Here are my latest estimates on the national state of the Democratic campaign. The methodology for the high-end estimate can be found here, and the spreadsheet with the high-end data can be viewed here. The methodology for the low-end estimate can be found here, and the spreadsheet with the low-end data can be found here.

High-End Estimate

Date	Clinton	Obama	Edwards	Others / Unsure
May 08	35.2%	27.8%	16.3%	20.7%
May 04	34.0%	28.8%	17.8%	19.4%
Apr 30	33.5%	30.3%	18.0%	18.2%
Apr 27	35.2%	29.8%	18.0%	17.0%
Apr 24	35.7%	28.4%	17.6%	18.3%
Apr 20	35.7%	28.0%	17.2%	19.1%
Apr 16	37.0%	26.3%	17.0%	19.7%
Apr 13	37.0%	24.5%	17.0%	21.5%
Apr 10	37.8%	22.8%	17.3%	22.1%
Apr 06	37.7%	23.3%	17.0%	22.0%
Apr 02	37.3%	23.3%	17.2%	22.2%
Mar 30	36.6%	24.6%	16.8%	22.0%

Low-End Estimate

Date	Clinton	Obama	Edwards	Other / Unsure
May 08	33.2%	24.6%	14.6%	27.6%
May 04	33.0%	25.7%	16.5%	24.6%
Apr 30	34.2%	27.0%	16.7%	22.2%
Apr 27	34.4%	26.4%	16.3%	22.9%
Apr 24	34.3%	25.9%	16.0%	23.8%
Apr 20	34.0%	25.1%	15.0%	25.9%
Apr 16	33.9%	24.6%	15.1%	26.4%
Apr 13	34.9%	24.0%	15.7%	25.4%
Apr 10	35.8%	22.0%	15.5%	26.7%
Apr 06	35.4%	22.9%	15.4%	26.3%
Apr 02	35.4%	22.9%	15.4%	26.3%
Mar 30	34.8%	23.6%	15.3%	26.4%

The recent numbers in the two estimates tell two different stories. In the high-end estimate, Clinton is rising compared to everyone else. In the low-end estimate, the field is rising against the top-tier candidates. The cause for this discrepancy is the generally low number of national polls right now, as only five are included in the low-end, and only four in the high-end. With a small number of significantly varying polls, the trend is less clear. What does seem clear, however, is the most recent polls are positive for neither Obama nor Edwards (perhaps especially Edwards). This is probably because the debate stopped Obama's post-fundraising bounce trend, and gave the rest of the field more exposure. Also, Edwards has been somewhat bothered by the bullshit haircut story. I mean, many candidates running for president spend literally tens of millions of dollars making themselves look better, and $400 is supposed to be a big deal? What. Ever. Typical right-wing, context-free smear.

Yesterday morning, I produced a chart of the rolling averages of national Democratic nomination preference polls from February 23rd through April 24th. I thought about that chart a lot today, and considered different ways that polling averages of this sort could be produced. The result of that thought is a second chart, meant to be a companion of the first chart, that provides a lower estimation of support of all three top-tier candidates.

National Democratic Polls, Low-End Estimate, 2/1-4/24

Date	Clinton	Obama	Edwards	Other / Unsure
Apr 24	34.3%	25.9%	16.0%	23.8%
Apr 20	34.0%	25.1%	15.0%	25.9%
Apr 16	33.9%	24.6%	15.1%	26.4%
Apr 13	34.9%	24.0%	15.7%	25.4%
Apr 10	35.8%	22.0%	15.5%	26.7%
Apr 06	35.4%	22.9%	15.4%	26.3%
Apr 02	35.4%	22.9%	15.4%	26.3%
Mar 30	34.8%	23.6%	15.3%	26.4%
Mar 27	34.9%	25.0%	14.3%	25.9%
Mar 23	35.8%	25.8%	12.5%	26.0%
Mar 20	36.4%	25.0%	11.6%	27.0%
Mar 16	36.5%	25.8%	12.1%	25.6%
Mar 13	36.1%	25.0%	12.6%	26.3%
Mar 09	36.2%	25.0%	12.7%	26.1%
Mar 06	35.7%	25.4%	12.7%	26.1%
Mar 02	35.6%	24.0%	11.2%	29.2%
Feb 27	35.0%	22.4%	10.2%	32.4%
Feb 24	35.8%	21.3%	10.3%	32.8%
Feb 20	36.0%	20.0%	10.7%	33.3%
Feb 16	35.3%	19.2%	11.3%	34.2%
Feb 12	38.0%	17.8%	11.6%	32.6%
Feb 09	35.0%	18.7%	11.7%	34.7%
Feb 05	36.7%	17.3%	10.7%	34.7%
Feb 01	37.3%	17.3%	12.7%	32.7%

This chart differs from the first chart in two key ways. First, it incorporates all polls that include the entire, announced Democratic field in their nomination preference question, including those polls that put Al Gore in the question. Second, when a given poll offers both Gore-inclusive and Gore-exclusive results, this chart utilizes the Gore-inclusive data. There are many benefits to this methodology:

1. More data. This chart only excludes polls that ask two-way or three way questions, and as such increases the total data points from 33 to 43.
2. Longer trend lines. The increased number of data points allows for a trendline going back to February 1st, rather than February 23rd.
3. Less Soft Support. This is the most important difference. Supporters of Gore are placed into the "other / unsure" category. This is justifiable on the grounds that if "Poll Participant X" would choose Gore instead of a "Non-Gore Candidate Y" simply because Gore is included in the question, then "Poll Participant X" clearly is a very, very soft supporter of "Non-Gore Candidate Y." As I have long railed about the excessive pushing of undecideds and leaners in Democratic nomination polls this far from the actual primary / caucus season, this is actually a useful way to up the percentage of "other / unsure" even in polls like Gallup that push undecideds way too hard. At this point, it seems obvious that those who at this point would still support Gore are clearly undecided about the rest of the field (or, as I will discuss tomorrow, not yet engaged in the campaign). By contrast, those who support "Non-Gore Candidate Y" when gore is included in the question are harder supporters of "Non-Gore Candidate Y." thus, this chart produces a lower, but harder, estimate of support for all candidates. Even though I don't like unannounced candidates being included in poll questions, this methodology is a means of making lemonade out of lemon polls.

Otherwise, the two charts are methodologically identical. The excel spreadsheet I use to gather this data can be found here. Note that polls are added to the average the day after they are completed, and removed from the average fifteen days after they are completed. Only candidates averaging over 5.0% in national polls are included in the chart. Source polls can be found at Polling Report and Rasmussen. I will update this chart every three or four days throughout the entire primary / caucus season. Until the release of the next Rasmussen poll on Monday, results for April 27th are partial, and thus are not included in the chart.

Now Cross-Posted on Dailykos

For the past few months, I have been frustrated by the difficulty of determining rolling averages for national Democratic primary preference polls. There are three basic causes for this difficulty, but at long last I have developed system to deal with those three difficulties that I personally find satisfactory. Here are the three difficulties, along with my solution to each:

1. Not all polls include the same candidates in their questions. Polls that include Gore and Kerry artificially deflate the numbers for all other Democrats, while polls with only Hilary, Edwards and Obama artificially inflate the numbers for those three candidates. Thus, for my rolling poll average, I have decided to only include polls that include all announced candidates, and do not include either Gore or Kerry. This way, the numbers I am using in the averages are more compatible with one another.
2. Different polls sample different universes of voters. However, during my behind the scenes work on the Inflated Clinton Poll Theory, I now feel that the universes samples among the polls that meet criteria #1 are currently not different enough to pose a serious problem during averaging. While that includes Rasmussen and Gallup, both of whom are outliers in this regard, to a certain extent cancel each other out, both because they are outliers in opposite directions and because they are the two most prolific pollsters. I still believe a tighter sample of Democrats needs to be the universe all pollsters sample, and I will keep pushing for it behind the scenes, but this will do for now.
3. Different polls push undecideds to different degrees. This is still a problem, but name recognition among the three leading Democratic candidates that pushing undecideds no longer heavily favors Hillary Clinton. Obama and Edwards both hover around 90% name recognition among Democrats. By restricting myself to the post announcement period (mid-February and later), while this is still a problem, it is not as much of a problem.

Now, with all of this in mind, without further ado here are the national Democratic primary polling average from February 23rd until April 24th, presented in three and four day intervals:

Date	Clinton	Obama	Edwards	Others / Unsure
Apr 24	35.7%	28.4%	17.6%	18.3%
Apr 20	35.7%	28.0%	17.2%	19.1%
Apr 16	37.0%	26.3%	17.0%	19.7%
Apr 13	37.0%	24.5%	17.0%	21.5%
Apr 10	37.8%	22.8%	17.3%	22.1%
Apr 06	37.7%	23.3%	17.0%	22.0%
Apr 02	37.3%	23.3%	17.2%	22.2%
Mar 30	36.6%	24.6%	16.8%	22.0%
Mar 27	37.0%	25.4%	15.6%	22.0%
Mar 23	37.7%	26.0%	14.0%	22.3%
Mar 20	39.0%	26.3%	13.3%	21.4%
Mar 16	39.2%	27.5%	13.3%	20.0%
Mar 12	39.0%	26.8%	14.0%	20.2%
Mar 09	37.4%	27.1%	13.7%	21.8%
Mar 06	37.9%	27.1%	13.4%	21.6%
Mar 02	37.8%	24.8%	14.0%	23.4%
Feb 26	38.8%	24.5%	13.8%	22.9%
Feb 23	42.3%	23.0%	14.3%	20.4%

The excel spreadsheet I use to gather this data can be found here. Note that polls are added to the average the day after they are completed, and removed from the average fifteen days after they are completed. Only candidates averaging over 5.0% in national polls are included in the chart. Source polls can be found at Polling Report and Rasmussen. I will update this chart every three or four days throughout the entire primary / caucus season.

For now, I will leave analysis of this data to you. One thing I will note is how Edwards and Obama were stuck at a combined 38.3%--41.6% for a long time. However, over the last ten days, they have quickly risen to a combined 46.0%, mainly at the expense of others / unsure, but also, to a lesser extent, at the expense of Clinton. That strikes me as a particularly important trend in the campaign, one that is an entirely new development and that impacts every single announced candidate.