2020 South Carolina Primary: How did my final polling averages fare?

Given the extremely volatile polling for the 2020 Democratic presidential nomination now that voting has commenced, I will not provide global monthly updates for the next few months. Instead, I will focus on the first handful of primaries and caucuses: Iowa on February 3, New Hampshire on February 11, Nevada on February 22, South Carolina on February 20, the 14 Super Tuesday contests on March 3, and so forth.

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[1] 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 March 1, 2020.

And then there were six—though it is somewhat unclear whether United States House of Representatives Member (“Representative”) from Hawaii Tulsi Gabbard is still actively campaigning. Within 24 hours of the announcement of results from the 2020 South Carolina Democratic Presidential Primary, two candidates ended their bid to be the 2020 Democratic nominee for president: billionaire activist Tom Steyer and former South Bend, Indiana Mayor Pete Buttigieg. Both men ran optimistic, forward-looking and generally positive races, and they are to be commended for ending their campaigns with class and dignity.

I also praise the South Carolina Democratic Party for disseminating results from >99% of precincts within five hours of polls closing in their state at 7 pm EST on February 29, 2020. Earlier that day, I published my final 2020 South Carolina Democratic Primary WAPA (weighted-adjusted polling average) for the eight then-declared Democratic presidential candidates, calculated seven different ways (Tables 1 and 2):

• 53 since January 1, 2019
• 41 since the 1^st Democratic debate on June 26, 2019
• 22 since the 5^th Democratic debate on November 19, 2019
• 18 since the 7^th Democratic debate on January 14, 2020
• 15 since the Iowa Caucuses on February 3, 2020
  • 7 between February 12 and February 22
  • 8 beginning February 23

Table 1: Final South Carolina WAPA for declared 2020 Democratic presidential nomination candidates

Candidate	All Polls	Since 1st Debate	Since 5th Debate	Since 7th Debate	Since Iowa
Biden	33.2	33.0	32.4	32.2	32.3
Sanders	18.6	18.7	20.3	20.7	20.7
Steyer	11.4	11.7	13.4	13.5	13.5
Warren	9.1	9.1	8.4	8.1	8.1
Buttigieg	7.7	7.7	8.5	8.7	8.8
Klobuchar	3.9	4.0	4.6	4.8	4.9
Gabbard	2.1	2.2	2.5	2.6	2.4
Bloomberg	0.3	0.3	0.3	0.2	0.2
DK/Other	13.7	13.3	9.6	9.1	9.1

Table 2: South Carolina WAPA for declared 2020 Democratic presidential nomination candidates following the Iowa Democratic Caucuses

Candidate	Before Nevada Caucuses	After Nevada Caucuses	Change
Biden	26.0	36.5	+10.5
Sanders	21.2	20.6	-0.6
Steyer	15.7	12.9	-2.8
Warren	8.7	7.7	-1.0
Buttigieg	9.5	8.3	-1.2
Klobuchar	5.7	4.0	-1.8
Gabbard	2.1	2.2	+0.1
Bloomberg	0.7	0.0	-0.7
DK/Other	10.5	7.8	-2.7

Based solely on these numbers, one could reasonably draw the following conclusions:

• Former Vice President Joe Biden was rapidly rising in the polls.
• No other candidate was moving in the polls more than a few points one way or the other.

Comparing WAPA to results. Table 3 lists the results of the 2020 South Carolina Democratic Primary as of 7:30 pm EST on March 1, 2020:

Table 3: Percentage of vote received in 2020 New Hampshire Democratic Primary

Candidate	% Vote
Biden	48.4
Sanders	19.9
Steyer	11.3
Buttigieg	8.2
Warren	7.1
Klobuchar	3.2
Gabbard	1.3
Bloomberg (not on ballot)	0.0
All others	0.6

Table 4 lists the arithmetic differences between each candidate’s final South Carolina Primary WAPA and each of the three reported measures; positive values indicate better performance in the primary than in the polls.

Table 4: Arithmetic difference between Vote % and WAPA, 2020 New Hampshire Democratic Primary

Candidate	All Polls	Since 1st Debate	Since 5th Debate	Since 7th Debate	Since  Iowa	Mean Difference
Biden	15.2	15.4	16.0	16.2	16.1	15.8
Sanders	1.3	1.2	-0.4	-0.8	-0.8	0.1
Steyer	-0.1	-0.4	-2.1	-2.2	-2.2	-1.4
Warren	-0.9	-0.9	-0.2	0.1	0.1	-0.4
Buttigieg	-0.6	-0.6	-1.4	-1.6	-1.7	-1.2
Klobuchar	-0.7	-0.8	-1.4	-1.6	-1.7	-1.2
Gabbard	-0.8	-0.9	-1.2	-1.3	-1.1	-1.1
Bloomberg	-0.3	-0.3	-0.3	-0.2	-0.2	-0.3

With one glaring exception, these polling averages were remarkably accurate; only one candidate did not finish within 1.4 percentage points (“points”) in either direction of her/his final WAPA. But this was a substantial exception: Biden outperformed his final WAPA by an average of 15.8 points. Even then, however, the average “miss”—regardless of direction—was only 2.7 points. And limiting the comparison only to the eight polls released in the preceding week, Biden still outperformed by 11.9 points, with only Steyer missing by >1.0 point (-1.6).

Bottom line. To evaluate these comparisons globally, I calculated two difference measures for each of the five WAPA, excluding “DK/Other” (Table 5):

1. Means of the absolute value of each candidate’s value in Table 4
2. Sums of the squared differences (“SSE”) between each WAPA value and final results

Table 5: Global differences between WAPA and results, 2020 New Hampshire Democratic Primary

Polling period	Mean AV Difference	SSE
All Polls	2.5	235.1
Since 1st Debate only	2.6	241.5
Since 5th Debate only	2.9	266.1
Since 7th Debate only	3.0	274.8
Since Iowa Caucuses	3.0	271.7
Iowa-Nevada	4.4	536.2
Post-Nevada	2.2	147.8
Average	2.7	257.8

The five primary versions of WAPA were very accurate, even with Biden’s large overperformance, missing by between 2.3 and 3.0 points in either direction, on average, and with a fairly low and narrow range of SSE. For the first time, however, it was the older set of polls that was (barely) more accurate.

There is one glaring exception to this pattern, though, that demonstrates how difficult it is to poll voters during a fast-moving presidential nomination process. Polling conducted between the Iowa Caucuses on February 3 and the Nevada Caucuses on February 22 was far less predictive of the final results (though, to be fair, still reasonably accurate) than polling conducted in the week after the Nevada Caucuses; the latter was by far the most predictive of all, even with Biden’s overperformance.

Given the variation in patterns over the first four Democratic presidential nominating contests, I will continue to use this template to assess WAPA.

Now, on to the 16 Super Tuesday contests, with 1,344 pledged delegates at stake, on March 3, 2020!

Until next time…

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