Top 25 Most Evil People of the Millennium

According to a New York Post poll conducted from
September 30 - November 1, 1999 among NYPost.com users

Total number of votes received = 19,184

On-Line Polls Are Out Of Line

from STATS:  Statistical Assessment Service

Politicians seem to live and die by opinion polls. So President Clinton must not have been amused when a Nov. 18 New York Post on-line poll of the 25 most evil people of the century ranked him second only to Adolf Hitler. His wife Hillary, running for a Senate seat in New York, must have been equally displeased by her sixth place finishing. Should the President resign himself to a legacy of infamy? Should the First Lady withdraw from her race in shame?

An even better question is whether the Post should have mentioned the results of such a dubious poll in the first place.

The advantages to conducting polls on-line are obvious. A telephone poll may take several days and cost thousands of dollars, but an on-line poll can be ready overnight and for a fraction of that cost.

On-line polls also regularly capture large numbers of responses, which might seem to make them especially newsworthy. Fox News Channel aired the results of an Internet poll Dec. 2 asking who had won the Republican television debate in New Hampshire. As reported by The Washington Times (Dec. 7), Alan Keyes won the poll “conducted by vote now.com – proving he is the most eloquent of the batch.” The Vote.com poll [vote now.com does not exist] had captured 8,000 responses by the time those results were released on TV. In another instance, an ABC News poll on Internet addiction this spring yielded 17,251 responses – 17 times the sample of a typical telephone poll.

In this case, size doesn’t matter. Internet poll respondents take the initiative to make their views known. Hence, on-line polls capture the opinions of a group that is self-selected and non-random. Therefore, it does not represent the general population. Even worse, respondents can often skew the results by voting repeatedly. Last May, a poll by The Toronto Star on a political debate supposedly was programmed to allow people to vote only once, but hackers generated more than 9,500 votes for one political party from a single computer. Another 9,000 votes for a second party came from one other computer.

There are also significant demographic differences between the respondents of Internet and telephone polls. This is to be expected, because there are social distinctions between those who have the time and inclination to accept a telephone poll from a stranger and those who surf the Internet.

On-line polls are limited to the roughly 40 percent of Americans using the Internet. According to the Pew Research Center, registered voters who go online are relatively well educated and affluent. They are also young, while most studies indicate the over-65 crowd votes more than any other demographic. College graduates are substantially over-represented – 42 percent of those online, compared to 25 percent of all registered voters – as are members of families with incomes of more than $50,000 a year. Political independents often participate in disproportionate numbers.

To explore how such differences affect results, the Pew Research Center conducted two simultaneous polls this spring – one by telephone, the other on-line. The results were vastly different on some key issues. For example, on-line poll participants “pay closer attention to election news,” and were “more supportive of (President) Clinton’s impeachment.”

Despite the problems with Internet polling, Harris Interactive has committed $55 million to on-line polling for upcoming American political elections and referendums. Harris Interactive has tried to improve results of traditional methods by having millions of “cooperative respondents” join a database and inviting selected people to respond to each survey, based on the demographics that they submit. It then will adjust results for demographic discrepancies between the real world and the wired one.

Although they use a more rigorous method than the average Internet poll, the Harris on-line polls still suffer from self-selected samples. As Warren J. Mitofsky argued in a summer issue of Public Perspective, “If you want to survey people who do not have computers or who are not online, you cannot do that online.” No amount of statistical manipulation will change that.

Once computers with Internet access become as common as the telephone, demographic deficiencies will dissipate and techniques of statistical weighting may be workable. Although security problems will never disappear, the ability to tag respondents with unique identifiers is within reach. Some day, a good on-line poll should be able to yield a number of quality responses from a reliable sample that far surpasses any traditional poll.

But that day has yet to arrive. According to Alan J. Rosenblatt of George Mason University, “The numbers suggest that the rate of usage is growing slowly and that it may take a while for the last third of the population to join the ranks of computer users.” As long as the wired population is limited, so are the results of any Internet survey.

While survey companies like the Harris organization struggle to overcome the limitations of Internet polling, frivolous polls like the New York Post’s don’t even recognize this existence.

The New York Times (Nov. 23) discussed the Post’s poll on evil people with the comment, “Some newspapers would have tossed out such results as malicious and patently absurd.” Unfortunately, it is not clear that all readers responded that way. News media use of polling has come a long way towards accuracy from the “Dewey Defeats Truman” headline days, and it would be unfortunate to discard that progress in pursuit of the latest fashion. To prove it to themselves, maybe editors should ask themselves a question: “Do you want opinion polling to be 1) technologically flashy or 2) accurate?”