2020 Democratic primaries on March 10: My final polling update

[Updated at 4:00 pm EST to account for late polls]

On March 10, 2020, six more states will hold primaries to help select the 2020 Democratic presidential nominee, bringing the total number of such contests to 24. Table 1 lists these states, sorted by poll closing times, and the number of pledged delegates each state will provide to the Democratic National Convention, which will be held July 13-16, 2020 in Milwaukee, Wisconsin. A total of 352 pledged delegates are available on March 10, 8.8% of the total 3,979 to be awarded.[1]

Table 1: Democratic presidential nominating contests, March 10, 2020 by Poll Closing Times

Jurisidiction Poll Closing (EST) Pledged Delegates
Mississippi 8 pm 36
Missouri 8 pm 68
North Dakota 8 pm 14
Michigan 9 pm

(79 of 83 counties close at 8 pm)

Idaho 11 pm 20
Washington 11 pm

(balloting by mail)


In a previous post, I presented final polling updates for the 14 states (including American Samoa and Democrats Abroad) holding Democratic presidential nominating contests on March 3. Unlike previous contests in Iowa, New Hampshire, Nevada and South Carolina, however, I have not yet posted a comparison of these polling averages to the final results. That is because votes are still being counted in California, while Dallas County in Texas may recount its votes.

Nonetheless, it is apparent that former Vice President Joe Biden strongly overperformed his final polling averages, emerging with an overall lead of 77 pledged delegates,[2] while United States Senator (“Senator”) from Massachusetts Elizabeth Warren largely underperformed. Indeed, Warren ended her bid for the 2020 Democratic presidential nomination on March 5; former New York City Mayor Michael Bloomberg had already ended his bid one day earlier. However, while Bloomberg immediately endorsed Biden, Warren has yet to endorse any other candidate. Meanwhile, on March 9, 2020 two more former rivals, New Jersey Senator Cory Booker and California Senator Kamala Harris, endorsed Biden at a Detroit, Michigan rally.

Three declared candidates remain for the 2020 Democratic presidential nomination—down from 28 in total:

  • Biden
  • United States House of Representatives Member from Hawaii Tulsi Gabbard
  • Vermont Senator Bernie Sanders


In the remainder of this post, I present final WAPA (weighted-adjusted polling average) for Biden, Gabbard and Sanders in each state, calculated up to two ways depending upon available data polls are up-to-date as of 2 am EST March 10, 2020. As with the 18 previous contests, a candidate must win ≥15% of the vote to be awarded delegates either statewide or within a Congressional district. All publicly-available polls conducted since January 1, 2019 may be found here.

And here is my updated weighting scheme:

  • Polls conducted entirely or partially after February 3, 2020, but before February 12, 2020 are weighted 2.00 or 1.00+fraction[3] times, respectively, higher than polls conducted entirely before February 4, 2020.
  • Polls conducted entirely or partially after February 11, 2020, but before February 23, 2020 are weighted 3.00 or 2.00+fraction times, respectively, higher than polls conducted entirely before February 12, 2020.
  • Polls conducted entirely or partially after February 22, 2020, but before March 1, 2020 are weighted 4.00 or 3.00+fraction times, respectively, higher than polls conducted entirely before February 23, 2020.
  • Polls conducted entirely or partially after February 29, 2020, but before March 4, 2020 are weighted 5.00 or 4.00+fraction times, respectively, higher than polls conducted entirely before February 29, 2020.
  • Polls conducted entirely or partially after March 3, 2020, but before March 11, 2020 are weighted 10.00 or 5.00+fraction times, respectively, higher than polls conducted entirely before March 4, 2020.

To provide context for the percentage either truly undecided or selecting a different candidate (“DK/Other”), I also include the aggregate final state WAPA for Bloomberg; former South Bend, Indiana Mayor Pete Buttigieg; Minnesota Senator Amy Klobuchar; billionaire activist Tom Steyer and Warren combined (“BBKSW”). Their supporters still comprise a sizeable proportion of the “DK/Other” group in some states, adding a modicum of additional uncertainty to the outcomes of Tuesday’s races.

8 pm EST


Only four polls were conducted here, with only two—with an average rating of C+ according to FiveThirtyEight.com’s pollster ratings—conducted after July 2019. Overall, Biden leads Sanders 72.1 to 24.5%, with Gabbard at 0.5% It would not be surprising if Biden netted more than 12 pledged delegates here


Here is the breakdown of publicly-available polls of the 2020 Missouri Democratic Primary:

  • 9 since January 1, 2019
  • 5 since the Iowa Caucuses on February 3, 2020

Table 2: Final Missouri Primary WAPA for declared 2020 Democratic presidential nomination candidates

Candidate All Polls Post Iowa Caucuses
Biden 53.9 54.3
Sanders 34.5 35.0
Gabbard 2.0 2.1
DK/Other 9.6 8.7
BBKSW 4.3 3.6

Biden appears headed for a sizeable victory in the Show Me state and could easily net 12 or more pledged delegates.

North Dakota

Only one polls was conducted of the 2020 North Dakota Democratic presidential primary, by Swayable (C+) from March 7 to March 9,  2020; Biden led Sanders 65 to 31%, with 0% for Gabbard. In 2016, though, when North Dakota held caucuses, Sanders beat former Secretary of State Hillary Clinton 64.2 to 25.6%, netting eight pledged delegates; all 2016 Democratic presidential nomination contest results are from Dave Liep’s invaluable Atlas of U.S. Presidential Elections. Rather than extrapolate from a single, low-rated poll, so I will split the difference and say both Biden and Sanders earn seven pledged delegates here.

9 pm EST


The company for which I worked in 2000-01 was headquartered in Ann Arbor, home to the University of Michigan, so I spent the equivalent of four weeks in Michigan over those two years. Here I am standing in front of the original headquarters of Motown Records in June 2001.


Here is the breakdown of publicly-available polls of the 2020 Michigan Democratic Primary:

  • 21 since January 1, 2019
  • 10 since the Iowa Caucuses on February 3, 2020

Table 3: Final Michigan Primary WAPA for declared 2020 Democratic presidential nomination candidates

Candidate All Polls Post Iowa Caucuses
Biden 52.0 53.2
Sanders 31.8 32.6
Gabbard 0.8 0.8
DK/Other 15.4 13.4
BBKSW 4.9 3.8

While it might appear that Biden is headed for a win of a least 20 percentage points (“points”) in the Wolverine State, a similar polling lead for Clinton here four years ago turned into a 49.7-48.3% upset for Sanders, though Clinton still net 2 pledged delegates. Splitting the difference would give Biden a solid 10-point win, netting 12-15 pledged delegates.

11 pm EST


Only two polls were conducted of the 2020 Idaho Democratic Presidential Primary, both by C+ pollsters after the Iowa Caucuses; on average, Biden led Sanders 51.5-42.5%, with Gabbard earning 2%. A close Idaho finish between Biden and Sanders would be in stark contrast to 2016, when Sanders won what were then caucuses 78.0 to 21.2%, netting 13 pledged delegates. I expect a tighter race this time, with maybe an 11-9 split in delegates for Sanders.


Every election in the state of Washington is conducted by mail; all ballots for this primary must be postmarked by March 10 or placed in a ballot drop box by 8 pm local time. As with California, no winner could be declared until Wednesday morning at the earliest.

Here is the breakdown of publicly-available polls of the 2020 Washington Democratic Primary:

  • 7 since January 1, 2019
  • 4 since the Iowa Caucuses on February 3, 2020

Table 4: Final Washington Primary WAPA for declared 2020 Democratic presidential nomination candidates

Candidate All Polls Post Iowa Caucuses
Biden 35.0 35.6
Sanders 35.1 35.4
Gabbard 1.1 1.1
DK/Other 28.8 27.8
BBKSW 11.8 11.1

Four years ago, when Washington—like Idaho and North Dakota—held caucuses, Sanders crushed Clinton 72.7 to 27.1%. This year, though, the race between Biden and Sanders appears much closer—though with two in seven potential primary voters up for grabs, either candidate could win by a double-digit margin. On balance, though, a 53-47% Sanders win is a plausible outcome, with a net of four-five pledged delegates.

There are two reasons to be extremely cautious about these “projections.” First, of these six contests, only Michigan’s Democratic voters were polled more than nine times, and even they were only polled 21 times by a total of 18 pollsters whose average rating is B-. Second, it is not unusual for primary and caucus voters to hit the brakes on a seemingly-certain nomination process; this is one explanation for Sanders’ Michigan upset in 2016. This can occur in one of two ways: voters who are only leaning toward the front-runner stay home, and other voters affirmatively choose an alternate candidate as a way of declaring “the race is not over because we have not yet had our say.”

All of this is to say: while Biden could easily come out of the March 10 primaries with a net gain of 56 pledged delegates (splitting the BBKSW percentage 3-2 for Biden and the “pure DK/Other” percentage 2-1 for Sanders)…

…there is a plausible scenario—Biden and Sanders split Idaho and North Dakota, Sanders wins Washington 53-47% and splits Michigan nearly evenly—in which Biden “only” nets 24 pledged delegates.

We shall see.

Until next time…

[1] An additional 764, at least, “automatic delegates” (also known as “superdelegates”)—mostly elected Democrats—would vote on a second ballot if no candidate clears the 1,991-vote threshold on the first ballot at the Democratic National Convention.

[2] According to NBC News, as of 2 am EST on March 10, 2020

[3] Percentage of days the poll was being conducted were after the most recent primary or caucuses

2020 Nevada Caucuses: Final Polling Update

At 10 am Nevada time (1 pm EST) on February 22, 2020, Nevadans who did not already vote between February 15 and 18 by submitting a ranking of their three top choices to be the 2020 Democratic nominee will gather in nearly 2,100 meeting places to support their preferred candidate(s). While about 84,000 Nevadans caucused for Democrats in total in 2016, the number of Nevadans who voted early in 2020 is estimated to be at least 70,000.

This post presents four variations on my final pre-Caucuses WAPA, calculated using the four different timeframes detailed below. To learn how I calculate candidate WAPA (weighted-adjusted polling averages), please see here. Polls conducted partially or entirely after the Iowa Caucuses, but before the New Hampshire Primary, are weighted up to 1.33 to 2.00 times higher than polls conducted before the Iowa Caucuses. Polls conducted partially or entirely after the New Hampshire Primary are weighted 2.33 to 3.00 times higher than polls conducted before the New Hampshire Primary.

I have never been to Nevada, so here is the February 2020 lighthouse photograph in my Down East 2020 Maine Lighthouses wall calendar.

Feb 2020 lighthouse


As of midnight EST on February 22, 2020, here is the breakdown of publicly-available Nevada Caucuses polls.

  • 22 conducted since January 1, 2019
  • 19 conducted since the 1st Democratic debate on June 26, 2019
  • 10 conducted since the 5th Democratic debate on November 19, 2019
  • 7 conducted since the 7th Democratic debate on January 14, 2020

First, however, here are some words of caution.

1. Very few high-quality polls

Only 22 polls of the Nevada Caucuses have been conducted since January 1, 2019, considerably fewer than the 59 polls of the Iowa Caucuses and the 72 polls of the New Hampshire Primary conducted over the same period of time. Overall, the 15 pollsters operating in Nevada, as a group, compare favorably to the 19 pollsters who operated in Iowa and the 21 who operated in New Hampshire: all three sets of pollsters averaged a B/B-, using FiveThirtyEight.com pollster ratings. However, only one of the seven polls conducted since the January 14, 2020 Democratic debate was conducted by a pollster who do have either a B/C (three) or a C+ (three) rating: an Emerson College poll (A-) conducted February 19-20, 2020. This poll is weighted 2.57; no other poll is weighted higher than 1.76.

The combination of many fewer polls, a dearth of recent high-quality polls and the fact polling in Nevada is extremely challenging in the best of circumstances makes these final Nevada Caucuses WAPA even more “wobbly” than those for the unpredictable Iowa Caucuses.

2. Reporting snafus 2.0?

Recall that in a caucus setting, voters literally declare their preferences in a public setting. If, after an initial tabulation, a candidate does not have the support of at least 15% of that site’s caucus attendees, supporters of that candidate either join a group that does (i.e., is “viable”), the “uncommitted” group or call it a day. This realigning continues until only viable candidates remain, at which time a complex formula is used to calculate “state delegate equivalents,” or SDEs. Prior to 2020, only the percentage of SDEs won were reported.

However, as was the case in Iowa, this year the Nevada Democratic Party plans to report three sets of results:

  • The initial statewide tally for each candidate
  • The post-viability tally for each candidate
  • SDE’s for each candidate

Having to report all three tallies in Iowa proved so difficult it ultimately cost the state’s Democratic Party Chair, Troy Price, his job. The Nevada Democratic Party has reassured us it is doing everything it can to report the results of its caucuses in a timely manner, though accuracy should always be prioritized over speed. There is a vast difference between conducting an election and reporting the results of that election; the former should take precedence over the latter, whatever the discomfiture level of journalists waiting to report results.

With those two caveats, Table 1 presents the final pre-Caucuses WAPA for the eight remaining candidates for the 2020 Democratic presidential nomination; even though former New York City Mayor Michael Bloomberg is not actively campaigning in Nevada, he is included as Nevadans could theoretically caucus for him.

Table 1: Final Nevada Caucuses WAPA for declared 2020 Democratic presidential nomination candidates

Candidate All Polls Since 1st Debate Since 5th Debate Since 7th Debate
Sanders 24.6 24.8 26.4 27.8
Biden 19.6 19.0 16.8 15.5
Warren 13.4 13.4 11.4 11.2
Buttigieg 10.9 11.0 12.6 13.7
Steyer 9.8 9.8 12.2 12.9
Klobuchar 6.5 6.3 8.3 9.4
Gabbard 1.4 1.3 1.5 1.5
Bloomberg 0.1 0.1 0.1 0.0
DK/Other 13.7 14.4 10.6 7.9

United States Senator (“Senator”) from Vermont Bernie Sanders would appear to have a significant edge—and momentum—heading into the final day of caucusing in Nevada. Increasingly falling behind Sanders are five candidates bunched relatively close together: former Vice President Joe Biden; Massachusetts Senator Elizabeth Warren; former South Bend, Indiana Mayor Pete Buttigieg; billionaire activist Tom Steyer and Minnesota Senator Amy Klobuchar. However, while Buttigieg, Steyer and Klobuchar appear to have some momentum heading into Saturday, Biden and Warren are fading somewhat, though we have no idea how Warren’s dominant February 19 debate performance will impact her final results. After a similarly-strong performance, Klobuchar outperformed her final New Hampshire WAPA by an average of 11.5 percentage points (“points”); were Warren to jump even one-third that amount—around four points—she could easily finish in 2nd place.

The bottom line.

As with the earlier Iowa Caucuses, anybody who thinks they know what will happen in the 2020 Nevada Democratic Caucuses has absolutely no idea what will happen in the 2020 Nevada Democratic Caucuses. Polling is very difficult to do in a multi-candidate race, with caucuses adding the additional wrinkle of unknowable “backup” choices or even who will participate. Combine this with a noticeable lack of recent high-quality polling, and we have something more akin to a gut-level hunch than a scientific projection.

It may very well be Sanders is the heavy favorite to win the Nevada Caucuses with literally every other candidate struggling to reach the 15% viability threshold, but I would not bet anything remotely of value on it.

We shall see.

Until next time…

Organizing by themes X: Doctor Who

This site benefits/suffers/both from consisting of posts about a wide range of topics, all linked under the amorphous heading “data-driven storytelling.”

In an attempt to impose some coherent structure, I am organizing related posts both chronologically and thematically.

Having run through nine different “themes” of this blog…

…I will now add new themes as the need arises.

TARDIS phone

I first addressed the television series Doctor Who over three posts in December 2016/January 2017. These posts constituted a preliminary attempt to use online ratings data to assess the relative popularity of each episode released since the series was revived in March 2005:

Rating Doctor Who, Episode 1

Rating Doctor Who, Episode 2

Rating Doctor Who, Episode 3

Following Series 10 in 2017, I updated, refined and edited these analyses into a single July 2018 post.

In the summer of 2018, I wrote an essay of roughly 10,000 words detailing the influence of classic film noir on the “resurrected” series. Three edited versions later, in May 2019, I published a 7,600+-word version in four parts on this site.

The Noir of Who: Backstory and Part 1

The Noir of Who: Part 2

The Noir of Who: Part 3

The Noir of Who: Part 4

A PDF of the complete essay may be found here.



Organizing by themes IX: The random bits

This site benefits/suffers/both from consisting of posts about a wide range of topics, all linked under the amorphous heading “data-driven storytelling.”

In an attempt to impose some coherent structure, I am organizing related posts both chronologically and thematically.

Having run through the primary themes of this blog…

…all that remains are a few personal odds and ends which defy easy characterization, although the first two have been referenced obliquely in a few of the preceding organizational posts.

–An attempt to find the good news from the year 2016

–A literal collection of “odds and ends” from July 2017

–How difficult it can be to separate the art from the artist who produced it.

–Some thoughts on St. Valentine’s Day (spoiler alert: thumb down) followed by some absurd and funny bits.

–A sampling of my taste in fiction, based upon a Facebook challenge (show one book a day for seven straight days with no explanations):

Detective Fiction

Oscar Wilde/George Bernard Shaw

–Random facts about me

Questions asked…and answered

For my 100th post…100 random facts

–Moving experiences

Moving memories

Moving serendipity

And that is about it.

Well, not quite…a post about random blog posts should be accompanied by a random photograph of random things:

IMG_0967 (2).JPG

Until next time…

Updating the Doctor(s)

This spring, we learned that the charming three-story brick townhouse whose ground and basement floors Nell and I have occupied since September 2007 was being sold. As a result, we four will move into a nearby Brookline apartment (nicer and with a spectacular view of Boston, to be fair) at the end of July.

While that was happening, I was finishing an essay on the manifestations of film noir in the resurrected Doctor Who I would love to have published in the Film Noir Foundation quarterly e-magazine or other equally-solid periodical. If nothing else, it will better contextualize this photograph.


To prepare for the move, I undertook a massive purge of my office space, throwing out/recycling at least one full trash bin of detritus. Some items I re-discovered will likely be fodder for an upcoming post.

Needless to say, things have been hectic around here.

But given the revelatory side effects of moving, my essay and the full-episode debut of Jodie Whittaker as the 13th Doctor—the first to be played by a woman—this fall (see the 12th Doctor’s “brilliant” regeneration here), I decided to dig deep into my own timeline (here, here and here) for this post. Specifically, I updated (all data as of July 17, 2018) and edited those original Doctor Who posts into a single continuous narrative:

Along the lines of my Charlie Chan film ranking, I collected data on the relative popularity of the 144 episodes of the resurrected Doctor Who[1], from “Rose” (March 26, 2005) through the 2017 Christmas special “Twice Upon a Time.” Excluding John Hurt’s War Doctor, there have been four incarnations of The Doctor during this time period: #9-12. These 144 episodes comprise 10 12-13 episode Series plus 13 Christmas specials and four specials, three featuring the 10th Doctor (David Tennant) as well as the November 2013 50th anniversary epic, in which Doctors 10 and 11 (Matt Smith) teamed with the War Doctor to save Gallifrey, The Doctor’s home planet.

For each episode, I collected four values:

  1. Its BBC “Audience Appreciation Index” (AI) score, an integer from 0-100 revealing how much the (British) audience enjoyed each episode when it first aired. Higher scores indicate greater enjoyment.
  2. Where the episode ranked that week (Chart), with a lower score indicating more viewers.
  3. Its weighted-average Internet Movie Database (IMDB) score on a 0-10 scale, with 10 being the most favorable) and…
  4. The number of IMDB “raters” whose scores were averaged. The higher the number of raters, in principle, the more “compelling” the episode—though higher ratings could also simply reflect a longer rating time frame.

The goal is to assess the relative popularity of individual episodes, both when first released and with hindsight, as well as of the Series and Doctors. I decided to ignore “Chart” values as they were difficult to compare over time.

Table 1 provides details on each Series. It excludes the 13 Christmas specials (2005-17—“Twice Upon a Time” technically marks the start of Series 11), two 2009 10th Doctor specials (“Planet of the Dead,” “The Waters of Mars”) and “The Day of the Doctor.”

Table 1: Doctor Who Series (2005-17)

# Dates # Episodes Doctor Primary Companion(s)
1 March 26-June 18, 2005 13 9 Rose Tyler
2 April 15-July 8, 2006 13 10 Rose Tyler
3 March 31-June 30, 2007 13 10 Martha Jones
4 April 5-July 5, 2008 13 10 Donna Noble
5 April 10-June 26, 2010 13 11 Amy Pond/Rory Williams
6 April 23-June 4, 2011;

August 27-October 1, 2011



11 Amy Pond/Rory Williams
7a September 1-29, 2012 5 11 Amy Pond/Rory Williams
7b March 30-May 18, 2013 8 11 Clara Oswald
8 August 23-November 8, 2014 12 12 Clara Oswald
9 September 19-December 5, 2015 12 12 Clara Oswald
10 April 15-July 1, 2017 12 12 Bill Potts

Individual episodes. Overall, the resurrected series has been very well-received with a “global” IMDB rating of 8.7 (173,072 raters). Upon first airing, average AI score was a remarkable 84.8, with a very small standard deviation of 2.7 (all but six episodes between 80 and 89). Enthusiasm has not diminished over time: average IMDB score is 8.13 (sd=0.8), with 110 (76%) between 7.0 and 8.9. Two highly-regarded episodes—2007’s “Blink” (9.6) and “The Day of the Doctor” (9.4) each attracted ~15,000 raters (median=4,132; 106 [74%] between 3,000 and 4,999), accounting for the discrepancy between “overall” IMDB ratings.

Table 2: Most- and least-admired Doctor Who episodes (2005-17) when first aired

Title Series-Episode Doctor AI Score
Journey’s End 4-13 10 91
The Stolen Earth 4-12 10 91
Forest of the Dead 4-9 10 89
Doomsday 2-13 10 89
Silence in the Library 4-8 10 89
Asylum of the Daleks 7a-1 11 89
The Parting of the Ways 1-13 9 89
The Big Bang 5-13 11 89
The End of Time: Part Two 10th Doctor Specials 10 89
14 Episodes 3  to 50th Anniversary 10 (8), 11 (6) 88
16 Episodes 1,8-11 12 (14), 9 (2) 82
Twice Upon a Time 11-Christmas 12 81
The Eaters of Light 10-10 12 81
World War III 1-5 9 81
The Long Game 1-7 9 81
The Woman Who Lived 9-6 12 81
Heaven Sent 9-11 12 80
The Unquiet Dead 1-3 9 80
Sleep No More 9-9 12 78
Rose 1-1 9 76
Love & Monsters 2-10 10 76
The End of the World 1-2 9 76

According to Table 2, British audiences did not immediately warm to Doctor Who’s resurrection (with Christopher Eccleston as the 9th Doctor): the first two new episodes (“Rose,” “The End of the World”)—are tied with the execrable Series 2 episode “Love & Monsters” for lowest AI score; five of the first seven are in the bottom nine. There was also a severe drop-off in the reaction to new episodes with Peter Capaldi’s 12th Doctor: 18 (45%) of his episodes rank in the bottom 27 in AI score.

Meanwhile, four of the five episodes with the highest AI scores came as the 10th Doctor’s song was ending: the two-part Series 4 finale (“The Stolen Earth/Journey’s End) and the two-part “Silence in the Library/Forest of the Dead.” The top nine is rounded out by four other “finale” episodes: “The Parting of the Ways” (9th Doctor’s regeneration), “Doomsday” (Rose Tyler [Billie Piper] trapped in a parallel universe), “The End of Time: Part Two” (10th Doctor’s regeneration) and “The Big Bang” (Series 5 finale), as well as the first episode of Series 7a, “Asylum of the Daleks.”

If AI scores are a fixed (British audience) starting point, then the IMDB ratings (flaws and all) in Table 3 represent evolution in regard for Doctor Who episodes over time, after they have been watched and re-watched, shared with others, and discussed at length.

Table 3: Doctor Who episodes (2005-17) with highest/lowest IMDB ratings

Title Series-Episode Doctor IMDB Rating # User-Raters
Blink 3-10 10 9.8 14,970
Heaven Sent 9-11 12 9.6 7,138
Forest of the Dead 4-9 10 9.5 6,471
Silence in the Library 4-8 10 9.4 6,198
The Day of the Doctor 50th Anniv 10/11 9.4 15,365
Doomsday 2-13 10 9.3 6,099
Vincent and the Doctor 5-10 11 9.3 7,441
The Girl in the Fireplace 2-4 10 9.3 7,637
5 Episodes* 3,4,5,7,10 10 (2), 11 (2), 12 (1) 9.2 2,642-5,746
4 Episodes 1,3,8 9 (2), 10 (1), 12 (1) 7.1 3,990-4,475
Evolution of the Daleks 3-5 10 7.0 4,017
The Idiot’s Lantern 2-7 10 6.9 4,197
Victory of the Daleks 5-3 11 6.9 4,075
The Curse of the Black Spot 6-3 11 6.9 3,957
The Lazarus Experiment 3-6 10 6.7 4,054
Love & Monsters 2-10 10 6.3 5,035
Fear Her 2-11 10 6.2 4,445
In the Forest of the Night 8-10 12 6.2 3.624
Sleep No More 9-9 12 6.1 3,254

      * The Family of Blood (3), Journey’s End (4), The Big Bang (5), The Name of the Doctor (7), World Enough and Time (10),

        † Aliens of London/World War III (1) Daleks in Manhattan (3), Kill the Moon (8)

Twenty-six resurrected Doctor Who episodes have an IMDB rating of 9.0 or higher, topped by “The Day of the Doctor,” Silence in the Library/Forest of the Dead,” the penultimate Series 9 episode “Heaven Sent” and, of course, “Blink.” The extremely high number of “Blink” raters would seem to confirm this is the episode most often used by Doctor Who fans to introduce the show to non-fans. Somewhat less often used this way (ranked 3rd and 4th in raters) are the bittersweet episodes “The Girl in the Fireplace” (Series 2) and “Vincent and the Doctor” (Series 5). The heartbreaking “Doomsday” rounds out the top eight. My personal favorite episode, “A Good Man Goes to War” (Series 6), is tied for 14th with a 9.1 IMDB rating.

Bringing up the rear are nine episodes with IMDB ratings between 6.1 and 7.0, three from Series 2 alone: “The Idiot’s Lantern,” “Love and Monsters” and “Fear Her.“ This remarkably uneven series featured these three episodes AND “Army of Ghosts (8.5)/Doomsday,” “Girl in the Fireplace” and “The Impossible Planet/The Satan Pit” (8.8, 8.9); Series 3 episodes “Daleks in Manhattan/Evolution of the Daleks” and “The Lazarus Experiment” are similarly poorly-regarded. Rounding out this list are two 11th Doctor episodes (“Victory of the Daleks,” “The Curse of the Black Spot”) and two 12th Doctor episodes (“In the Forest of the Night,” “Sleep No More”).

These three rankings clearly overlap: “Doomsday,” “Silence in the Library/Forest of the Dead,” “The Stolen Earth/Journey’s End,” “The End of Time: Part Two,” “The Pandorica Opens/The Big Bang,” “A Good Man Goes to War” and “The Day of the Doctor” remain among the most admired and oft-rated episodes, while “Sleep No More” and “Love and Monsters” are still best forgotten. On the other hand, an episode like “Heaven Sent,” which was relatively poorly received when it first aired in November 2015 (AI score=80), is now the 2nd-highest rated episode on IMDB!

A correlation coefficient (r) measures how well too measures “agree” in a linear way. R ranges between -1.00 and 1.00; if r is negative, then as one measure increases, the other decreases, and if r is positive, as one measure increases, the other measure increases. When r=0.00, the association is completely random.

The correlation between AI score and IMDB rating is a solid 0.44, while that between IMDB rating and number of raters is an even-better 0.48. These associations are seen more clearly in Figures 1 and 2 below. The correlation between AI score and number of user-raters was a more modest, though still positive, 0.24 (data not shown).

Figure 1: AI Score vs. IMDB Rating, Doctor Who episodes, 2005-17 (n=144)

Doctor Who Figure 1

Figure 2: IMDB Rating vs. # Raters, Doctor Who episodes, 2005-17 (n=144)

Doctor Who Figure 2

Evolution of regard. Comparing each episode’s AI scores and IMDB ratings will show which episode’s appeal has increased over time, and which have declined. To do this, I converted each value to its z-score (number of SD above/below average—this allows valid comparisons between values with different scales); every z-score has average=0 and SD=1. For example, “A Good Man Goes to War has an IMDB rating of 9.1. Subtracting the average of 8.1 from 9.1, then dividing by the SD of 0.8 yields a z-score of 1.2, meaning this IMDB rating is 1.2 SD more highly regarded than average.

Figure 3: AI Score vs. IMDB Rating (z-scores), Doctor Who episodes, 2005-17 (n=144)

Doctor Who Figuere 3

More than half (60%) of resurrected episodes are still either better regarded than average (both z-scores>0, n=47) or less well regarded than average (both z-scores<0, n=39). Once again, “Blink” and “The Stolen Earth/Journey’s End” were, and remain, highly regarded, while “Love and Monsters” and “Sleep No More” were, and remain, episodes best to avoid.

Thirty-five episodes (24%) went from above average to below average in regard (lower right quadrant of Figure 3), most notably the Series 3 episodes “Daleks in Manhattan” and “The Lazarus Experiment.” The former declined 2.1 SD from a respectable AI score of 87 to a well-below-average IMDB rating of 7.1, while the latter dropped 2.3 SD (85 to 6.7). The only episode to drop as many as 2.0 SD is “The Curse of the Black Spot” (86 to 6.9). Other episodes to decline at least 1.5 SD to become less well-regarded than average are: “Planet of the Dead,” “The Poison Sky,” “The Vampires of Venice,” “Night Terrors,” “Partners in Crime” and “The Doctor’s Daughter.” These disparate episodes are split between the 10th (6) and 11th Doctors (3), though nothing else obviously links them. I quite like “Partners” and “Daughter,” the latter especially because it is how Tennant met wife Georgia Moffatt (the titular “daughter”), who is the daughter of Peter Davison, the 5th Doctor.

Finally, 23 episodes (16%) went from below average to above average in regard (upper left quadrant of Figure 3), most notably “Heaven Sent,” which increased an astonishing 3.7 SD (80 to 9.6) in less than three years; this episode—the Groundhog Day of Doctor Who—rewards repeat viewing. The only other episode to increase at least 2.0 SD is “Listen” (82 to 9.0), one of the 12th Doctor’s earliest and most personal adventures. In fact, five of the seven other episodes to increase at least 1.5 SD to become more well-regarded than average—“Hell Bent,” “The Doctor Falls,” “The Husbands of River Song,” “Extremis” and “Twice Upon a Time”—feature the 12th Doctor. Perhaps his imminent departure from the series prompted this positive reevaluation; “The Empty Child” and “The Girl in the Fireplace” round out the list.

Series: As seen in Table 1, there have actually been 11 resurrected Doctor Who Series, as Series 7 was split into two halves: one with companions Amy Pond (Karen Gillan) and Rory Williams (Arthur Darvill), and one with companion Clara Oswald (Jenna Coleman). While Series 6 featured a nearly three-month gap between the first seven and the final six episodes, I consider it a single Series because it the same companions and a unifying story arc.

Further complicating the demarcation of individual Series’ are the 13 Christmas episodes, three 10th Doctor specials and the 50th anniversary special. It is not clear into which, if any, Series these episodes should be placed.

Table 4: AI Scores and IMDB Ratings, Doctor Who Christmas and Special Episodes (2005-17)

Title Date Doctor AI Score IMDB Rating
Christmas Specials
The Christmas Invasion 2005 10 84 8.2
The Runaway Bride 2006 10 84 7.6
Voyage of the Damned 2007 10 85 7.7
The Next Doctor 2008 10 86 7.6
The End of Time: Part One 2009 10 87 8.2
A Christmas Carol 2010 11 83 8.6
The Doctor, The Widow and the Wardrobe 2011 11 84 7.4
The Snowmen 2012 11 87 8.5
The Time of the Doctor 2013 11 83 8.5
Last Christmas 2014 12 82 8.4
The Husbands of River Song 2015 12 82 8.6
The Return of Doctor Mysterio 2016 12 82 7.5
Twice Upon a Time 2017 12 81 8.3

10th Doctor Specials (after Series 4, excluding Christmas)

Planet of the Dead April 11, 2009 10 88 7.6
The Waters of Mars November 15, 2009 10 88 8.7
The End of Time: Part Two January 1, 2010 10 89 8.9

50th Anniversary Special

The Day of the Doctor November 23, 2013 War, 10, 11 88 9.4

For simplicity, I assessed individual Series’ using only the 128 episodes listed in Table 1; the AI scores, IMDB ratings and number of raters for the 16 non-Series episodes are listed in Table 4.

Figure 4: Average AI Scores and IMDB Ratings, Doctor Who Series’ (2005-17)

Doctor Who Figure 4

Series 1 started slowly (Figure 4; AI scores are divided by 10 for an apples-to-apples comparison), although four of the final five episodes rank among the most well-regarded now (“The Empty Child/The Doctor Dances,” “Bad Wolf/The Parting of the Ways,” average IMDB score=9.0).

While Series 2 is now slightly less well-regarded than Series 1, and average IMDB rating for Series 3 drops to 8.03 without “Blink,” Series’ generally became better-regarded through Series 4. This latter Series is the best-regarded of the resurrected Doctor Who, both when first aired (average AI score=88.1) and now (average IMDB rating=8.46). It started slowly: while “Partners in Crime” through “The Unicorn and the Wasp” (n=7) have a solid AI score average of 87.3, their average IMDB rating is only 7.84. Starting with the brilliant “Silence in the Library/Forest of the Dead,” however, the six episodes through “Journey’s End” have an astonishingly-high average AI score (89.0) and IMDB rating (9.18)! Outside of the three-episode sequence “The Name…” (88, 9.2), “The Day…” (88, 9.4) and “The Time of the Doctor” (83, 8.5), this is the pinnacle of the resurrected Doctor Who, rivaled only by the conclusion to Series 9.

Following the 10th Doctor’s regeneration, however, Series’ 5 and 6 dropped back to Series 3 levels. The latter Series had two distinct parts: the seven-episode sequence of The Impossible Astronaut through A Good Man Goes to War have solid average AI score (86.7) and IMDB rating (8.26), which drop to 85.7 and 8.10, respectively, for the final six episodes (Let’s Kill Hitler through The Wedding of River Song).

Starting in Series 7a, these measures diverge, with average AI score jumping to 87.2 and average IMDB rating dropping to 8.10; the Series started (Asylum of the Daleks, 89, 8.7) and ended (The Angels Take Manhattan, 88, 9.0) well, though it faltered in between (n=3, 86.3, 7.60). The advent of companion Clara Oswald in Series 7b appeared to spike a further decline in regard, which only deepened when she teamed with the 12th Doctor in Series’ 8 and 9, excepting the average IMDB rating of 9.03 for the three-part Series finale (“Face the Raven/Heaven Sent/Hell Bent”). Finally, Series 10, with the first openly lesbian companion (Bill Potts [Pearl Mackie]), signaled a return to Series-8-level regard.

By contrast, Christmas episodes were less admired at initial airing (average AI score=84.1 vs 85.2 for all other episodes) and now (average IMDB rating=8.05 vs. 8.15 for all other episodes). The other four Specials, however, were—and, excepting Planet of the Dead, are—better-regarded.

Figure 5: Average AI Scores and IMDB Ratings, Doctor Who Doctors (2005-17)

Doctor Who Figure 5.jpg

Doctors. Figure 5 displays average values for all 9th (n=13), 10th (n=47), 11th (n=44) and 12th Doctor (n=40) episodes; excluding Christmas episodes and Specials made no appreciable difference.

While websites like WatchMojo.com suggest David Tennant’s 10th Doctor is the best-regarded Doctor ever (rivaling Tom Baker’s 4th Doctor), this is not necessarily borne out by the data. There is a clear demarcation between the 10th and 11th Doctors, on one hand, and the 9th and 12th Doctors on the other. And while the 10th Doctor edges his next incarnation on both average AI score (86.3 to 86.0) and IMDB rating (8.19 to 8.15), the values are not materially different.

Summary. The Doctor Who resurrection did not find its footing until late in Series 1. The 10th and 11th Doctors were held in modestly higher regard than the 9th and 12th Doctors, even if the ends of Series 1 and 9 are very highly-regarded now. The pinnacle of the revived series is the latter half of Series 4, although the most highly-rated episode currently is “Blink” (Series 3), followed by “Heaven Sent” (Series 9) and “The Day of the Doctor (50th anniversary special). “Blink” and “Day” also have received the most IMDB user-ratings by far (~15,000 each). By contrast, it is best to avoid the Series 3 episode “Love and Monsters” and the Series 9 episode “Sleep No More.” While many 10th Doctor episodes have lost stature over time, a similar number of 12th Doctor episodes have done the opposite. Finally, average AI scores and IMDB ratings of 84.8 and 8.13, respectively, are remarkably high, demonstrating just how well-received the Doctor Who revival has been.

For those who are interested, here is a PDF of the data I used in these analyses.

Doctor Who Episode data, 2005-17

Until next time…

[1] The “classic” series aired from November 1963 to December 1989, with only one 1996 television movie—intended to be an American series pilot—before its triumphant return in 2005.