HOT OFF THE PRESS: British Inquiry into Inaccurate 2015 Election Polling

Dewey_Truman_1948 2015 British Election polling blunder

Most Americans are familiar with the photo of President Harry Truman, in triumph after the 1948 presidential election, holding up the Chicago Daily Tribune with the headline declaring his opponent NY Gov. Thomas Dewey was predicted to win.  The pollsters and the news reporter, in the early years of surveys, screwed up.

Truman pulled in 303 electoral votes and 49.6% of votes cast, Dewey received 189 and 45.1% and Strom Thurmond collected 39 and 2.4%. The pollsters used a poor sampling methodology, and the industry made adjustments going forward.

And, it happened again!  In the May 7th, 2015 British general election, late public polls indicated the Conservative and Labour parties were in a close race, 34% each.  Nope.  The Conservatives collected 38% and Labour 31%.

So, what happened?  The British Polling Council (BPC) and the Market Research Society just released their 115-page “Report of the Inquiry into the 2015 British general election opinion polls.” Click here for the report.

The BPC is an association of polling organizations that publish polls. The self-described objectives are to ensure standards of disclosure that provide consumers of survey results that enter the public domain with an adequate basis for judging the reliability and validity of the results.

So, before I jump into the findings, here is my perspective (things I have said for years) as to why this matters:

  1. The news media places far too much significance on the horserace early in the campaign season. It is a lazy way for the news media to get headlines.  The result: Donald Trump touting horserace polls and voters – who do not have time to delve into the details (isn’t that a role of news reporters?) – following the supposed front runner.

Campaign professionals, including veteran news reporters and editors, know that in the early phases of a campaign, the guts of the polls are more important than the horserace.  These are the private polls that are not shared with the public.  What is the voter sentiment? What are they seeking in their next leader?  These are the questions that are supposed to identify trends such as who is angry in the electorate, how many of them, reasons why they are angry and what will appeal to them.   Without the deeper analysis, the Republican Party and the media were blind-sided by the bluster of Donald Trump.  And, the result is an American political system in upheaval and hand-wringing among domestic voters and international viewers.

  1. However, late in a close campaign, the horserace does matter. In the final weeks of an election, the campaigns should be well in tune with the electorate and, based on the horserace, know how to deploy their best messages and resources for Election Day.  These final public polls – supposedly the result of our modern knowledge economy — are critical in providing stability in any changeover in national governance.
  1. But, what if the horserace polls are wrong? That is a problem.  If the polls do not match the results, it raises questions as to the validity of the election results.  There are known problems in polling, often relating to the increased costs in reaching random samples of voters.  Many voters are in cell-phone only homes; reaching these voters is expensive.  People with landlines are also answering surveys at increasingly lower rates, which also raises the cost of conducting a voter survey.  Are there other reasons, beyond cost, that are driving these problems?  And, for some additional context, there is also the challenge of polls not being able to track voters deciding late in an election (this can be done, but not something I have seen public polling organizations do – anyone want to hire me to do this?).
  1. So, this inquiry matters.   The public election horserace polls provide stability to the electorate and world economies.  And, the reputation of polling has similar implications among the corporations and organizations that rely on surveys.  As voters and users of survey research, we need confidence in our survey systems.  So, this inquiry will provide important lessons of the source of the problem, and, hopefully, guidance for resolving the problem.

The British Inquiry into Inaccurate 2015 Election Polling:

I am sure colleagues smarter than me will weigh in with more insights.  But, here is my interpretation of the findings of the BPC:

Reliable public election polling is expensive.  The pollsters in the UK took shortcuts that do not work if you are looking to accurately predict a national election.  If you want to poll for the public for a national election and focus on the horserace, spend your budget on less but more accurate polling.  The problems were avoidable.

If you are interested in the details, here are some major details I gleaned from the report:

  1. The BPC could not find a singular problem other than the polls consistently had too many Labour voters and too few Conservatives. They even worked through a process of elimination, going through eight other possible sources of consistent error (i.e. intentional misreporting, major changes in late-deciding voters, voters misleading in their answers, unexpected changes in voter turnout, inaccuracy in expected voter models, etc.).  They found no errors to account for such a high and consistent disparity.
  1. THE ULTIMATE PROBLEM IS COST. The BPC provides criticism of both online surveys and telephone surveys that were conducted prior to the UK election for cutting corners due to cost in ways that changed the composition of survey respondents.
  1. ONLINE SAMPLES ARE POOR FOR ACCURATELY MEASURING GENERAL POPULATION ATTITUDES, TO THE POINT WHERE FIXING THE PROBLEM ADDS SO MUCH COST THEY MIGHT AS WELL CONDUCT A TELEPHONE SURVEY. Many of the polls examined by the BPC were conducted online with opt-in panels—people who agree to be included in online polling samples.  It is significantly less expensive than a random digit dialing (RDD) telephone survey.

There have been internal arguments in the opinion research world for decades about whether the opt-in panels can accurately mimic the accuracy of RDD.  From the mid-1960s to mid-2000s, RDD was the gold standard for most closely achieving true random sampling of a first-world voter population (the new gold standard includes manually dialing cell phone numbers).  Along with the randomness of being picked for a survey in RDD (as opposed to opt-in panels), the use of a flesh-and-blood interviewer is considered essential to minimizing the inherent sampling and other errors in a survey. A professional interviewer is trained to get people to respond who might initially decline to participate.

There is no magical statistical formula for filling the differences in opinions between people who readily agree to take a poll and people who need some cajoling to take a poll.  Some firms conducting studies online have tried different statistical techniques to patch together a proxy for a random sample.  Some claim their models are adequate, but, to me, the failure in the UK demonstrates otherwise. While these methods are decent for testing experimental hypotheses in surveys, I believe they are flawed when trying to provide the general public a reliable estimation of election preferences.

  1. TELEPHONE SAMPLES CAN ALSO HAVE PROBLEMS BUT ARE MORE EASILY FIXED. It is well-documented that RDD telephone surveys of voters have become increasingly expensive because they get fewer responses from voters with landline telephones (people are less willing to respond and they have more ways to spend their evenings than answering telephone calls) and they have to hand-dial cell phone numbers.  The BPC report calls on future telephone surveys to increase the hours in which they call, require more callbacks and calls to people who do not initially respond, increase the percentage of cell-phone only users, and to spend more days completing their surveys.  These are all tried-and-true elements of a well-conducted survey, and it is a shame that pollsters sharing important civic information have cut costs to the point of damaging public trust.

Do we have the same problem in the United States in our election polls?  The opinion research industry went through a similar self-examination after the 2008 Presidential election and reached similar results.  The good news is public polls are mainly conducted by telephone and do not have a consistent error. The bad news for news outlets is they are very expensive.  As I have mentioned before, I hope this forces more reporters to examine polls more deeply than the horserace so we better understand the good and the bad in the minds of voters.

I have not seen this addressed in the BPC report, but why were major British newspapers reporting on online polls — known to have flaws — for their national elections? 

On some final notes, it is likely polling budgets for news agencies have been overstretched with the long drawn out primaries in both parties; we will see fewer public polls through the conventions, and possibly in the fall election season.  As I have shared before, Gallup announced they made a business decision to no longer conduct, at their own expense, public election polls focused on the horserace.

QUALITATIVE RESEARCH 101, Part I: Introduction

QUALITATIVE RESEARCH 101, Part I: Introduction

“In a world moving increasingly to data science, it feels as though qualitative research has been relegated to the bottom of our professional toolbox.”

My colleagues and friends typically think of me as a “quant” guy who keeps my head buried in numbers.  It is true, I love surveys and data.  However, I have a big heart and a lot of love for qualitative research, too!

I define qualitative research as direct interactions between a researcher and the audience.  These are typically focus groups and in-depth one-on-one interviews.

In a world moving increasingly to data science, it feels as though qualitative research has been relegated to the bottom of our professional toolbox.  “Where did I put that focus group guide? It is in there…  somewhere.”

So, I am going to reach into my own toolbox and share a series of thoughts and professional insights into qualitative research.

Great qualitative research requires developing and using a set of skills that many data scientists are hesitant to pursue: managing conversations with flesh-and-blood people.  This requires an additional set of skills, training, and experience that many specialized data-oriented researchers have ignored or have not had opportunities to explore.  I can point to myself as a former member of this crowd – I worked for an incredibly bright and talented firm that conducted a successful U.S. presidential campaign without holding a single focus group.  However, I was also fortunate to later work with an amazing firm with a reputation for conducting top-notch qualitative research.  Each of the two forms of research – quantitative and qualitative – has their role in understanding opinions and how to influence them.

Many people I meet are also not aware of another secret: we have new technological tools in qualitative research for delivering cutting-edge analysis.

As researchers looking for insights, we first need a signal that “something is off,” and there is something new to explain.  For example, in the burgeoning field of behavioral economics, scholars such as Daniel Ariely, author of books such as Irrational Behavior, grab our attention by pointing out the quirks of human nature.  Why do people act against their self-interest?

I have had tremendous success for clients and personal satisfaction by talking to real people.  These interactions can generate new ideas and be a source for explaining unexpected phenomenon.

The process of finding answers to these questions is one of many uses of qualitative research.  It is a key tool when researchers need to “know what we do not know.”

Since this is an introduction, here is a preview of some areas I will cover:

  • Some guiding principles of qualitative research.
  • Some anecdotes and case studies.
  • Reasons saying you conducted “your own focus groups” deeply concerns me.
  • Classic and new ways to analyze qualitative research.
  • The real-world solution for many organizations: combine qualitative and quantitative research.
  • Ways I can help you conduct qualitative research, including with a tight budget.

As always, contact me directly at jstarr@starr-research.com to discuss opinion research and solving your organization’s challenges.

Reading Between the Lines at The Times

To start off 2016, The New York Times snuck in something new: a general population survey conducted mostly online.  Until then, the newspaper only conducted polls with live interviewers calling landline and mobile telephone numbers.

Credit: Joshua Bright for The New York Times
Credit: Joshua Bright for The New York Times

John Broder, their editor of News Surveys, provided details about this change in a special Times Insider column.  Methodology junkies will enjoy it.  Click here to go to the article.

Was this a boring story for most readers? Probably.

But, here are some interesting things to consider:

Is this, in part, a trial-run by The NY Times to improve the reliability of the political horserace question, in time for the 2016 campaign?  American readers, and the journalists who rely on them, are obsessed with the horserace – who is “winning” or “losing” and by how much?  Donald Trump did not create this obsession, but in some fashion his candidacy reflects the American fascination with these questions.

Unfortunately, it has been well-documented in recent years the reliability of general population or voter surveys have deteriorated – at least, by the admission of The New York Times – due to, among other things, the increase in cell-phone only households.  The resulting increase in costs to conduct reliable polls has been staggering, and certainly taken a toll on newsroom budgets.  Side note: Would it also be fair to say that The New York Times just announced that their general public/voter polling is flawed?

We are lost in the political desert without reliable polls.  News organizations are desperate to find a solution to return the credibility to these polls.  They need to feed the public’s interest in the horserace.  Likewise, journalists need the polls to help them write their political stories and analyses.

So, with this one poll and accompanying article, The New York Times might be preparing the general public for a new methodology for their political polling.  I don’t think they can have it both ways for too long – some polling with an online component, and some without.  And, from my perspective, the sooner a change is made to make general public surveys with an online component the gold standard, the sooner survey costs can come back to earth.

Of course, only The New York Times knows in their testing whether this methodology is ready for their front pages.  But, why else would they publish the results and article?

If this methodology is sufficiently reliable, we will see the return of the horserace question across the front pages.  Phew.

 Will there be an impact for communication professionals?  Will standards change to publish your polling?  News editors across the country are asked daily to publish polls conducted by a 3rd party.  No matter how interesting the results, the first question is whether the survey was methodologically sound.  Journalists, often weak in math and statistics, have been trained over the years to sniff out bad polling.

Will The New York Times create a new standard for polling, whether good or bad, and will news editors across the country follow their lead?

Perhaps John Broder’s article will have broader implications than just be a dry review of survey methodologies.