Understanding political opinion polls

By Ronald Musoke

On May 26, the WBS Television Auditorium at Naguru, in Kampala hosted the public to debate the recently released opinion poll done by Research World International (RWI) which was commissioned by Monitor Publications Limited and the Uganda Governance Platform to assess the opinions and attitudes of voting-age Ugandans two years to 2016 general elections. Many in the audience wanted to know how credible the poll should be taken by Ugandans when they had doubts about the methodology.

Others wanted to know whether the 2142 sample was representative enough for a country whose population is estimated at about 36 million people. It did not help matters that the pollsters used the 2002 population census data to determine population distribution across the country.

Other participants like Sheila Kawamara Mishambi, the chairperson of the Uganda Women’s Network also wondered whether some of the questions were well structured to elicit good responses.

Interestingly, not just at the WBS TV event but over the last seven days, Patrick Wakida, the executive director of RWI, maintained that given the lack of available data, and the often urban and elite bias of political commentary and analysis, his firm’s opinion poll was credible enough because it used the most scientific method employed by credible polling firms around the world.

So what makes or breaks opinion polls?

Public opinion polls are everywhere these days, measuring people’s beliefs, attitudes, or expectations on countless political, social, and economic issues.

In the US, the Gallup Poll is widely recognized, although polls have also been devised and implemented by magazines, television networks, and newspapers down the years.

Among the more prominent polls are those sponsored by Time and Newsweek, NBC News/Wall Street Journal, ABC News/Washington Post, CBS News/New York Times, and USA Today/CNN.

A public opinion poll is a method of systematically interrogating a smaller, representatively-selected sample of the public; a sample that is fundamentally an accurate “mirror” of the opinions held by the entire population as a whole.

A poll only represents a “snapshot of opinion” at a particular point in time.

In other words, if a polling organisation like RWI asks a national sample of 2142 Ugandans for whom they will vote in the presidential election of 2016, then the percentage preferences found for each candidate in the sample should reflect, within an acceptable sampling error, how the much larger voting population of 36 million Ugandans will vote.

Is this possible?

In the US, the Gallup Poll has accurately predicted the presidential winner in most election years; ten of the last twelve elections.

However, although opinion polls are far more scientific and therefore very accurate today, they still may run into problems met by earlier pollsters.

According to the US-based cable news network, CNN, prior to the era of modern scientific polling, magazines and newspapers would solicit opinions from their readers through face-to-face straw polls or mail surveys.

But, despite a large number of responses, these techniques were unreliable.

The straw vote stressed quantity of responses over the quality of the sample. In other words, an accurate cross-section of the voting population was unlikely to be achieved.

A case in point was in 1936, when The Literary Digest, a popular magazine of its day, predicted that the Democrat, incumbent President Franklin D. Roosevelt, would lose to his Republican challenger, Alfred Landon.

After more than two million ballots were returned and counted, The Literary Digest stated that Landon was the choice of a clear electoral majority.

But the opposite happened as Roosevelt won in a landslide, capturing 60% of the vote and winning every state except Vermont and Maine.

CNN explains that The Literary Digest had unwittingly received ballots from predominantly wealthier Americans who could afford cars and telephones during a depression year when millions of other Americans were barely able to make ends meet.

So, the sizable number of poor, or even average- income Americans, unable to afford the luxuries of a car or phone, were missing from The Literary Digest’s sample.

It was exactly these Americans who overwhelmingly supported Roosevelt in the 1936 election. So, The Literary Digest’s sample was “biased.” In other words, it did not reflect the entire population, since so many poor people never had a chance to send in ballots.

The poll was therefore inherently flawed and led to a completely wrong prediction. The Literary Digest went out of business not too long after this polling debacle.

Lawrence Bategeka, an economist who has just retired from the Makerere University-based think tank, the Economic Policy Research Centre (EPRC), says opinion polls are credible if the pollster gets correct the method of sampling to make sure that it represents the population.

“This is no mean feat because you need technical abilities,” he told The Independent, adding that, “Unless this is achieved we cannot wholly take opinion polls seriously because of sampling shortcomings.”

According to the American Association for Public Opinion Research’s  best practice guidelines,   the quality of a survey is best judged by “how much attention is given to preventing, measuring and dealing with the many important problems that can arise”, rather than just the size or scope of the polls.

For a poll to be accurate it must be based upon a representative, randomised sample, employ valid or reliable questions, and have polling personnel to carefully communicate with those interviewed.

First, a representative sample is chosen through the process of random selection, which is basically a lottery system whereby every individual in the population (by age, religion, race, living area, etc.) in the nation has an equal mathematical chance of being included in the sample, just as in a lottery every number has the same probability of being selected.

In other words, a properly constructed sample will include all segments of the population. If the national sample is large enough (typically 1500 to 2000 people interviewed) and is truly randomly formed, then those laws of probability state that final opinion results will be satisfactory, usually within a small margin of error-typically no more than plus or minus 3 to 5% in national polls.

Today, public opinion polls have become important tools for democracy in many countries with leaders such as presidential candidates relying on them to find out voters’ attitudes to key issues of the day during campaigns. The media also employs opinion surveys to judge how a campaign is progressing for hopeful public office-seekers or to publicize an important societal issue.

No doubt when polls are conducted properly, they can be very accurate. However, opinion polls have not gone without criticism.

One criticism is the “band-wagon effect,” where published poll results may influence voters to go for the candidate who appears far ahead of his opponent because people want to select the obvious winner.

Other experts also say that citizens may even decide not to vote, arguing that the election is over. In the US, this has happened with exit polls, when voters in the far West hear the early poll returns on the TV networks which may favour a particular presidential candidate. They end up not voting, thereby reducing national turnout.

Poll questions over-simplify issues, frequently asking those interviewed for only “yes” or “no” answers to very complex problems.

Pollsters also have a challenge of satisfying the public on who was interviewed and how credible the science is to determine the popularity of somebody.

RWI maintain poll is accurate

Dr. Patrick Wakida, the executive director of Research World International has been pre-occupied trying to satisfy the consumers of his poll results.

He says the sampling technique is the most popular technique that his team always employs each time they conduct opinion polls in the country. This was the third public opinion poll conducted by the firm since 2012.

With the firm’s results given with a +/-3% margin of error at a 97% confidence level, Wakida insists stakeholders should make use of the opinion poll’s data. “This Poll can be used by both the government to retain power and by the opposition to usurp power while the civil society can use it to effect social change,” he says. He says all polls conducted by his firm have been as accurate as scientific polls can be.