ArtsAutosBooksBusinessEducationEntertainmentFamilyFashionFoodGamesGenderHealthHolidaysHomeHubPagesPersonal FinancePetsPoliticsReligionSportsTechnologyTravel

Who Will the 2020 Democratic Nominee Be?

Updated on March 23, 2019

Updated Polling and Non-Polling Data - Mar. 23, 2019

This article will follow the probability of the most likely Democratic candidates to be nominated for President of the United States in the 2020 election. The aggregate projection combines non-polling (expert opinion, social media presence, traditional media presence, activist momentum, endorsements, and funding) and polling data. The total number of data points used in this analysis from beginning of the tracking project (November 20, 2018) until this update = 6,185 [Updated on March 23, 2019 with 87 new data points].

The author calls the reader's attention to the fact that Biden has not officially announced whether he is running.

On March 20, 2019, your author has decided to consider candidates or possible candidates with 1% polling in a group called the "Oneseys." These candidates are discussed in a separate capsule from those polling above 1%. As a result, the reader will not see Gabbard, Gillibrand, Hickenlooper and Castro in the main charts. Further, Yang and Buttigieg have been added to the statistical analysis. On March 23, 2019. John Delaney and Jay Inslee are being added. They will both appear in the "Onesey" capsule. If a candidate from the "Onesey" capsule hits 2% in polling, that candidate will be moved to the main capsule.


Aggregate, Non-Polling and Polling Probabilities of Nomination - Mar. 23, 2019


rank
Aggregate
Non-Polling
Polling
Biden
1
26
21
34
Sanders
2
22
20
25
Harris
3
16
19
11
O'Rourke
4
13
16
8
Warren
5
6
4
9
Booker
6
4
3
4
Klobuchar
7
3
3
3

Analysis of Aggregate, Non-Polling and Polling Data - Mar. 23, 2019

Four tiers have emerged: Tier 1 (Biden, Sanders); Tier 2 (Harris and O'Rourke); Tier 3 (Warren, Klobuchar and Booker); and Tier 4 (everyone else). One of the focal points of this author will be examining the probability that a candidate would move up to the next tier or down to a lower tier. Currently there is a 6 point gap between Sanders in Tier 1 and Harris in Tier 2. Likewise, there is a 7 point gap between O'Rourke in Tier 2 and Warren in Tier 3.

Biden now leads in non-polling as well as continuing to enjoy a large lead in polling. His lead in non-polling is 1 point over Sanders, 2 points over Harris and 5 points over O'Rourke. It would seems that any bounce due to his pending announcement (whenever that may be) will be small at best. His polling lead is 9 points over Sanders, 23 points over Harris, and 26 points over O'Rourke. Statistically, it would be expected that these leads will narrow over time but that Biden will remain ahead on the polling factor for at least several months into the future.

Sanders' non-polling number has probably leveled out but there is room for improvement on the polling side. Harris used to be a clear front-runner on non-polling but has now fallen to 3rd. She has definitely been hurt by Biden being more in the news and the Beto launch, in addition to Sanders staying front and center. Strategy will be a key for Harris. If she is not polling well in Iowa and New Hampshire, will she focus on South Carolina, Nevada and California? Sanders just campaigned in California showing it it would appear that he plans to be everywhere. O'Rourke is catching up, and the media is doing the same. Trying to figure out where Beto is going next, in terms of campaign stops is difficult at best. he has been driving himself and has not had has a chief advisor as yet.

Warren stays 5th and has not shown any propensity to make a serious run. Booker and Klobuchar at best are in the same tier with Warren but each looks comfortable to make the debate stage.

Your author is reasonably confident these are the top seven candidates.


Confidence Levels Mar. 23, 2019

 
Rank
1 dn
2 dn
3 dn
4 dn
Biden
1
68%
89%
95%
99%
Sanders
2
78%
87%
97%
99%
Harris
3
64%
88%
93%
94%
O'Rourke
4
80%
86%
87%
-
Warren
5
60%
62%
-
-
Booker
6
53%
-
-
-
Klobuchar
7
-
-
-
-
"x" dn = Confidence that candidate has an advantage over the competitor ranked "x" positions down the chart

Analysis of confidence levels - Mar. 23, 2019

The most important number to watch in this chart is the confidence level upper left. The 68% in the "dn 1" column means that we can be 68% confident that Biden, who is ranked 1st overall, has an advantage over Sanders who is ranked 2nd overall. The confidence that #1 ranked Biden leads Harris, O'Rourke and Warren is 89%, 95% and 99%. This shows that Biden's lead over Harris is quite substantial and that the advantage over O'Rourke and Warren is significant. With high confidence, we can say that O'Rourke should not be considered at the top rank with Biden and with very high confidence that Warren should not be considered competitive with Biden at this point in the campaign. In the last day, confidence for Biden in the Biden-Harris comparison increased 1% from 88% to 89%.

We can be reasonably confident that Sanders has a lead over Harris, quite confident that he has an advantage over O'Rourke and very confident that he leads both Warren and Booker. Currently, we can conclude that neither Warren nor Booker should be considered at the same level with Sanders. In the last day, confidence for Sanders improved 2% in the comparison with Harris.

Going down the list, we can be reasonably confident that Harris leads O'Rourke and quite confident that she leads Warren, Booker and Klobuchar. However, below the Sanders line, there are no confidence levels equal to or greater than 95%. I will only use terms like significant or very confident for cells where the number equals or exceeds 95%, which is the conventional threshold in social sciences for statistical significance.

O'Rourke continues to hold down the 4th position with little competition. We can be reasonably confident that he leads Warren, Booker, and Klobuchar.

In the last day, confidence for O'Rourke improved 2 points in the Sanders-O'Rourke comparison, 3 points in the Harris-O'Rourke comparison, 1 point in the O'Rourke-Warren comparison and 1 point in the O'Rourke-Booker comparison.

Warren improved 1 point relative to Sanders, Harris and Booker. She lost a point relative to Klobuchar.

Most Recent Four Polls - Mar. 23, 2019

 
SSRS 3-19
EM 3-19
PP IA 3-20
CHR 3-22
Biden
33
29
39
36
Harris
14
13
7
9
Sanders
23
29
20
24
O'Rourke
13
12
9
7
Warren
7
9
11
9
Booker
3
3
5
3
Klobuchar
3
1
8
2
CHR = Change research (national) SSRS = SSRS for CNN (national) PP IA - Public Policy Polling Iowa EM = Emerson (national)

Analysis of Recent Polls - Mar. 23, 2019

In this capsule, the reader will note analysis of recently added polls. Today, I look at how the recent national Change Research poll compares to the overall weighted average and what this poll may indicate about the nomination trend.

By examining residual variation, I am able to quickly note whether a candidate is over-performing her/his weighted average of all of the other polls or under-performing the average, and to what extent. The larger the percent a candidate's poll result contributes to the residual, the larger the deviation from the candidate's expected poll result based on past experience. Secondly, we are able to see whether the poll is an outlier (a relatively large residual variance) or in line with other polls. My benchmark for an outlier poll is when the residual variance exceeds 10%.

The Change Research national poll accounts for 99% of the variance of the weighted averages of the first 51 polls. The unexplained variance of 1% can largely be explained by a moderate over-performance by Biden, Buttigieg and Inslee and a moderate under-performance by Harris.

This Change Research poll asked about the race with Biden in the race and not in the race. With Biden in the race, he collected 36% support. The question is where does that 36% come from? The answer is 12 points from Sanders (33% of Biden support comes from Sanders in other words), 8 points from Harris, 7 points from O'Rourke and 4 points from Warren.

NOTE: Poll results which are used in the polling factor computations and listed in the chart above are based on the 7 main candidates plus the 8 "Oneseys" making for 15 candidates altogether.. The total therefore for the 15 candidates on any poll is 100% regardless of whether other candidates have received some percent of the vote. No preference tallies are reapportioned to the other candidates based on their standing at that time.


The "Oneseys" - Probability of Nomination - Mar. 23, 2019

 
Rank
Aggregate
Non-Polling
Polling
Yang
8
3
4
0
Buttigieg
9
2
3
1
Gabbard
10
2
2
1
Gillibrand
11
1
2
1
Hickenlooper
12
1
1
1
Castro
13
1
1
1
Inslee
14
1
1
0
Delaney
15
0
1
0

Analysis of the "Oneseys" - Mar. 23, 2019

Your author has separated out candidates who are polling at 1% or a fraction of 1%. Andrew Yang, Peter Buttigieg, Jay Inslee and John Delaney (all of whom have announced) have been added to the mix as each has received at least one point from non-polling or from polling to be recognized. The apparent conclusion is that based on non-polling factor alone that Yang is a candidate to be reckoned with. Yang is currently rated 5th in non-polling ahead of Warren and his aggregate score of 3% places him in 8th overall.. However, he has been included in polls only rarely. Buttigieg has been included in some polls and recently received 3% in the Emerson and 2% in the Change Research national polls. Buttigieg however has not matched Yang's non-polling interest. Overall, this has placed Yang above Buttigieg who has now surpassed both Gabbard and Gillibrand. Hickenlooper and Castro are now 12th and 13th. Inslee and Delaney are rated 14th and 15th respectively. Inslee has received some support as he polled at 2% in the recent Change Research survey.

What do second choices tell us? - Mar. 4, 2019

The recent Morning Consult-Politico poll provides data on "second choice candidates." This is like my saying "table" and you say ... "chair." The problem in politics is what is the connection - why do people make that association?

Biden supporters chose Sanders by a 28%-11% margin over Harris. That makes sense because arguably they are the political figures best known in the field.

Turn that around and we find that Sanders supports Biden 2nd with a margin over Harris of 29%-7%, considerably larger than the margin above. the reason for the differential is that for supporters of Sanders, after Biden comes Warren 3rd (Biden at 29% and Warren at 16%). This is when we begin to see what we could do with a cluster analysis, since Sanders and Warren seem to be linked.

As to Harris, who polls 3rd overall, her 2nd choice is Biden at 17% and Sanders at 16%, so for Harris none of the top five candidates appear to be within her cluster group.

The key is Warren. Second choice is Sanders at 27%, 3rd is Biden at 17%, showing again that Warren and Sanders belong to the same cluster group. This would be good news if it holds for one or the other candidate if the respective candidate drops out.

For O'Rourke, Biden is 2nd at 22% and Sanders 3rd at 21%, so again no obvious cluster, at least yet.

Sanders and Warren are both fighters but you can only fight as long as you have money to do so. As of this moment, if one of these candidates were to drop out, it would be Warren and therefore Sanders would benefit substantially if this data holds.

Your author will continue to examine this poll for changes over the weeks and months to come.

Latest News Regarding Possible Democratic Nominees - Mar. 14, 2019

On March 14, 2019, Beto O'Rourke announced he is running. On the morning of the announcement, he is positioned in 4th on the aggregate ranking, 4th in non-polling and 5th in polling. The probability that he should currently be ranked 1st is 7%, 2nd is 12% and 3rd is 21%. In other words, he has a considerable way to go to get to even 3rd place in the short term.

On March 7, 2019, Senator Sherrod Brown announced he is not running. On the day of the announcement, he was mid-pack in the second five on the ranking of candidates.

On March 5, 2019, Michael Bloomberg announced he was not running. All of his non-polling and polling data were zeroed out and proportionally reassigned to the remaining candidates based on their standing. The net effect is that (a) the battle for 6th is now between Klobuchar, Booker and Brown and (b) Gabbard and Gillibrand will now compete for 9th.

On March 4, 2019, John Hickenlooper, former Governor of Colorado announced he was running. On the morning of his announcement, he was judged to be 13th in this tracking project.

On March 1, 2019, Governor Jay Inslee (WA) announced he was running. Inslee is best known for driving decisions based on climate change. Since the beginning of this tracking project, over 38 polls, he has received 1% in only one poll (CNN-SSRS Dec-9). As a result he does not register (perhaps yet) in my top 13 candidates. In order to make the first debate in June, he will need to pickup polling and/or fund raising support.

On February 19, 2019, in a morning email to supporters, Senator Bernie Sanders (VT) announced he was launching a bid for the Presidency. At the point of this announcement (before new non-polling data was added the same day), Sanders placed 3rd overall on my chart, slightly ahead of O'Rourke, 4th on the non-polling factor slightly ahead of Klobuchar and a solid 2nd on the polling factor.


On February 10, 2019, Senator Amy Klobuchar (MN) announced she was running, outside in the middle of a raging snowstorm, against the backdrop of the I-35 bridge which collapsed in 2007 and has not been fixed. As of the date of her announcement, she is ranked 6th on my chart with an aggregate 4%. Positions 6-10 are very close.

On February 1, 2019, Senator Cory Booker (NJ) announced he was joining the field of candidates. Booker has held a position right around 7th place in my analysis for most of the last two months. He is grouped with Klobuchar, Brown and Bloomberg behind Warren and ahead of Gillibrand and Gabbard.

On January 29, 2019, we have our first withdrawal of a candidate from my original list of 15. Eric Garcetti, Mayor of Los Angeles, has announced he is not running.

On January 25 and 26, 2019, there were several news stories which have begun to shift the political landscape. First, there was excitement that insiders supposedly were saying that Senator Bernie Sanders (VT), who had run in the 2016 primary against Hillary Clinton, was definitely going to announce he was running again, and that the announcement was imminent. Second, there was a story that O'Rourke was admittedly exhausted after his Senate run in Texas and that he would take a few months to figure out if he was going to run. Third, Harris officially launched her campaign before a large rally in California. The net result has been that Sanders moved to 3rd, but as of this update, the O'Rourke has stopped losing ground and Sanders again is placed 4th and O'Rourke now 3rd. Harris is a solid 2nd.

On January 21, 2019, Senator Kamala Harris (CA) officially announced. The day she announced, she was ranked third in aggregate on my chart behind Beto O'Rourke and Joe Biden.


On January 15, 2019, Senator Kirsten Gillibrand (NY) announced she was entering the race. On the day of her announcement, she started in 11th place overall. Since the announcement she has been ranked 10th or 11th.

On January 12, 2019. Former Secretary of Housing and Urban Development, Julian Castro officially announced his candidacy. With the announcement, Castro moved from 15th to 12th and has been 12th or 13th ever since. The news on January 15, 2019 was not particularly favorable to Castro. When he was a council member in San Antonio in 2002, he voted for $600,000 in subsidies to bring the Miss USA beauty pageant to the city, an event operated by none other than Donald Trump.

On January 11, 2019, Representative Tulsi Gabbard (HA) announced she was making a run. On the day of her announcement, this analysis had her ranked in 11th place. She has been ranked as high as 9th but has now dropped back to 11th.

On December 31, 2018 - Elizabeth Warren announced she was forming an exploratory committee. Your author had her rated in 5th place the morning of her announcement. As of this update, she remains 5th now behind O'Rourke and ahead of Booker. Warren had the weakest performance to date since late November 2018 in terms of momentum of any of the top candidates moving from 3rd to 5th on my list.

The First Debate June 2019

Based on the rules as your author understands them so far, the following candidates appear to qualify based on either or both polls and donors: Biden, Sanders, Harris, O'Rourke, Warren, Booker, Klobuchar, Buttigieg and Yang. Nate Silver at 538 says (tentatively) Gillibrand is in but I have her at a weighted average (my calculation not the DNC one) at 1.05% and I do not believe she has met the donor requirement - so she looks really close to me. Also Silver has Castro (again tentatively) as in but I have him at only .98% for my weighted average polling number and I do not believe has has qualified for donors either. On the bubble would seem to be Gabbard who I have at a poll number of only .59% and I understand she still needs more donors. Your author is still looking at the details for the polling criteria.

The Democratic National Committee announced details regarding rules about which candidates may appear in the first debate in June 2019. While your author is still searching for additional information, that is what has been presented so far. The number will be limited to 20 candidates over two nights. Selection of whom will appear each night will be based on a random draw. Candidates can qualify by receiving a minimum of 1% in three national (or first four caucus/primary states) polls and/or a minimum of 65,000 small donor contributions nationally and at least 200 donations in each of 20 states. If more than 20 candidates qualify, the tiebreaker is reportedly first the candidates who qualify under both the polling and fund raising criteria. If that does not get the number down to 20, then there is a vague statement that the criteria will be increased and rely more on polling.

Clarity is needed on the definition of which polls count, only three, the last three only certain ones?. Also, is 1% an average or a minimum on each poll? This was an issue in the 2016 GOP rules setting protocol. Further, there is a question about whether the state polls will have any weight. Finally, the final tiebreaker lacks any clarity.

Changes to Primary Schedule and Rules - Mar. 9, 2019

The Democratic party has made significant changes to the schedule and the rules. Although final dates for the key Iowa Caucus and the New Hampshire primary are not finalized, we know that those two events begin the election season, followed by South Carolina and Nevada, with right now all four elections slotted for February.. That order has not changed and the interval between those elections will not change. However, California and Texas have both moved to Super Tuesday.

Second, in 2016, the minimum percent in a primary the candidate needed to earn delegates was 15% and that rule is being maintained. This rule as applied to 2020 will make much more of a difference in a crowded field. For example, if we apply this rule to exactly where candidates currently stand on the polling weighted average, only two candidates (Biden and Sanders) have more than 15% of the poll results, meaning they would share all of the delegates in a state and none of the rest would receive any. As an example, were Biden to finish a state with 35% and Sanders 23%, Biden would receive 60% of the delegates and Sanders 40%.

The third change resulted from the "tilt" of the 2016 nomination process where Clinton had a huge lead in super-delegates, which meant that Sanders was always in catch up mode. The party realized the problem (apparently) and now super-delegates cannot cast a vote until a second ballot if one is needed.

Notes on computations and weightings - Mar. 23, 2019

As of March 21, 2019, 52 polls have been used to create the polling component: As of this update, the three polling firms which represent the largest contribution to the weighted polling average are as follows: Politico-Morning Consult (34%), Emerson (21%) and Change Research (8%). In terms of specific polls, the three highest weighted polls to date are the DesMoines-Selzer March 9 poll (4.55%), the Monmouth March 9 poll (4.36%) and the SSRS-CNN Mar-19 poll (4.09%).

Note on polling and non-polling weights and the calendar date: On March 22, 2019, the polling factors changed. When computing the polling factor, the calendar date polling value this week is 3.40. This means that the calendar date value for polls this week is 3.40 times as large as polls taken the first week of December 2018. When computing the aggregate score, the non-polling factor weight this week is 60.25% and the polling factor weight this week is 39.75%. The details on computations and all weights may be found below.

The weight given to each poll is the product of [log base 10 X sample size] X the [poll priority] X the [calendar date polling value]. Note that if the sample size of a poll exceeds 17,711, that the calculation will use a sample size of 17,711, the same number that will be used when primary and caucus popular vote data is incorporated beginning February 2020.

Poll priority values are Monmouth 10, DesMoines Register-Selzer IA 10, CNN-SSRS 8, Emerson (all) 7, University of New Hampshire NH 6, Politico-Morning Consult 5, Harvard-Harris 4, Change Research 4, Zogby 3, Firehouse Strategies-Optimus (all) 2, McLaughlin 2, Iowa Rural 1 and Bold Blue Campaigns 1 . When caucuses and primaries occur, the popular vote will be captured for each as if the election were a poll (priority will be set at 20, n=17,771 (if state popular vote exceeds 17,771) and the calendar date of that election will be used in the formula).

The calendar date polling value was set on December 1, 2018 at 1.00. The calendar date polling value increased by .02 to 1.02 on December 8, 2018. Then each week thereafter, the differential increase week to week is another .02. For example, in the 3rd week of December 2018, the value increased .04 and then the 4th week the value increased .06 etc through the nomination process. In that way, the most recent polls receive an increasingly higher priority week to week and month to month. For comparison sake, the calendar date polling value the last week of May 2020 will be 52.26 which means that any poll taken the last week of May 2020 will be about 52 times as important than the first week of December 2018.

The weekly non-polling factor across each week and month was set at 64.00 on December 1, 2018, decreasing 0.25 points each week until February 1, 2020. At that time, the non-polling factor will decrease 1.0 points each week (four weeks per month) through the nomination.

The weekly polling factor across each week and month was set at 36.00 on December 1, 2018, increasing 0.25 points each week until February 1, 2020. At that time, the polling factor will increase 1.0 point each week (four weeks per month) through the nomination.

Comments

    0 of 8192 characters used
    Post Comment

    No comments yet.

    working

    This website uses cookies

    As a user in the EEA, your approval is needed on a few things. To provide a better website experience, hubpages.com uses cookies (and other similar technologies) and may collect, process, and share personal data. Please choose which areas of our service you consent to our doing so.

    For more information on managing or withdrawing consents and how we handle data, visit our Privacy Policy at: https://hubpages.com/privacy-policy#gdpr

    Show Details
    Necessary
    HubPages Device IDThis is used to identify particular browsers or devices when the access the service, and is used for security reasons.
    LoginThis is necessary to sign in to the HubPages Service.
    Google RecaptchaThis is used to prevent bots and spam. (Privacy Policy)
    AkismetThis is used to detect comment spam. (Privacy Policy)
    HubPages Google AnalyticsThis is used to provide data on traffic to our website, all personally identifyable data is anonymized. (Privacy Policy)
    HubPages Traffic PixelThis is used to collect data on traffic to articles and other pages on our site. Unless you are signed in to a HubPages account, all personally identifiable information is anonymized.
    Amazon Web ServicesThis is a cloud services platform that we used to host our service. (Privacy Policy)
    CloudflareThis is a cloud CDN service that we use to efficiently deliver files required for our service to operate such as javascript, cascading style sheets, images, and videos. (Privacy Policy)
    Google Hosted LibrariesJavascript software libraries such as jQuery are loaded at endpoints on the googleapis.com or gstatic.com domains, for performance and efficiency reasons. (Privacy Policy)
    Features
    Google Custom SearchThis is feature allows you to search the site. (Privacy Policy)
    Google MapsSome articles have Google Maps embedded in them. (Privacy Policy)
    Google ChartsThis is used to display charts and graphs on articles and the author center. (Privacy Policy)
    Google AdSense Host APIThis service allows you to sign up for or associate a Google AdSense account with HubPages, so that you can earn money from ads on your articles. No data is shared unless you engage with this feature. (Privacy Policy)
    Google YouTubeSome articles have YouTube videos embedded in them. (Privacy Policy)
    VimeoSome articles have Vimeo videos embedded in them. (Privacy Policy)
    PaypalThis is used for a registered author who enrolls in the HubPages Earnings program and requests to be paid via PayPal. No data is shared with Paypal unless you engage with this feature. (Privacy Policy)
    Facebook LoginYou can use this to streamline signing up for, or signing in to your Hubpages account. No data is shared with Facebook unless you engage with this feature. (Privacy Policy)
    MavenThis supports the Maven widget and search functionality. (Privacy Policy)
    Marketing
    Google AdSenseThis is an ad network. (Privacy Policy)
    Google DoubleClickGoogle provides ad serving technology and runs an ad network. (Privacy Policy)
    Index ExchangeThis is an ad network. (Privacy Policy)
    SovrnThis is an ad network. (Privacy Policy)
    Facebook AdsThis is an ad network. (Privacy Policy)
    Amazon Unified Ad MarketplaceThis is an ad network. (Privacy Policy)
    AppNexusThis is an ad network. (Privacy Policy)
    OpenxThis is an ad network. (Privacy Policy)
    Rubicon ProjectThis is an ad network. (Privacy Policy)
    TripleLiftThis is an ad network. (Privacy Policy)
    Say MediaWe partner with Say Media to deliver ad campaigns on our sites. (Privacy Policy)
    Remarketing PixelsWe may use remarketing pixels from advertising networks such as Google AdWords, Bing Ads, and Facebook in order to advertise the HubPages Service to people that have visited our sites.
    Conversion Tracking PixelsWe may use conversion tracking pixels from advertising networks such as Google AdWords, Bing Ads, and Facebook in order to identify when an advertisement has successfully resulted in the desired action, such as signing up for the HubPages Service or publishing an article on the HubPages Service.
    Statistics
    Author Google AnalyticsThis is used to provide traffic data and reports to the authors of articles on the HubPages Service. (Privacy Policy)
    ComscoreComScore is a media measurement and analytics company providing marketing data and analytics to enterprises, media and advertising agencies, and publishers. Non-consent will result in ComScore only processing obfuscated personal data. (Privacy Policy)
    Amazon Tracking PixelSome articles display amazon products as part of the Amazon Affiliate program, this pixel provides traffic statistics for those products (Privacy Policy)