Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A few words about FiveThirtyEight

natesilver.net

Post reply on HN
Print view View original

131–140 of 140 posts

Re: A few words about FiveThirtyEight

#131

Post by snickerbockers »

iuyhtgbd wrote: post #14
snickerbockers wrote: post #8

Earlier quoted context omitted.

Nobody who thinks they can pin a probability on an event that only gets sampled once should ever be taken seriously.

This is such tired debate that comes up whenever 538 is mentioned in discussion. Polls sample an election's outcome many times throughout the campaign. Statistics works. You can't know the future but you can predict it with error bars. 51/49 or 70/30 should tell you there's a very real chance of a Trump victory. People get bent out of shape about 538 but it's usually because they're misinterpreting the prediction, no…

>Statistics works

it does but just because nate silver calls something "statistics" doesn't necessarily mean that it is. If Donald Trump has a 20% chance of winning that means that we can hold the election 100 times and expect that he'll win approximately 20 elections and lose the other 80. Which is ridiculous because each voter is not an independent random variable.

Re: A few words about FiveThirtyEight

#132

Post by int_19h »

genewitch wrote: post #107
kelnos wrote: post #97

Earlier quoted context omitted.

> the German upper house, the Bundesrat, represents the German states (Länder), and although (unlike the Australian and US Senates) it does give more populous states a greater number of seats, the number of seats is still out of proportion to population: in Bremen there are 223,830 people per a seat, compared to 2,977,586 people per a seat in North Rhine-Westphalia. To be fair, though, in the US, the House also has u…

I've heard this my entire life, too. However, having lived more places than just California, I see California as having undue influence on the entire country. Prop 65 warnings pop up on things outside of California. I've even seen stuff labeled as CARB outside of California. These are trivial examples, but both of those things are California legalities. If Louisiana had undue influence on the US, more packaging would…

California is larger than many countries, and more productive than many countries as well (at least as far as GDP goes). Of course it should have a proportionally large influence on the rest of the country; it's not "undue".

Re: A few words about FiveThirtyEight

#133

Post by int_19h »

JumpCrisscross wrote: post #88
aaronbrethorst wrote: post #63

Earlier quoted context omitted.

Counties don't vote and Trump's popular vote "mandate" is smaller than Clinton's popular vote win in 2016. Here's a fun stat: literally 40 states have a population that is less than the population of Los Angeles county alone. Why doesn't Los Angeles itself have 80 senators? https://en.wikipedia.org/wiki/2016_United_States_presidentia... https://en.wikipedia.org/wiki/2024_United_States_presidentia... Setting aside 200…

> why doesn't Los Angeles itself have 80 senators? The electoral college internally balances the power of a population against the difficulty of holding land. Look at New York State, where NYC mostly holds court. If it were a country you’d see rebellion. Because while the city outnumbers the country, it’s culturally more similar to itself than the country, and that in practice leaves lots of people disenfranchised. (…

Even if you buy into the whole notion of "representing geography", the problem is that state boundaries ceased to be representative of any meaningful kind of political distinction a long time ago, as evidenced by the massive red/blue splits in many states. It's not just NY - you can see the same thing in other large states, e.g. in WA where the split is geographical within state boundaries - west of the Cascades is very blue, east is very red. Nor is it unique to blue states - TX has the same exact issue with blue counties having a lot of population that is effectively not represented at all.

Unless and until this is fixed, there's no meaningful "geographic representation" in the Senate, so it's strictly a negative.

Re: A few words about FiveThirtyEight

#134

Post by skissane »

int_19h wrote: post #132
genewitch wrote: post #107

Earlier quoted context omitted.

I've heard this my entire life, too. However, having lived more places than just California, I see California as having undue influence on the entire country. Prop 65 warnings pop up on things outside of California. I've even seen stuff labeled as CARB outside of California. These are trivial examples, but both of those things are California legalities. If Louisiana had undue influence on the US, more packaging would…

California is larger than many countries, and more productive than many countries as well (at least as far as GDP goes). Of course it should have a proportionally large influence on the rest of the country; it's not "undue".

I think a valid question is why is California so big...

There's North Carolina and South Carolina, North Dakota and South Dakota, Virginia and West Virginia – why not North California and South California?

Re: A few words about FiveThirtyEight

#135

Post by fsckboy »

>538-style of election coverage in 2008... I'm not really convinced about what it adds to the conversation around elections

I'm not really convinced that conversations around elections add anything. for me, 538-style coverage is great substitute for having to listen to myriad opinions that are generally facially flawed, and neither a representative sample.

Re: A few words about FiveThirtyEight

#137

Post by iuyhtgbd »

snickerbockers wrote: post #131
iuyhtgbd wrote: post #14

Earlier quoted context omitted.

This is such tired debate that comes up whenever 538 is mentioned in discussion. Polls sample an election's outcome many times throughout the campaign. Statistics works. You can't know the future but you can predict it with error bars. 51/49 or 70/30 should tell you there's a very real chance of a Trump victory. People get bent out of shape about 538 but it's usually because they're misinterpreting the prediction, no…

>Statistics works it does but just because nate silver calls something "statistics" doesn't necessarily mean that it is. If Donald Trump has a 20% chance of winning that means that we can hold the election 100 times and expect that he'll win approximately 20 elections and lose the other 80. Which is ridiculous because each voter is not an independent random variable.

Each eligible voter is a random variable, independence aside. Silver's model does not operate on the level of the voter however. A random variable is a very flexible abstraction, almost anything can be a random variable if you can find a way to measure it. Polls are a measurement. They're imperfect, but all measurements contain error.

It's not statistics because any authority says it is, it's statistics because it starts with a measure of probability (aggregated polls) and builds an interpretation on top of it. That's what statistics is. It can be good statistics or bad statistics, but that's a separate question. Incidentally, it has a pretty good track record.

If you have a criticism of Silver's model I'm curious to hear it. However, as it is I don't see a criticism in your comment. You say it's ridiculous, but it isn't. It's complicated, not ridiculous. I can't say precisely what's on your mind, but if I had to guess, it doesn't make sense to you, which is a different matter.

Re: A few words about FiveThirtyEight

#138

Post by int_19h »

skissane wrote: post #134
int_19h wrote: post #132

Earlier quoted context omitted.

California is larger than many countries, and more productive than many countries as well (at least as far as GDP goes). Of course it should have a proportionally large influence on the rest of the country; it's not "undue".

I think a valid question is why is California so big... There's North Carolina and South Carolina, North Dakota and South Dakota, Virginia and West Virginia – why not North California and South California?

Pretty much all state boundaries are historical artifacts at this point. We could ask the same question about Texas, or even NY for that matter.

But when it comes to changing the boundaries, you need the state legislature and Congress acting in agreement. And state boundaries are inherently a partisan political matter at this point because every new state is going to be either "red" or "blue", and this then means the corresponding adjustments to Senate representation (and House too, actually, it's just less pronounced) as well as EC. If, say, Republicans drafted a bill to split red rural areas off CA into its own state, as often proposed, what sane Democrat would ever support it knowing that it means +2 Republican senators in Congress? For the same reason, we aren't going to see statehood for Puerto Rico or DC anytime soon. The only way it could possibly work out is if states are carved out in pairs - e.g. separate deep red areas from CA, but at the same time also do the same for deep blue areas of Texas. But deep blue areas also tend to be the ones that bring in the most taxes, so Texas Republicans might balk at that on economic grounds...

Truth is, our system is too broken to recover. Too many deadlocks. It was possible in the past, when fewer issues were quite so partisan, but of course back then the need for it was also much less obvious. But now, I think it's just going to deteriorate until the dysfunction on federal level gets so bad that the country literally cannot proceed without a major constitutional reform. At which point it'll likely break apart because we won't be able to agree on the new constitution.

Re: A few words about FiveThirtyEight

#139

Post by skissane »

int_19h wrote: post #138
skissane wrote: post #134

Earlier quoted context omitted.

I think a valid question is why is California so big... There's North Carolina and South Carolina, North Dakota and South Dakota, Virginia and West Virginia – why not North California and South California?

Pretty much all state boundaries are historical artifacts at this point. We could ask the same question about Texas, or even NY for that matter. But when it comes to changing the boundaries, you need the state legislature and Congress acting in agreement. And state boundaries are inherently a partisan political matter at this point because every new state is going to be either "red" or "blue", and this then means the…

> If, say, Republicans drafted a bill to split red rural areas off CA into its own state, as often proposed, what sane Democrat would ever support it knowing that it means +2 Republican senators in Congress?

> The only way it could possibly work out is if states are carved out in pairs - e.g. separate deep red areas from CA, but at the same time also do the same for deep blue areas of Texas. But deep blue areas also tend to be the ones that bring in the most taxes, so Texas Republicans might balk at that on economic grounds...

Couldn't they find some way of splitting CA into 3 states, two "blue" and one "red", such that you'd get two new Democratic Senators and two new Republican Senators, which would cancel each other out?

> For the same reason, we aren't going to see statehood for Puerto Rico or DC anytime soon.

Puerto Rico isn't a solid lock for the Democrats. PR's new Governor, Jenniffer González-Colón, is a Republican, and prior to becoming the Governor, she was PR's non-voting delegate to Congress. Of course, it would be a gamble for the GOP, but not one they'd be guaranteed to lose. Especially if you consider Trump has made significant inroads with Hispanic voters over the last two elections, and the GOP might do even better if they were to pick a Hispanic candidate.

DC, I agree it is unlikely Republicans would agree to it.

But, admission of a new state only needs a simple majority of Congress – in a Democratic trifecta, like Biden had 2021–2023, or Obama had in 2009–2011 – that DC or PR statehood didn't happen then was ultimately due to decisions made by the Democrats, not by the Republicans – if the Democrats had been totally committed to it, it would have happened over Republican objections – but obviously they weren't.

A Democratic trifecta could easily happen again – e.g. Trump II turns out to be really unpopular, and Democrats have a big win in 2028 – but will Democrats do anything more about PR/DC statehood in 2029–2031 than they did in 2009–2011 or 2021–2023? I doubt.

Re: A few words about FiveThirtyEight

#140

Post by snickerbockers »

iuyhtgbd wrote: post #137
snickerbockers wrote: post #131

Earlier quoted context omitted.

>Statistics works it does but just because nate silver calls something "statistics" doesn't necessarily mean that it is. If Donald Trump has a 20% chance of winning that means that we can hold the election 100 times and expect that he'll win approximately 20 elections and lose the other 80. Which is ridiculous because each voter is not an independent random variable.

Each eligible voter is a random variable, independence aside. Silver's model does not operate on the level of the voter however. A random variable is a very flexible abstraction, almost anything can be a random variable if you can find a way to measure it. Polls are a measurement. They're imperfect, but all measurements contain error. It's not statistics because any authority says it is, it's statistics because it st…

I don't see the point in anything that isn't falsifiable, and in order for that to happen there needs to be a sample size greater than one. If Hillary has a 99.9% chance of winning and Donald has a 0.1% chance of winning, does that mean the model was wrong or does that mean we're in the 0.1% timeline?

If you want to prove that a coin flip has a 50% chance of landing heads, a 50% chance of landing on tails, and a negligible chance of landing on its edge, you can run as many tests as you want and observe that as N approaches infinity the number of heads converges on 0.5N and the number of tails converges on 0.5N. Alternatively, you might find that the coin isn't well-balanced, in which case you've proven that the "50/50 model" was not accurate.

You can't do that with elections because each election only happens once. Even if the same two candidates are running against each other in every election, the issues at stake are different and the voterbase is different. In reality one candidate has a 100% chance of victory and the other has a 0% chance of victory but we don't know which candidate it is.

Post reply on HN