538 Model Debut: 64% Chance of Republican Majority; R+7 Most Likely

[NHLiberal]

Guys, if you add up the individual probabilities, the model is projecting R+9.

I think you missed the fact that GA, KY, and KS are currently Republican held seats.

No, because WV and MT aren't even on the list. What he/she meant was that the model shows Republicans having a greater than 50% chance in 9 states: WV, SD, MT, AR, AK, LA, NC, CO, and IA. Gauss is correct in pointing out that it doesn't actually mean the model is predicting 9 seats though.

[○∙◄☻¥tπ[╪AV┼cVê└]

Guys, if you add up the individual probabilities, the model is projecting R+9.

I think you missed the fact that GA, KY, and KS are currently Republican held seats.

No, because WV and MT aren't even on the list. What he/she meant was that the model shows Republicans having a greater than 50% chance in 9 states: WV, SD, MT, AR, AK, LA, NC, CO, and IA. Gauss is correct in pointing out that it doesn't actually mean the model is predicting 9 seats though.

Odds are certainly against Republicans winning all of Iowa, Colorado, North Carolina, and Alaska.

[JRP1994]

Guys, if you add up the individual probabilities, the model is projecting R+9.

I think you missed the fact that GA, KY, and KS are currently Republican held seats.

No, because WV and MT aren't even on the list. What he/she meant was that the model shows Republicans having a greater than 50% chance in 9 states: WV, SD, MT, AR, AK, LA, NC, CO, and IA. Gauss is correct in pointing out that it doesn't actually mean the model is predicting 9 seats though.

Yes, exactly what I meant.

Guys, if you add up the individual probabilities, the model is projecting R+9.

'
But events aren't independent here.  The races tend to go together.......

Thus, you can't just add up expected values like that.

Good point. But isn't that how Silver "correctly projected the outcome" in all 50 states, by adding the expected value? The model showed Obama winning something like 318.5 electoral votes, but 332 if you added up ever state in which he had a >50% chance.

[GaussLaw]

Good point. But isn't that how Silver "correctly projected the outcome" in all 50 states, by adding the expected value? The model showed Obama winning something like 318.5 electoral votes, but 332 if you added up ever state in which he had a >50% chance.

IIRC, Nate Silver discussed how his model does not treat each election as an independent event, but rather one party winning a specific race affects the probabilities of all the other races going a certain way (in that wining party's favor, of course).  I forgot a lot of stats stuff since college, so this is begging for an SPC post to get into the statistical nitty-gritty.

[Vosem]

Colorado and Iowa both flipped from the Republicans to the Democrats in the model today (though Iowa is at D+0 and 50/50; as close as you can get, basically), so R+7, viewed as the likeliest number-result, is now the result reflected in the model. (While a significant pickup for the Republicans, it might also be a bit ominous; every state voting the same way it did presidentially in 2012, except Collins being reelected in Maine).

[DrScholl]

Remember when 538 was supposed to not reliable and people were sending the site nasty emails? How quickly minds change when favorable results are produced for certain people.

For the record, I never cared for this sort of model in 2012, even if it favorable to Democrats, because it misses the mark.

[Ogre Mage]

Alaska could very easily slip through the same small-state hole in Silver's model that Montana and North Dakota fell through last time.

That was my thought as well.  Silver's forecast there is very incongruous with the polling data we have seen from Alaska.  Granted it is a hard state to poll, but still ...

[Nichlemn]

Meh. Wang is better anyway.

Wang uses polling only and then applies way too much certainty in his models. If he's right, he looks smart and can bleat on about how Nate Silver adds too many bells and whistles, but when he's wrong, it can be spectacularly bad. For instance, in 2010, his model was off by 6.5x his stated standard error, which would occur by chance something like one in a billion times. Nate is much more realistic about the amount of uncertainty in prediction models.

His current prediction for KS-Sen, Orman as 80% to win, is clearly ludicrous. A single poll of a then-purely hypothetical race is enough to make such a confident prediction on? This is exactly the sort of case where non-poll factors like "state fundamentals" really are clearly needed.

[JRP1994]

Meh. Wang is better anyway.

Wang uses polling only and then applies way too much certainty in his models. If he's right, he looks smart and can bleat on about how Nate Silver adds too many bells and whistles, but when he's wrong, it can be spectacularly bad. For instance, in 2010, his model was off by 6.5x his stated standard error, which would occur by chance something like one in a billion times. Nate is much more realistic about the amount of uncertainty in prediction models.

His current prediction for KS-Sen, Orman as 80% to win, is clearly ludicrous. A single poll of a then-purely hypothetical race is enough to make such a confident prediction on? This is exactly the sort of case where non-poll factors like "state fundamentals" really are clearly needed.

PREACH IT.

[Free Bird]

Remember when 538 was supposed to not reliable and people were sending the site nasty emails? How quickly minds change when favorable results are produced for certain people.

For the record, I never cared for this sort of model in 2012, even if it favorable to Democrats, because it misses the mark.

Hypocrisy at its finest, ladies and gentlemen. I better remember Democrats gushing about Silver about how accurate he was back in the day.

[NHLiberal]

Remember when 538 was supposed to not reliable and people were sending the site nasty emails? How quickly minds change when favorable results are produced for certain people.

For the record, I never cared for this sort of model in 2012, even if it favorable to Democrats, because it misses the mark.

Hypocrisy at its finest, ladies and gentlemen. I better remember Democrats gushing about Silver about how accurate he was back in the day.

"For the record, I never cared for this sort of model in 2012, even if it favorable to Democrats, because it misses the mark."

So no.

[Free Bird]

Remember when 538 was supposed to not reliable and people were sending the site nasty emails? How quickly minds change when favorable results are produced for certain people.

For the record, I never cared for this sort of model in 2012, even if it favorable to Democrats, because it misses the mark.

Hypocrisy at its finest, ladies and gentlemen. I better remember Democrats gushing about Silver about how accurate he was back in the day.

"For the record, I never cared for this sort of model in 2012, even if it favorable to Democrats, because it misses the mark."

So no.

Was talking in general

[NHLiberal]

Remember when 538 was supposed to not reliable and people were sending the site nasty emails? How quickly minds change when favorable results are produced for certain people.

For the record, I never cared for this sort of model in 2012, even if it favorable to Democrats, because it misses the mark.

Hypocrisy at its finest, ladies and gentlemen. I better remember Democrats gushing about Silver about how accurate he was back in the day.

"For the record, I never cared for this sort of model in 2012, even if it favorable to Democrats, because it misses the mark."

So no.

Was talking in general

But he/she is one person, so you can't contend the hypocrisy of all Democrats based on his/her individual statements that specifically reveal the exact opposite of the hypocrisy you are highlighting.

[Lief 🗽]

Two weeks later, Republicans' chances of taking a majority are down to 55%.

[Fuzzybigfoot]

Two weeks later, Republicans' chances of taking a majority are down to 55%.

Post-Labor Day polling FTW. 

[KCDem]

Two weeks later, Republicans' chances of taking a majority are down to 55%.

The Republican wave has crested.

[The Other Castro]

Looks like it might be coming down to Alaska, Iowa, and Kansas, with Dems needing 2/3

[Senate Minority Leader Lord Voldemort]

Two weeks later, Republicans' chances of taking a majority are down to 55%.

It's happening!!

......except in Alaska.

[Adam Griffin]

Barring some big changes in several different races, 2014 may be the year when Silver loses his shine. Looking back, each national cycle he has covered has been relatively one-sided and not as many individual races were truly close; his "none here and one there" track-record of inaccuracies may fall apart. As it stands and as it has stood for many months, there's a good chance that:

• several Senate races could be very close to 50/50 (two-way model)
• the national PV could be very close to 50/50
• the composition of the Senate may end up being 50/50

That makes his whole probability angle risky in terms of correctly identifying who will win (I don't care if the method provides a technical cop-out for him: people listen to him because they expect his probabilities are going to be the result).

[○∙◄☻¥tπ[╪AV┼cVê└]

Barring some big changes in several different races, 2014 may be the year when Silver loses his shine. Looking back, each national cycle he has covered has been relatively one-sided and not as many individual races were truly close; his "none here and one there" track-record of inaccuracies may fall apart. As it stands and as it has stood for many months, there's a good chance that:

• several Senate races could be very close to 50/50 (two-way model)
• the national PV could be very close to 50/50
• the composition of the Senate may end up being 50/50

That makes his whole probability angle risky in terms of correctly identifying who will win (I don't care if the method provides a technical cop-out for him: people listen to him because they expect his probabilities are going to be the result).

He didn't do so great with the 2012 Senate elections. He predicted 52.5 Democrats, it ended up being 55 Democrats. He had 92.5% odds that Rick Berg was going to be elected.

[Bacon King]

Barring some big changes in several different races, 2014 may be the year when Silver loses his shine. Looking back, each national cycle he has covered has been relatively one-sided and not as many individual races were truly close; his "none here and one there" track-record of inaccuracies may fall apart. As it stands and as it has stood for many months, there's a good chance that:

• several Senate races could be very close to 50/50 (two-way model)
• the national PV could be very close to 50/50
• the composition of the Senate may end up being 50/50

That makes his whole probability angle risky in terms of correctly identifying who will win (I don't care if the method provides a technical cop-out for him: people listen to him because they expect his probabilities are going to be the result).

He didn't do so great with the 2012 Senate elections. He predicted 52.5 Democrats, it ended up being 55 Democrats. He had 92.5% odds that Rick Berg was going to be elected.

In 2010 he called three races wrong as well. The Senate's always been Silver's weak point.

[Nichlemn]

Barring some big changes in several different races, 2014 may be the year when Silver loses his shine. Looking back, each national cycle he has covered has been relatively one-sided and not as many individual races were truly close; his "none here and one there" track-record of inaccuracies may fall apart. As it stands and as it has stood for many months, there's a good chance that:

• several Senate races could be very close to 50/50 (two-way model)
• the national PV could be very close to 50/50
• the composition of the Senate may end up being 50/50

That makes his whole probability angle risky in terms of correctly identifying who will win (I don't care if the method provides a technical cop-out for him: people listen to him because they expect his probabilities are going to be the result).

Nate has said himself that he doubts he (or anyone else) is likely to get every race (or all but 1) race correct. That isn't (or at least shouldn't) be a knock on him. He's not a wizard, he can only work with the information available. If a race is a true tossup according to all available data then he can't read people's minds.

[Mechaman]

Ugh god, I said I wouldn't comment on any more Congressional threads, but I just love the defense of the Almighty Saint Silver that is going on here.  "OH he can't predict everything correctly!"  Nevermind that his entire approach to predicting politics is based off of a misguided belief that everything comes down to some kind of statistical mathematic formula or some sh*t like that.

When you start to think that everything can be explained by numbers and formulas you are arguably as stupid as people who believe that the Earth is a giant solar cracker.  No matter how many MIT degrees you may hold.

[Antonio the Sixth]

Ugh god, I said I wouldn't comment on any more Congressional threads, but I just love the defense of the Almighty Saint Silver that is going on here.  "OH he can't predict everything correctly!"  Nevermind that his entire approach to predicting politics is based off of a misguided belief that everything comes down to some kind of statistical mathematic formula or some sh*t like that.

When you start to think that everything can be explained by numbers and formulas you are arguably as stupid as people who believe that the Earth is a giant solar cracker.  No matter how many MIT degrees you may hold.

Except he has never said such things. He's actually a lot more nuanced in his analyses than people give him credit for.

Now, I also believe Silver's model has its flaws (and his 2014 model has been particularly disappointing in terms of  sophistication). But he remains one of the few people in America whose predictions are worth taking seriously.

[7,052,770]

NATE SILVER CAN NEVER BE "RIGHT"

NATE SILVER CAN NEVER BE "WRONG"

HE NEVER CLAIMS OTHERWISE

WHY IS THIS SO HARD FOR SOME PEOPLE TO GRASP?