The Simple Reason Sanders Is Winning

February 13, 2016
By

(This article was first published on Econometrics by Simulation, and kindly contributed to R-bloggers)

Sanders has way more backers across the United States (with the possible exception of the South).

Hillary Clinton might be doing well at the polls. However, the shocking fact of polling is that only 8-9% of those asked to participate in polls combined with most polls given to landline owners, the populations being polled do not currently represent of the voting population.

The results of these two factors is what we saw in the Iowa and New Hampshire primaries. That is, even the best estimates were off by a significant margin. As a result, of the growing inability to execute effective polls, we must look to other sources of data. Some have looked at search results, twitter posts, facebook posts, etc. These, posts sources of information seem useful though they are difficult to interpret.

A much better indicator of campaign health, I would suggest, is the ability of a candidate to inspire a wide and diverse base of supporters. From my last post, Analysis: Clinton backed by Big Money: Sanders by Small, it is clear from the data filed with the Federal Election Commission that Sanders has a massive number of small supporters relative Clinton’s relatively small number of large supporters.

The implications of this information are initially unclear. Obviously, any candidate would want more supporters. However, distribution of supporters is important. Perhaps all of Sanders’ supporters are in the North East around Vermont and New Hampshire and thus his message is not being picked up by the rest of the country.

Before jumping into the maps let me just first warn that due to the immensity of small contributions to the Sanders campaign, we do not have information on 74% of contributor information in contrast to that of the Clinton campaign in which we are only missing 14% of contributor data.

In the following maps I am counting how many contributors have contributed to each campaign in each county (the next unit smaller than a state, much like a municipality or district in other countries) of the contiguous United States (apologies Alaska, Hawaii, and our protectorates). A county is ranked from 0 to 1 with 0 being all of those who contributed to a campaign contributed to the Clinton campaign and a 1 being if all of those who contributed to a campaign contributed to the Sanders campaign. Any numbers in between indicate proportion of contributions to the sanders campaign from total number of contributions. Counties without recorded contributions are left out.

In April, very few people knew who Bernie Sanders is. Hillary Clinton however was well known and had people across the country contributing to her. From the map we can see that 82% of counties who had contributors, had the majority of contributors to Hillary.

As early as May 2015, we can see that Sanders is rapidly closing the contributor gap, knocking the number of countries in which Clinton leads from 82% to 62%.

In June, more of the same; Sanders gaining a significant foothold in California and New England.

We can see that even as Sanders is closing in on Hillary’s lead, more of the counties in the US start participating in the process.

By as early as August, we can see that the average number of contributors across counties only has a 6 point gap between Clinton and Sanders.

 And into September, Sanders has taken the lead in contributing counties across the country.

In September Sanders does not gain ground but Clinton also does not lose ground.

But going into November, whatever gains Clinton had made become lost as an increasingly larger portion of the counties start contributing.

By the end of 2015, even with 74% of Bernie’s contributions not being recorded compared with only 14% of Hillary’s, Bernie has people committed enough to contribute to his campaign from across the US that 67% of counties favoring him relative to 31% that favor Hillary.

So what? Does this really matter?

Given that for every one Bernie supporters showing up in the data we know, there are approximately three contributors not showing up in the data, this is a pretty huge margin of supporters willing to give up their personal resources in order to support the Sanders presidential bid.

Yet, even these numbers are only from the end of December. January was the biggest month on record so far with Bernie Sanders for the first time out-raising Hillary. Once those contributions are reported to the FEC, I am certain a much bigger chunk of the map will be blue.

Despite Bernie mobilizing contributors from all around the country, you still may be unconvinced of Bernie’s significant and otherwise difficult to observe edge over Hillary.

If so, scroll through these maps one more time and get a feel for the growing numbers and diversity of supporter rallying in the country. The momentum is with Bernie Sanders. Unless something dramatic and unexpected happens, Sanders is going to continue to dominate the primaries.

Related Posts:
Analysis: Clinton backed by Big Money: Sanders by Small
As First Lady, Popularity of Babies Named “Hillary” Dropped by an Unprecedented 90%
Hillary Clinton’s Biggest 2016 Rival: Herself
Cause of Death: Melanin | Evaluating Death-by-Police Data
Obama 2008 received 3x more media coverage than Sanders 2016
The Unreported War On America’s Poor
What it means to be a US Veteran Today

To leave a comment for the author, please follow the link and comment on their blog: Econometrics by Simulation.

R-bloggers.com offers daily e-mail updates about R news and tutorials on topics such as: Data science, Big Data, R jobs, visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...



If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook...

Comments are closed.

Sponsors

Mango solutions



RStudio homepage



Zero Inflated Models and Generalized Linear Mixed Models with R

Quantide: statistical consulting and training



http://www.eoda.de







ODSC

ODSC

CRC R books series





Six Sigma Online Training





Contact us if you wish to help support R-bloggers, and place your banner here.

Never miss an update!
Subscribe to R-bloggers to receive
e-mails with the latest R posts.
(You will not see this message again.)

Click here to close (This popup will not appear again)