665 00:37:35,880 --> 00:37:38,560 Speaker 1: same thing, but people just look at it differently. Like 666 00:37:38,719 --> 00:37:42,200 Speaker 1: an underdog like Trump was an underdog that supposedly had 667 00:37:42,239 --> 00:37:45,399 Speaker 1: like a fifteen to thirty percent chance of winning. Some 668 00:37:45,440 --> 00:37:49,000 Speaker 1: people said, one, yeah, well that's ridiculous, But a thirty 669 00:37:49,000 --> 00:37:51,360 Speaker 1: percent chance of winning is a real shot at winning, 670 00:37:51,680 --> 00:37:53,600 Speaker 1: for sure. Yeah, that's the way it's framed. It doesn't 671 00:37:53,600 --> 00:37:56,759 Speaker 1: seem that way in politics, no, And so that's one thing. 672 00:37:56,840 --> 00:37:59,160 Speaker 1: But another thing is that we shouldn't even be talking 673 00:37:59,200 --> 00:38:04,040 Speaker 1: about president vential elections with like chance of winning, chance 674 00:38:04,120 --> 00:38:06,680 Speaker 1: of winning like that is not how we should present it. 675 00:38:06,960 --> 00:38:08,920 Speaker 1: We and that's not how we used to present it. 676 00:38:09,160 --> 00:38:12,600 Speaker 1: We used to present it saying like this poll found that, um, 677 00:38:12,760 --> 00:38:16,600 Speaker 1: that Clinton was going to lead Trump of forty eight 678 00:38:16,640 --> 00:38:19,480 Speaker 1: percent or something like that, plus or minus two points, 679 00:38:19,520 --> 00:38:22,080 Speaker 1: and that would have shown you like, Okay, well this 680 00:38:22,120 --> 00:38:25,080 Speaker 1: is a really close race, way closer than I think, um. 681 00:38:25,200 --> 00:38:30,200 Speaker 1: And that's that there's my information. Not The problem is 682 00:38:30,520 --> 00:38:34,520 Speaker 1: that you can take that same statistic chance of winning 683 00:38:34,719 --> 00:38:38,000 Speaker 1: plus or minus of four point um margin of error. 684 00:38:38,440 --> 00:38:41,239 Speaker 1: If you convert that to a normal distribution, you come 685 00:38:41,280 --> 00:38:46,080 Speaker 1: up with a probability of a win. That's the problem 686 00:38:46,600 --> 00:38:50,320 Speaker 1: is that the statistics that are being being the data 687 00:38:50,360 --> 00:38:53,799 Speaker 1: that's being produced by these polls, are being converted in 688 00:38:53,880 --> 00:38:56,440 Speaker 1: ways that they shouldn't be, and then that's what the 689 00:38:56,480 --> 00:38:59,520 Speaker 1: media jumps on. That's what the public lapse up because 690 00:38:59,600 --> 00:39:02,840 Speaker 1: that is the horse race statistic, and eighty four percent 691 00:39:02,920 --> 00:39:05,640 Speaker 1: chance of winning, a fifteen percent chance of winning, that's 692 00:39:05,640 --> 00:39:08,200 Speaker 1: what we we think about. That's what we look at. 693 00:39:08,239 --> 00:39:11,120 Speaker 1: And so rather than realizing that actually this is a 694 00:39:11,120 --> 00:39:15,520 Speaker 1: close race plus or minds four points, we see eighty 695 00:39:15,520 --> 00:39:18,000 Speaker 1: four percent chance of winning, and that's a foregone conclusion 696 00:39:18,040 --> 00:39:21,400 Speaker 1: that that person is going to win. That's that, ultimately 697 00:39:21,480 --> 00:39:25,560 Speaker 1: is where the media and the public are culpable for this. Yeah, 698 00:39:25,920 --> 00:39:28,359 Speaker 1: I don't think uh, I don't think they were meant 699 00:39:28,400 --> 00:39:32,040 Speaker 1: to be extrapolated like that to begin with. And that 700 00:39:32,200 --> 00:39:36,520 Speaker 1: you know, polls are valuable, but like, I haven't looked 701 00:39:36,560 --> 00:39:40,959 Speaker 1: at any polls, and partially because of the way went down. 702 00:39:41,760 --> 00:39:43,839 Speaker 1: Um And in fact, for the past week, I've taken 703 00:39:43,880 --> 00:39:49,040 Speaker 1: a complete uh internet news and social media break and 704 00:39:49,080 --> 00:39:52,880 Speaker 1: it's been pretty great actually because yeah, I mean I 705 00:39:52,920 --> 00:39:57,040 Speaker 1: literally haven't looked at a single news thing. Very sadly 706 00:39:57,040 --> 00:39:59,680 Speaker 1: found out that Chadwick Boseman passed away like three days 707 00:39:59,719 --> 00:40:03,600 Speaker 1: after word. Like that's how how dark I've gone, uh, 708 00:40:03,640 --> 00:40:05,719 Speaker 1: and not looking at the Internet unless it's something that 709 00:40:05,760 --> 00:40:08,120 Speaker 1: brings me joy, which is to say, you know, old 710 00:40:08,239 --> 00:40:11,840 Speaker 1: led Zeppelin and Van Halen YouTube videos. I was looking 711 00:40:11,920 --> 00:40:15,440 Speaker 1: up classic Mad magazine covers of the eighties. That's all 712 00:40:15,440 --> 00:40:17,600 Speaker 1: I've been doing is if it doesn't bring me joy 713 00:40:17,719 --> 00:40:21,120 Speaker 1: on the internet, I'm not doing it. Um. And you know, 714 00:40:21,120 --> 00:40:23,000 Speaker 1: I gotta break that soon, because I do think you 715 00:40:23,040 --> 00:40:26,120 Speaker 1: should be active and involved in in in the know. 716 00:40:26,320 --> 00:40:30,040 Speaker 1: But yeah, but taking a break fairly regularly is definitely 717 00:40:30,200 --> 00:40:33,479 Speaker 1: mentally healthy. But that aside, I haven't I'm not looking 718 00:40:33,480 --> 00:40:36,000 Speaker 1: at any polls and I don't care what any poll says. 719 00:40:36,680 --> 00:40:39,720 Speaker 1: We'll see. So I was I was thinking very similar 720 00:40:39,760 --> 00:40:44,600 Speaker 1: stuff too, and um, like, what what's the point of poles? Okay, 721 00:40:44,640 --> 00:40:46,680 Speaker 1: well I finally found it. If you look that up 722 00:40:46,680 --> 00:40:49,920 Speaker 1: on Google, there's there's just very little on it. But 723 00:40:49,960 --> 00:40:52,880 Speaker 1: I found somebody who who explained it pretty well. I 724 00:40:52,960 --> 00:40:56,080 Speaker 1: thought that, Um, poles aren't meant to tell you who's 725 00:40:56,120 --> 00:40:58,960 Speaker 1: going to win. They're not. They're not forecasting models, like 726 00:40:59,000 --> 00:41:01,880 Speaker 1: I said before, They're to be like a snapshot of 727 00:41:01,920 --> 00:41:06,160 Speaker 1: how whoever you're polling feels at the moment right um. 728 00:41:06,239 --> 00:41:11,280 Speaker 1: And in doing that, because you are sampling American people 729 00:41:11,440 --> 00:41:15,840 Speaker 1: and these are independent news organizations typically who are carrying 730 00:41:15,840 --> 00:41:20,400 Speaker 1: out these these polls, you get to tell everybody else 731 00:41:20,480 --> 00:41:24,120 Speaker 1: how America is feeling. Rather than the leaders saying I'll 732 00:41:24,200 --> 00:41:26,920 Speaker 1: decide how you're feeling. I can decide what you want 733 00:41:27,000 --> 00:41:29,600 Speaker 1: and what you need and what you think is important. 734 00:41:30,040 --> 00:41:33,920 Speaker 1: Polls prevent that from happening by telling the rest of 735 00:41:33,960 --> 00:41:35,920 Speaker 1: the people, Hey, this is how everybody else is feeling 736 00:41:36,000 --> 00:41:38,439 Speaker 1: right now too. And in some ways it is kind 737 00:41:38,440 --> 00:41:42,239 Speaker 1: of sheepish, where you know, the ideas like, oh, you know, 738 00:41:42,360 --> 00:41:44,560 Speaker 1: is that supposed to sway my opinion that everybody's going 739 00:41:44,640 --> 00:41:46,920 Speaker 1: to vote for this person and not for that person. 740 00:41:47,000 --> 00:41:49,560 Speaker 1: That should have no bearing or impact on your vote, 741 00:41:49,920 --> 00:41:51,960 Speaker 1: And it feels like that that's how polls are used sometimes. 742 00:41:51,960 --> 00:41:53,560 Speaker 1: But if you step back and look and see that 743 00:41:53,600 --> 00:41:57,600 Speaker 1: they're actually kind of an important part of of sharing 744 00:41:57,600 --> 00:42:00,680 Speaker 1: what other people are thinking, rather than being told what 745 00:42:00,680 --> 00:42:04,160 Speaker 1: we're thinking or you know, what, what to think, then 746 00:42:04,200 --> 00:42:07,920 Speaker 1: they actually are pretty legitimate in that sense. Yeah, well, 747 00:42:07,960 --> 00:42:11,839 Speaker 1: you know, I say, take your polls and sit on it. Well, 748 00:42:11,880 --> 00:42:14,040 Speaker 1: one more thing we get. We cannot talk about polling 749 00:42:14,040 --> 00:42:16,640 Speaker 1: and not talk about Internet polling real quick. This is 750 00:42:16,680 --> 00:42:20,240 Speaker 1: a completely different style of polling than's ever been done before. 751 00:42:20,800 --> 00:42:24,239 Speaker 1: Rather than a randomized sample, you actually just say hey, 752 00:42:24,280 --> 00:42:26,040 Speaker 1: you want to take the survey, and people click it. 753 00:42:26,120 --> 00:42:30,000 Speaker 1: So it's called opting in opt in surveying, and very 754 00:42:30,040 --> 00:42:33,719 Speaker 1: specific kinds of people take surveys on purpose on the Internet, 755 00:42:34,160 --> 00:42:37,439 Speaker 1: so they really are because they're new. They're really now 756 00:42:37,560 --> 00:42:41,040 Speaker 1: figuring out how to wait these things are not UM 757 00:42:41,160 --> 00:42:43,719 Speaker 1: and how to how to use them because they can 758 00:42:43,840 --> 00:42:48,040 Speaker 1: produce legitimate UM data, but it depends on who's conducting 759 00:42:48,040 --> 00:42:50,600 Speaker 1: the poll, how if they know what they're doing, that 760 00:42:50,680 --> 00:42:53,120 Speaker 1: kind of stuff. But just like everything else that the 761 00:42:53,360 --> 00:42:58,359 Speaker 1: moving things online is democratize polling, and so anybody can 762 00:42:58,400 --> 00:43:00,960 Speaker 1: conduct a poll now and basically enter the news cycle. 763 00:43:01,000 --> 00:43:04,160 Speaker 1: That's how Kid Rock almost became a senator in Michigan 764 00:43:04,200 --> 00:43:07,200 Speaker 1: for a second there. But so on the one hand, 765 00:43:07,239 --> 00:43:09,160 Speaker 1: it's good, but it's also we're in a big period 766 00:43:09,200 --> 00:43:11,719 Speaker 1: of disruption as far as polling is concerned. So for you, 767 00:43:11,800 --> 00:43:14,840 Speaker 1: the polling consumer, either go like Chalk and just stop 768 00:43:14,960 --> 00:43:19,680 Speaker 1: listening to polls altogether, or UM look for things like transparency. 769 00:43:19,760 --> 00:43:22,640 Speaker 1: Do you recognize the company or the name that produced 770 00:43:22,640 --> 00:43:26,040 Speaker 1: the poll. Are they sharing their data, like how the 771 00:43:26,160 --> 00:43:29,600 Speaker 1: questions exactly were worded, what their population size was, how 772 00:43:29,640 --> 00:43:32,480 Speaker 1: they waited at all this stuff? UM, if the if 773 00:43:32,520 --> 00:43:34,799 Speaker 1: there's all, if all that stuff is included, you can 774 00:43:34,840 --> 00:43:38,440 Speaker 1: probably trust the poll. And then UM, beyond that, just 775 00:43:38,520 --> 00:43:41,440 Speaker 1: remember what you're looking at that this isn't a predictor 776 00:43:41,480 --> 00:43:43,759 Speaker 1: of who's gonna win. It was a snapshot for a 777 00:43:43,880 --> 00:43:46,640 Speaker 1: very very brief moment of a very specific sample of 778 00:43:46,680 --> 00:43:50,799 Speaker 1: America to just to show how people would vote right then. 779 00:43:51,120 --> 00:43:53,360 Speaker 1: And it was right then too. This is not election 780 00:43:53,440 --> 00:43:55,400 Speaker 1: day we're talking about. Yeah, And I'm you know, I 781 00:43:55,480 --> 00:43:58,400 Speaker 1: want to be clear. I'm not poopooing polls. I just uh, 782 00:43:58,440 --> 00:44:00,680 Speaker 1: they're they're valid and useful, but I just don't care 783 00:44:00,719 --> 00:44:03,040 Speaker 1: to look at them right now. I understand. Yeah, that's 784 00:44:03,160 --> 00:44:06,320 Speaker 1: that's my jam. Well, you got anything else about polls, 785 00:44:06,480 --> 00:44:08,920 Speaker 1: nothing else about powells. Well, if you want to know 786 00:44:08,960 --> 00:44:12,120 Speaker 1: about polls, uh, start looking around and you go check 787 00:44:12,160 --> 00:44:16,120 Speaker 1: out Pew stuff and uh sidelines stuff and all that stuff. Um. 788 00:44:16,200 --> 00:44:18,799 Speaker 1: And since I said stuff three times here it comes 789 00:44:18,800 --> 00:44:27,200 Speaker 1: from will stillt Kid or a candy man. So, uh, 790 00:44:27,239 --> 00:44:29,920 Speaker 1: this is from Keiley Price. And Keily says this, Hi, guys, 791 00:44:29,920 --> 00:44:32,759 Speaker 1: I'm writing today not only to confess my unending love 792 00:44:32,800 --> 00:44:35,000 Speaker 1: for stuff you should know, but also to share a 793 00:44:35,000 --> 00:44:37,960 Speaker 1: link to some black owned bookstores. It would be so 794 00:44:38,000 --> 00:44:41,560 Speaker 1: cool if all of your listeners purchased your book. She 795 00:44:41,600 --> 00:44:45,600 Speaker 1: should just say period. Uh. Comma from a black owned 796 00:44:45,600 --> 00:44:48,239 Speaker 1: bookstore couldn't agree more. By the way, a couple of 797 00:44:48,280 --> 00:44:50,759 Speaker 1: podcasters that I listened to while I wait for stuff. 798 00:44:50,800 --> 00:44:53,439 Speaker 1: You should know have books out and coming out soon, 799 00:44:53,480 --> 00:44:56,560 Speaker 1: and they encourage their listeners to support black owned businesses 800 00:44:56,560 --> 00:44:58,680 Speaker 1: through the purchase of their book to win Win. I 801 00:44:58,680 --> 00:45:00,359 Speaker 1: don't know why it's taking me so long to think 802 00:45:00,400 --> 00:45:02,680 Speaker 1: to write this to you guys. I blame it on 803 00:45:03,040 --> 00:45:07,400 Speaker 1: Corona madness. But last, but not least, I'll say I 804 00:45:07,480 --> 00:45:09,120 Speaker 1: love the End of the World with Josh Clark and 805 00:45:09,160 --> 00:45:12,000 Speaker 1: movie Crush as well. Any chance to hear you guys 806 00:45:12,320 --> 00:45:14,719 Speaker 1: talk as a chance worth taking. When we get a 807 00:45:14,719 --> 00:45:16,919 Speaker 1: COVID vaccine and you guys can do your live shows again, 808 00:45:17,280 --> 00:45:19,920 Speaker 1: please come to Nashville. Oh yeah, for sure. I think 809 00:45:19,960 --> 00:45:24,080 Speaker 1: we planned on Nashville. Yeah, Nashville got scuttled by COVID 810 00:45:24,320 --> 00:45:26,799 Speaker 1: this time around. You're going to come now? We might 811 00:45:26,840 --> 00:45:29,279 Speaker 1: not ever be able to come. No, I know it's 812 00:45:29,280 --> 00:45:31,040 Speaker 1: super close to Atlanta. To lose my mind if I 813 00:45:31,040 --> 00:45:33,320 Speaker 1: got to see you guys here all the best, Keiley 814 00:45:33,360 --> 00:45:37,680 Speaker 1: Price and so. Keiley sent a link to a handy 815 00:45:37,719 --> 00:45:40,960 Speaker 1: website that lists black owned bookstores near you. I made 816 00:45:40,960 --> 00:45:43,759 Speaker 1: a little uh you are else shortener to make it 817 00:45:43,800 --> 00:45:46,359 Speaker 1: easier on everyone. Oh, let's have it so you can 818 00:45:46,400 --> 00:45:48,520 Speaker 1: go to bit dot lee slash s y s k 819 00:45:48,800 --> 00:45:52,839 Speaker 1: b l m uh and find black owned bookstores near 820 00:45:52,840 --> 00:45:55,880 Speaker 1: you to purchase Stuff you Should Know, an incomplete compendium 821 00:45:55,880 --> 00:45:59,520 Speaker 1: of mostly interesting things at the very least. Um, we 822 00:45:59,600 --> 00:46:01,719 Speaker 1: like to kurch people to go to indie bound dot 823 00:46:01,800 --> 00:46:05,279 Speaker 1: org and support indie bookstores. I don't know if there 824 00:46:05,360 --> 00:46:10,120 Speaker 1: is an actual black owned indie bookstore website, but I 825 00:46:10,120 --> 00:46:13,520 Speaker 1: would imagine most of the black owned bookstores are indie bookstores. 826 00:46:14,840 --> 00:46:18,359 Speaker 1: Uh yeah, probably, So check it out. Bit dot lee 827 00:46:18,760 --> 00:46:21,799 Speaker 1: slash s y s k v l M. Go out 828 00:46:21,880 --> 00:46:24,279 Speaker 1: and buy our book. Everybody. You're gonna love it. It's 829 00:46:24,320 --> 00:46:27,719 Speaker 1: really great, m um, and thanks thanks for that, Chuck, 830 00:46:27,760 --> 00:46:29,560 Speaker 1: and thanks for setting us up for that too, Kiley, 831 00:46:29,840 --> 00:46:33,320 Speaker 1: much appreciated. We'll see you in Nashville. I guess Kiely 832 00:46:33,360 --> 00:46:35,280 Speaker 1: will be the one, like you said, losing your mind 833 00:46:35,600 --> 00:46:38,839 Speaker 1: in the crowd. If you want to lose your mind 834 00:46:38,880 --> 00:46:41,120 Speaker 1: on us via email, we love that kind of thing. 835 00:46:41,239 --> 00:46:44,360 Speaker 1: Kind of um. You can send it off to stuff 836 00:46:44,400 --> 00:46:50,920 Speaker 1: Podcasts at iHeart radio dot com. Stuff you Should Know 837 00:46:51,000 --> 00:46:53,400 Speaker 1: is a production of iHeart Radio's How Stuff Works. For 838 00:46:53,480 --> 00:46:56,160 Speaker 1: more podcasts for my Heart Radio visit the iHeart Radio app, 839 00:46:56,239 --> 00:46:58,880 Speaker 1: Apple podcasts, or wherever you listen to your favorite shows.