tag:blogger.com,1999:blog-4257917002416684161.post5184435491235799611..comments2010-03-01T03:02:27.767-05:00Nate Silverhttp://www.blogger.com/profile/08334852368748204318noreply@blogger.comBlogger29125tag:blogger.com,1999:blog-4257917002416684161.post-17162143675729109682010-03-01T03:02:27.767-05:002010-03-01T03:02:27.767-05:00Hello, wonderful blog!thank you. By the way,here we offer a lot of good nike shoes,you can come to have <br /><br />a look.<br /><a href="http://www.tnchaussurescom.com/nike-shox-r5-c-49_79.html" rel="nofollow">nike shox r5</a><br /><a href="http://www.tnchaussurescom.com/nike-air-max-180-c-49_80.html" rel="nofollow">nike air max 180</a><br /><a href="http://www.tnchaussurescom.com/nike-air-max-180-air-yeezy-sneakers-nike-homme-chaussures-blanc-" rel="nofollow">air yeezy sneakers</a><br /><a href="http://www.tnchaussurescom.com" rel="nofollow">tn chaussures</a><br /><a href="http://www.tnchaussurescom.com" rel="nofollow">nike tn</a><br /><a href="http://www.tnchaussurescom.com" rel="nofollow">tn chaussures</a><br /><a href="http://www.tnchaussurescom.com" rel="nofollow">nike air max</a><br /><a href="http://www.tradewe.com/nike-shox-rival-r3-c-71_82.html" rel="nofollow">sneakers</a><br /><a href="http://www.tnchaussurescom.com/nike-shox-oz-c-51_68.html" rel="nofollow">shox oz</a><br /><a href="http://www.tnchaussurescom.com/nike-shox-monster-c-49_67.html" rel="nofollow">nike shox monster</a><br /><a href="http://www.tnchaussurescom.com/nike-shox-r5-bon-marche-shox-r5-chaussures-nike-shox-blanc-or-p-" rel="nofollow">bon marche shox r5</a><br /><a href="http://www.tnchaussurescom.com" rel="nofollow">men&#39;s nike shoes</a><br /><a href="http://www.tnchaussurescom.com/nike-shox-r4-c-49_66.html" rel="nofollow">nike shox monster</a><br /><a href="http://www.tnchaussurescom.com" rel="nofollow">nike store</a><br /><a href="http://www.tnchaussurescom.com/nike-shox-r4-c-49_66.html" rel="nofollow">nike shox r4</a><br /><a href="http://www.tnchaussurescom.com" rel="nofollow">nike air max</a><br /><a href="http://www.tnchaussurescom.com/nike-tn-classic-c-49_62.html" rel="nofollow">achat nike shox</a><br /><a href="http://www.tnchaussurescom.com" rel="nofollow">cheap nike shoes</a><br /><a href="http://kitty200911.worldpress.com" rel="nofollow">tn chaussures</a> <br /><a href="http://trustme2010.blogspot.com/" rel="nofollow">nike air max</a><br /><a href="http://www.tnchaussurescom.com/nike-chaussure-enfant-c-52.html" rel="nofollow">enfant chaussures</a> <br /><a href="http://www.tnchaussurescom.com" rel="nofollow">nike tn requin</a><br /><a href="http://www.tnchaussurescom.com/nike-tn-dollar-c-51_54.html" rel="nofollow">nike tn</a><br /><a href="http://www.tnchaussurescom.com/nike-shox-r4-cartoon-c-52_72.html" rel="nofollow">nike shox cartoon</a><br /><a href="http://www.tnchaussurescom.com/nike-tn-net-chaussures-nike-shox-femmes-bon-blanc-rose-p-" rel="nofollow">chaussures nike shox</a><br /><a href="http://www.tnchaussurescom.com/nike-tn-dollor-acheter-chaussures-homme-nike-dollor-air-max-" rel="nofollow">acheter chaussures homme</a><br /><a href="http://www.tnchaussurescom.com/nike-tn-spider-c-49_55.html" rel="nofollow">tn chaussures</a><br /><a href="http://www.tnchaussurescom.com/nike-tn-limpide-chaussures-sport-homme-nike-cuir-air-max-bleu-p-" rel="nofollow">chaussures sport</a><br /><a href="http://www.tnchaussurescom.com/nike-shox-r4-cartoon-discount-enfant-chaussures-nike-cartoon-" rel="nofollow">discount enfant chaussures</a>trustmehttp://www.blogger.com/profile/14822109021461864699noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-38126809420893135732009-10-09T04:32:43.602-04:002009-10-09T04:32:43.602-04:00<a href="http://www.freefun.com.tw/" rel="nofollow">酒店經紀人</a>,<br /><a href="http://www.freefun.com.tw/index-001.html" rel="nofollow">菲梵酒店經紀</a>, <br /><a href="http://www.freefun.com.tw/" rel="nofollow">酒店經紀</a>, <br /><a href="http://www.freefun.com.tw/index-001.html" rel="nofollow">禮服酒店上班</a>, <br /><a href="http://www.freefun.com.tw/" rel="nofollow">酒店小姐兼職</a>, <br /><a href="http://www.freefun.com.tw/index-001.html" rel="nofollow">便服酒店經紀</a>, <br /><a href="http://www.freefun.com.tw/" rel="nofollow">酒店打工經紀</a>, <br /><a href="http://www.wretch.cc/user/talon0616" rel="nofollow">制服酒店工作</a>,<br /><a href="http://mypaper.pchome.com.tw/news/talon061609" rel="nofollow">專業酒店經紀</a>, <br /><a href="http://blog.yam.com/talon0616" rel="nofollow">合法酒店經紀</a>,<br /><a href="http://talon0616.pixnet.net/blog" rel="nofollow">酒店暑假打工</a>, <br /><a href="http://www.freefun.com.tw/" rel="nofollow">酒店寒假打工</a>, <br /><a href="http://tw.myblog.yahoo.com/jw!llPXJbWGERvqSmnJjyxtZi8-/" rel="nofollow">酒店經紀人</a>, <br /><a href="http://tw.myblog.yahoo.com/jw!llPXJbWGERvqSmnJjyxtZi8-/article?mid=1&amp;prev=-1&amp;next=289" rel="nofollow">菲梵酒店經紀</a>, <br /><a href="http://tw.myblog.yahoo.com/jw!llPXJbWGERvqSmnJjyxtZi8-/article?mid=288&amp;prev=289&amp;next=283" rel="nofollow">酒店經紀</a>,<br /><a href="http://tw.myblog.yahoo.com/jw!llPXJbWGERvqSmnJjyxtZi8-/article?mid=283&amp;prev=288&amp;next=282" rel="nofollow">禮服酒店上班</a>,<br /><a href="http://www.wretch.cc/blog/talon0616" rel="nofollow">酒店經紀人</a>, <br /><a href="http://www.wretch.cc/blog/talon0616/21182056" rel="nofollow">菲梵酒店經紀</a>, <br /><a href="http://cid-28e72e39b1bdec6c.profile.live.com/" rel="nofollow">酒店經紀</a>, <br /><a href="http://blog.xuite.net/talon0616/talon0616" rel="nofollow">禮服酒店上班</a>, <br /><a href="http://www.wretch.cc/blog/talon0616/21182005" rel="nofollow">酒店小姐兼職</a>, <br /><a href="http://blog.sina.com.tw/talon0616/" rel="nofollow">便服酒店工作</a>, <br /><a href="http://talon0616.blogspot.com/" rel="nofollow">酒店打工經紀</a>,<br /><a href="http://blog.roodo.com/talon0616/" rel="nofollow">制服酒店經紀</a>, <br /><a href="http://mypaper.pchome.com.tw/news/mico0616" rel="nofollow">專業酒店經紀</a>,<br /><a href="http://blog.yam.com/mico0616" rel="nofollow">合法酒店經紀</a>, <br /><a href="http://mico0616.pixnet.net/blog" rel="nofollow">酒店暑假打工</a>, <br /><a href="http://www.wretch.cc/blog/talon0616/21192282" rel="nofollow">酒店寒假打工</a>,<br /><a href="http://mypaper.pchome.com.tw/news/talon061609" rel="nofollow">酒店經紀人</a>, <br /><a href="http://mypaper.pchome.com.tw/news/talon061609" rel="nofollow">菲梵酒店經紀</a>, <br /><a href="http://mypaper.pchome.com.tw/news/talon061609" rel="nofollow">酒店經紀</a>,<br /><a href="http://mypaper.pchome.com.tw/news/talon061609" rel="nofollow">禮服酒店上班</a>, <br /><a href="http://blog.roodo.com/mico0616" rel="nofollow">酒店小姐兼職</a>,<br /><a href="http://cid-4961aa246c049b91.profile.live.com/?sa=643154984" rel="nofollow">便服酒店工作</a>, <br /><a href="http://mico0616.blogspot.com/" rel="nofollow">酒店打工經紀</a>, <br /><a href="http://blog.sina.com.tw/mico0616/" rel="nofollow">制服酒店經紀</a>,<br /><a href="http://blog.udn.com/bobe5858/3287628" rel="nofollow">酒店經紀</a>,<br /><a href="http://bobe5858.pixnet.net/blog" rel="nofollow">菲</a><br /><a href="http://bobe5858.blogspot.com/" rel="nofollow">梵</a>,freefun0616http://www.blogger.com/profile/04707998987768327827noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-53926438281793589742009-02-10T22:53:00.000-05:002009-02-10T22:53:00.000-05:00<A HREF="http://toytoytoytoytoytoy.com/" REL="nofollow">情趣用品</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/home.phtml" REL="nofollow">情趣用品</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/ptlist.phtml?Category=258265" REL="nofollow">情趣用品</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/ptlist.phtml?Category=300129/#q15" REL="nofollow">情趣用品</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/ptlist.phtml?Category=258267" REL="nofollow">情趣用品</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/forum.phtml?bbcode=" REL="nofollow">情趣用品</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/ptlist.phtml?Category=258277" REL="nofollow">情趣用品</A>,<A HREF="http://78cf.com/" REL="nofollow">情趣用品</A>,<A HREF="http://78kb.com/" REL="nofollow">情趣用品</A>,<A HREF="http://78pl.com/" REL="nofollow">情趣用品</A>,<A HREF="http://78bk.com/" REL="nofollow">情趣用品</A>,<A HREF="http://omb1.com/" REL="nofollow">情趣用品</A>,<A HREF="http://6lv9.com/" REL="nofollow">情趣用品</A>,<A HREF="http://6lv6.com/" REL="nofollow">情趣用品</A>,<A HREF="http://6ea9.com/" REL="nofollow">情趣用品</A>,<A HREF="http://6ea6.com/" REL="nofollow">情趣用品</A>,<A HREF="http://6ck9.com/" REL="nofollow">情趣用品</A>,<A HREF="http://6ck6.com/" REL="nofollow">情趣用品</A>,<A HREF="http://0lv0.com/" REL="nofollow">情趣用品</A>,<A HREF="http://0ea0.com/" REL="nofollow">情趣用品</A>,<A HREF="http://0ck0.com/" REL="nofollow">情趣用品</A>,<A HREF="http://8bl8.com/" REL="nofollow">情趣用品</A>,<A HREF="http://8kb8.com/" REL="nofollow">情趣用品</A>,<A HREF="http://8bk8.com/" REL="nofollow">情趣用品</A>,<A HREF="http://8dl8.com/" REL="nofollow">情趣用品</A>,<A HREF="http://8ea8.com/" REL="nofollow">情趣用品</A>,<A HREF="http://8bv8.com/" REL="nofollow">情趣用品</A>,<A HREF="http://8ct8.com/" REL="nofollow">情趣用品</A>,<A HREF="http://8pr8.com/" REL="nofollow">情趣用品</A>,<A HREF="http://8dh8.com/" REL="nofollow">情趣用品</A>,<A HREF="http://8br8.com/" REL="nofollow">情趣用品</A>,<A HREF="http://7bl7.com/" REL="nofollow">情趣用品</A>,<A HREF="http://7kb7.com/" REL="nofollow">情趣用品</A>,<A HREF="http://7dl7.com/" REL="nofollow">情趣用品</A>,<A HREF="http://7lv7.com/" REL="nofollow">情趣用品</A>,<A HREF="http://7ea7.com/" REL="nofollow">情趣用品</A>,<A HREF="http://7bv7.com/" REL="nofollow">情趣用品</A>,<A HREF="http://7ct7.com/" REL="nofollow">情趣用品</A>,<A HREF="http://7ck7.com/" REL="nofollow">情趣用品</A>,<A HREF="http://7dh7.com/" REL="nofollow">情趣用品</A>,<A HREF="http://7br7.com/" REL="nofollow">情趣用品</A>,<A HREF="http://toytoytoytoytoytoy.com/" REL="nofollow">情趣</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/home.phtml" REL="nofollow">情趣</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/ptlist.phtml?Category=258265" REL="nofollow">情趣</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/ptlist.phtml?Category=300129/#q15" REL="nofollow">情趣</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/ptlist.phtml?Category=258267" REL="nofollow">情趣</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/forum.phtml?bbcode=" REL="nofollow">情趣</A>,<A HREF="http://toytoytoytoytoytoy.com/front/bin/ptlist.phtml?Category=258277" REL="nofollow">情趣</A>,<A HREF="http://78cf.com/" REL="nofollow">情趣</A>,<A HREF="http://78kb.com/" REL="nofollow">情趣</A>,<A HREF="http://78pl.com/" REL="nofollow">情趣</A>,<A HREF="http://78bk.com/" REL="nofollow">情趣</A>,<A HREF="http://omb1.com/" REL="nofollow">情趣</A>,<A HREF="http://6lv9.com/" REL="nofollow">情趣</A>,<A HREF="http://6lv6.com/" REL="nofollow">情趣</A>,<A HREF="http://6ea9.com/" REL="nofollow">情趣</A>,<A HREF="http://6ea6.com/" REL="nofollow">情趣</A>,<A HREF="http://6ck9.com/" REL="nofollow">情趣</A>,<A HREF="http://6ck6.com/" REL="nofollow">情趣</A>,<A HREF="http://0lv0.com/" REL="nofollow">情趣</A>,<A HREF="http://0ea0.com/" REL="nofollow">情趣</A>,<A HREF=信次http://www.blogger.com/profile/02481689321253585436noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-76908837607990962132008-11-09T13:28:57.775-05:002008-11-09T13:28:57.775-05:00Can you put up a final table concluding who the best Pollsters are? We can see your weighting for each of the states, but is there a national one like the original one you first posted? It's hard to go through all your versions to reorder it. Thanks! I love the statistical analysis!lococrazyhttp://lococrazy.wordpress.com/noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-90350537080600515302008-10-30T08:21:07.699-04:002008-10-30T08:21:07.699-04:00What ever happened to Arthur J. Finkelstein and AJF and Associates? What about Mike Lavelle and Diversified Research? McLaughlin/Fabrizio and the whole crew?POAPATRICKHhttp://openid.aol.com/POAPATRICKHnoreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-19858656023587196482008-10-24T11:12:27.446-04:002008-10-24T11:12:27.446-04:00Supposing you took your own "Projection" that you form by weighted-average of the different polls, and ran it through your PIE calculation, what would the result be?<BR/><BR/>The whole point of your model is that your particular aggregation of polls is more correct than any poll by itself - which will be true provided that some land on one side of correct and some on the other side. But if they all bias in the same direction then the least-biased would be better than your model.<BR/><BR/>?Ottohttp://www.blogger.com/profile/07832626444218950761noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-77943321500557631722008-10-11T20:27:00.813-04:002008-10-11T20:27:00.813-04:00Nate, can you comment on why Zogby is so prominant among the media? Even Potus '08 devotes alot of air time to Zogby. And Fritz just tonight (10/11/08) claims that Zogby has been the closes of any individual poll to all races since 1996. On what is he basing this claim?Mike Woodhttp://www.blogger.com/profile/16060040132309530874noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-482127705692549582008-10-05T09:16:22.905-04:002008-10-05T09:16:22.905-04:00To add on concerning the Dispatch, there is a nice article by the Mystery Pollster:<BR/><BR/>http://www.mysterypollster.com/main/2005/11/columbus_dispat.html<BR/><BR/>This is about one case where the Dispatch was incredibly wrong - on statewide ballot issues in an off-year election. By contrast their historical margin of error (over 20+ years) has been 1.6% in presidential contests, which is extremely good.OhioDemhttp://www.blogger.com/profile/14426145237363252519noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-88808064125044524182008-10-05T09:07:40.223-04:002008-10-05T09:07:40.223-04:00m really surprised by your low rating of the Columbus Dispatch poll; it has historically been very accurate in the General Election. Based solely on what you've done here it is being dismissed as Zogby-like silliness. Please look at the historical track record in presidential general elections and you'll find a very different overall pattern, one typically within the sampling error of the final outcome.<BR/><BR/>The fact that their method doesn't work well in primaries doesn't extend to having it work badly in the general election.OhioDemhttp://www.blogger.com/profile/14426145237363252519noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-36548135924773600712008-09-30T23:05:24.288-04:002008-09-30T23:05:24.288-04:00Hi,<BR/> <BR/> This seems to be a somewhat old thread, but I hope you are still looking at its comments...<BR/> <BR/> First, thanks for putting this nice information online: I had been looking for data on the reliability of the different polls.<BR/> <BR/> I was wondering if you have any sort of assessment of how the prices on intrade (www.intrade.com) perform as a poll. Intrade has the great advantage of providing information in real time.<BR/><BR/> Of course, the people betting on intrade are hardly a representative sample of the voters. However, one can argue that as real money is involved in each trade, people have incentives to place "rational" bets which could be representative of the opinions traders see flying around. For a sufficiently liquid contract, the prices should somehow be a consensus of opinions.<BR/><BR/> Congratulations on the site.<BR/> Let me know if you have any ideas on my comments.<BR/> <BR/> Thanks,<BR/> <BR/> G. Rochagvrochahttp://www.blogger.com/profile/13195728136417204313noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-46570596476641296542008-09-22T21:35:47.421-04:002008-09-22T21:35:47.421-04:00Hey guys --- I don't know if you're reading this old thread anymore, but I'd seriously suggest that you remove the Zogby Interactive polls from your calculations. Their level of accuracy does not come anywhere close to the real polls, and your ratings seem to agree. Better not to include them at all. I know that every pollster has occasionally wacky results, but Zogby Interactive is <I>regularly</I> weird:<BR/><BR/>McCain +10.3 in FL?<BR/>McCain +6.3 in NH?<BR/>McCain +4.8 in PA?<BR/><BR/>Including the results from this nutty pollster makes you guys look kinda silly...Psssthttp://www.blogger.com/profile/18435363010758799208noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-47890451925842739432008-09-16T13:23:55.794-04:002008-09-16T13:23:55.794-04:00Nate: Is it possible to include the Lake/Tarrance Battleground and Hotline polls in your ratings? Also, do you have an updated Pollster Ratings chart? Thanks.Jeff Gulatihttp://www.blogger.com/profile/07903273736416399042noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-62629430677600345472008-08-15T08:39:10.336-04:002008-08-15T08:39:10.336-04:00Nate _ or anybody that knows. <BR/><BR/>Where does "Pew" land on the list? <BR/><BR/>I don't see it?capthttp://www.blogger.com/profile/04541180524537586259noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-39423547047518183562008-07-10T18:39:29.563-04:002008-07-10T18:39:29.563-04:00I'm wondering about bias in the PIE. I've seen some indication that Rasmussen is generally, but not always, more positive for McCain than Survey USA. It seems to vary by state, and the difference can be well beyond the sampling error. Analysis is complicated by the scarcity of comparable samples. Any light to shed?postdocnoreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-78522510318124363352008-06-20T22:53:55.557-04:002008-06-20T22:53:55.557-04:00what about newsweek- especially after the huge obama lead today nationallyAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-78966211382282555682008-06-01T17:44:17.472-04:002008-06-01T17:44:17.472-04:00Obama should get more electoral votes if he picks Edwards as a vice presidential nominee, according to SurveyUSA. The election won't be so close once this happens. Right now, it is a toss-up who wins the election. Another thing to consider is the voter enthusiasm on the Democratic side. This may give the general election to Obama. Also, third party candidates may have a significant effect on the outcome, according to Rasmussen Reports.chadfoghttp://www.blogger.com/profile/12292914799461765487noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-89643611654852130412008-05-30T22:02:28.872-04:002008-05-30T22:02:28.872-04:00Does your ranking system account for regression toward the mean? The more polls a pollster does, the closer to the mean you would expect them to get, right? That may be why SUSA is ranked so high -- because they have polled close to the most races. Unless you have somehow adjusted for that in your ratings.thecouganoreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-3437755673967750522008-05-30T10:48:57.291-04:002008-05-30T10:48:57.291-04:00What's with the enormous error in SurveyUSA and yet they rank second amongst pollsters? They are all over the place. Obama is gonna win North Dakota and Indiana yet barely win Massachussetts and tie in New Jersey? Meanwhile, McCain barely wins North Dakota, South Carolina and Nebraska, gets blown away in Ohio and only wins by 11 in Utah (where Bush won by about 40).<BR/><BR/>I smell some serious bias here, or just incompetency.Mikenoreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-89209169626826946952008-05-29T11:48:50.118-04:002008-05-29T11:48:50.118-04:00How many polls has Seltzer conducted? SUSA polls every contest.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-65624068525193371472008-05-29T11:48:47.145-04:002008-05-29T11:48:47.145-04:00How many polls has Seltzer conducted? SUSA polls every contest.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-21302354813786556002008-05-28T18:25:33.270-04:002008-05-28T18:25:33.270-04:00I posted something along these lines on DailyKos, but I thought you might be the perfect person to run the analysis. <BR/><BR/>I have a hypothesis that Clinton is actually doing a little better than Obama amongst African-American voters, while Obama may be performing a little bit better with working class whites and older women than exit polling suggests. The exit polls have been unusually inaccurate in this cycle, and I believe that pollster bias may be affecting the answers they are receiving (for example, an African-American voter may be less inclined to tell an African-American pollster that they supported Clinton). <BR/><BR/>I'm wondering if there is a way to prove this by looking at the cross-tabs of the automated polls and comparing those the cross-tabs of the exit polls and the cross-tabs of the non-automated polls. <BR/><BR/>This might be useful in an attempt to filter out the biases in future non-automated polls.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-83822509174655413952008-05-28T18:21:52.348-04:002008-05-28T18:21:52.348-04:00I'm new to this site and I do not understand some of the numbers. For example:<BR/><BR/>- The Swing State Analysis for Ohio shows Obama vs McCain as 15.8% in BLUE and Clinton vs McCain as 8.1% in RED. What the heck does this mean?<BR/><BR/>- The Win Percentage Tracker shows what? The percentage of states a given candidate would win if the general election were held on a given day?<BR/><BR/>- The Regional Analysis tables shows what? The statistical probability that a given candidate will carry the state?<BR/><BR/>I would appreciate SOME simple explanations.<BR/><BR/>Thanks.rzieglerhttp://www.blogger.com/profile/14906774635617628619noreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-56218727882429067592008-05-28T16:18:20.452-04:002008-05-28T16:18:20.452-04:00Same anon:<BR/><BR/>Check Hawaii and Rhode Island. I'm quite sure the scenario you suggest is a tie - I get a tie using 270towin. In fact, it's the most common tie in <A HREF="http://www.fivethirtyeight.com/2008/05/like-kissing-your-sister.html" REL="nofollow">Poblano's tie analysis</A>, happening a whole .04% of the time last he checked.doktarrnoreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-45902173290839509242008-05-28T14:20:56.260-04:002008-05-28T14:20:56.260-04:00Here's my suggestion for using national polls:<BR/><BR/>1. Treat them as polls of a state, USA, without electoral college votes (and with the demographics of the USA).<BR/>2. Use them as another target for training the 538 regression.<BR/>3. Adjust higher the weight of the 538 regression.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-4257917002416684161.post-30984770455674300622008-05-28T13:56:51.034-04:002008-05-28T13:56:51.034-04:00Poblano, are you planning to correct old poll numbers based on national movement since then? It is a way to use the national poll numbers - though you'd have to smooth out the minor variations with a broad enough average. You could be conservative in your correction - multiply it by 0.9, or in some way subtract out a MOE.<BR/><BR/>If you are going to do this, you should definitely have the system in place before Clinton drops out, because that's just the start of the serious national movement.<BR/><BR/>Please respond, I think this idea is at least worth consideration, and I'd be happy to clarify how I see it working. Your model is still giving some weight to polls from February, and that will only get worse as the general comes on and pollsters shift some focus away from the states.<BR/><BR/>(if you wanted to be more complex about it, you could do your national correction by party-id subgroups. That way, as the lambs return to the fold, your correction would not just make the whole map bluer - some red states could get redder at the same time).homunqhttp://www.blogger.com/profile/15539994035167878969noreply@blogger.com