Articles and Analysis


Bush Approval: Newsweek 33%

Topics: George Bush


A new Newsweek poll [story, results] finds approval of President Bush at 33%, a record low for the Newsweek organization, though not for other polls. The poll, taken 10/5-6/06 also found disapproval at 59%. As the graph above makes clear, however, the Newsweek poll is far below other recent polls and the current trend estimate. Before concluding that approval has "really" fallen to 33%, a good deal more data will have to confirm this extremely large drop.

That is not to say that approval has not turned down. Indeed, after the last two weeks of unremitting bad news for the White House, it is hard to imagine how if could have failed to do so. The question is whether the Newsweek poll is a reasonable estimate of current opinion or if it is too far away from other results to be plausible.

With the addition of the Newsweek poll, my current estimate of approval (the dark blue line) stands at 39.4, a full point below the recent high of 40.4 on 9/20. (This value is constantly being revised as new polling allows better estimates of the peak. On 9/19 the estimate was 41.1, while on 9/21 it stood at 41.2. Three polls completed 9/25-9/27 agreed on 42%, driving the estimator that day to 42.2. However, in light of all the polling since, the revised estimate puts the recent high at only 40.4 as of 9/20.)

While a one point drop may seem small, this is a drop in the trend estimate, NOT the very noisy raw polls which move by much more from poll to poll but which also contain much more random variation. One point in 16 days is almost 2 points per month, which is quite a substantial rate of decline. For comparison, during the first five months of 2005, the President's approval declined by one point each 13.5 days, as estimated just before approval reversed and started back up on May 15. I hasten to add that we lack enough data to be at all confident as to what the current rate of decline actually is. One point per 16 days is merely the best guess given current data. It might be less or more and will certainly change as new data come in.

So granted approval is now clearly going down, is the Newsweek poll telling us that the drop is of historic rapidity and that new polls will also show similarly dramatic drops, or is Newsweek's poll a statistical outlier-- getting the direction right but seriously overstating the magnitude of decline?

Based on all polling since 2002, the Newsweek result is clearly a statistical outlier. It is well below the 90% confidence interval in the figure below and is among the larger negative outliers of the past four years. The figure plots the residuals, the deviation from the trend estimate, for each poll taken since January 1, 2002. Orange points are polls that fall outside the 90% confidence interval, indicated by the low and high horizontal lines. The mean of all residuals is zero, the middle horizontal line. Newsweek polls are in red for easy identification.


Newsweek has a good polling track record, producing only one previous outlier in 70 polls. Here "outlier" is any poll outside the 90% confidence interval. By definition, we expect 10% of cases to fall outside that range. In fact, Newsweek has now produced two out of 71 polls since 2002 that are outside that 90% CI, a 2.8% rate. This latest poll, however, is clearly well beyond the lower limit of the interval.

Two recent polls have also fallen outside, but above, the 90% CI. Both of these were completed prior to the revelations about Representative Foley's IM messages to House pages, though after the now estimated peak of approval on 9/20.

Even if we focus on the four polls completed (at least partially) since the Foley Folly began, we see that all four are well below the trend estimate, but that the Newsweek poll is substantially below even these polls.

The conclusion is that the Newsweek poll is implausibly low, given the other data we have seen so far. A possible (but statistically less likely) alternative is that approval is falling very rapidly so that the unusually low Newsweek result reflects a much sharper rate of decline than the 1% per 16 days that I currently estimate. Such a rate of decline would be much higher than any yet seen in the Bush administration. I find this quite unlikely, but the data will answer this one way or another within a couple of weeks. For now, I'd bet the approval trend will fall another half point by the end of next week. If it falls much more than that, the Newsweek poll will look like a harbinger rather than a statistical fluke.



TIME is at 36, so it'll be intersting to see what the new aggregate becomes with more data. I'll bet this is a more rapid fall from the mini-peak than is usual.


Andrew Dane:

This is a great sight! I just read the commentary regarding the latest newsweek poll and want to say how much I appreciate the straightforward analysis and simple, easy to follow writing style. Thanks



SUSA's survey (10/05/2006) about whether Hastert should resign or not had Bush at 37% approval and 59% disapproval.



I believe we are seeing an historic drop in approval. Among people I know who have always been die-hard Republicans, the Foley scandal has even turned them off completely. I believe the Democrats are poised to pick up 50-70 seats in the House and 7-10 in the Senate. President Bush will be impeached and convicted within 16 months. We will not see a Republican congressional majority or President for at least the next 20 years.



Aaron, 25-30 seats seems within reach. but 20-25 seems more reasonable and 15-20 seems likely. Bush will not be impeached. And we can't even predict the next 20 days, let alone the next 20 years.

Review Watergate. The '74 election saw R base depression of turnout, but it wasn't permanent.



"A possible (but statistically less likely) alternative is that approval is falling very rapidly so that the unusually low Newsweek result reflects a much sharper rate of decline than the 1% per 16 days that I currently estimate."

I can see saying "less likely", but why "statistically less likely"? If the Foley revelations have led to the bottom falling out from the GOP base, then we could see another period of rapid decline in the Bush approval rating similar to what happened after Katrina. Until you know exactly what effect the latest scandal will have, it doesn't really make sense to bolster your analysis with the language "statistically less likely". Whatever statistical support the trend line gives you does not translate, at least not mathematically, to the world of post-Foley.


As shown on my sample-weighting website, the Newsweek poll appears to have substantially oversampled Democrats.


Whenever a poll looks out of whack -- too favorable for either the Democrats or Republicans -- I believe the first question you should ask is, "What's the partisan composition of the sample?" One never knows for sure, but authentic large shifts in party ID in short periods of time are probably rare.

Zogby and Rasmussen weight their samples to a pre-specified partisan composition, so for their surveys, you can usually rule out swings in partisan composition for changes in Bush approval rating or the Generic Congressional Ballot. The only way Zogby or Rasmussen would be caught in a bad spot is if a seismic shift in party ID really were occurring!



just want to say this is a super site. This is the first time I've visited.

Keep up the good work!



SUSA has yet another poll out.
65% of the people polled said Hastert should resign for either his Speaker position or the House altogether.
Bush is polling at 33% approval and 63% dissappoval which matches the Newsweek survey. They had a lot more Democrats though in this survey 43% Democrats to 25% Republicans and 24% Indies. Two outliers or a trend?



What Alan Reifman says about party id is important to note, and would explain the swing. But it's also true that Bush is trending downward recently. Gallup has him down to 37% from 44 in the previous poll. Probably Gallup's 44 was too high and Newsweek's 33 is too low.

The problem of party ID is also interesting, and could be disturbed if party self-ID starts changing in the population at large - and that definitely happens over time. I wouldn't expect it to fluctuate dramatically over the course of a week, but if there was a week for that to happen, the past week would qualify. It's something to keep an eye on.


Gary Kilbride:

I noticed the 21 and 23 point generic House leads were included in the polling recap. Remember the thread here last week that quoted a Republican pollster saying any numbers more than 72 hours old were obsolete? From a Democratic point of view, I would caution that works in reverse also.

Right now the polling on the approval rating, and the generic ballot and also individual races is catching Republicans scraping from the bottom. I think it's extremely dangerous to put full stock in recent polling from the past week or ten days, particularly in House races. There will likely be a natural recoil and polling two weeks from now will be more accurate.

The market sites like Iowa Futures Market and Tradesports are routinely condemned by progressive bloggers but I think the current scandal demonstrates how useful and sharp they are. Market players understand there is a baseline "power rating," if you will, that doesn't alter nearly as dramatically as casual pundits like to believe. Even with the landslide news of the past ten days, the odds on Democrats taking the House has shifted only about 15-17%, from mid 40s up to about 60. That would equate to maybe a 5 seat shift, if you looked at it in terms of an over/under. From maybe 13 to 18.

No doubt the typical political observer would estimate much higher than that. That's where you get the wild estimates of 50-70 seats.

I realize I use sports examples too frequently but since it's 90% of what I do, sorry it's likely to continue. This political climate with the landslide predictions reminds me somewhat of the opening game of the NFL season, Miami at Pittsburgh. Roethlisberger was out. Pittsburgh dropped from a 4 point favorite to 1. The average bettor handicapped that as far too low of an adjustment. Miami was a hyped team in preseason. A manager of a major sportsbook showed me his computer screen an hour before the game. It was surreal. Almost all the small $20-type bets were on the Dolphins, literally thousands of them. Meanwhile, more than 80% of the large $1000+ bets were on the Steelers. That's what balanced the action but how it broke down completely differently.

The wise guys were concluding the quarterback change was not as much of a factor as the public wanted to believe, that there was still a base relationship between one team and the other and that was likely to play out in the game. IMO that's very similar to current political climate. The $20 bettors are anticipating a massive swing but that's not likely to be reality. Not as much has changed as we want to believe.

Democrats are viewed as a 50/50 team in terms of their own approval rating. Give me great candidates and a great message and a huge Democratic approval rating and I don't have to sample these blogs every day and sweat the poll numbers. Victory would be inevitable. As is, Democrats are counting on a mediocre team to obliterate a poor team. That's not how it works. The Bears win huge because they are playing great football. Tiger Woods can win 6 straight tournaments because he's a stunning player. You're not going to have a mediocre golfer win 6 in a row based on the rest of the field group hacking in the rough. That's not much different than what Democrats are anticipating on November 7. Gains, but not an avalanche.


Post a comment

Please be patient while your comment posts - sometimes it takes a minute or two. To check your comment, please wait 60 seconds and click your browser's refresh button. Note that comments with three or more hyperlinks will be held for approval.