Section 1.4 Bias in Studies 27 average, studies conducted in this way would overestimate the percentage of Democrats in the population. Studies conducted with methods that tend to overestimate or underestimate the true value are said to be biased. DEFINITION • A study conducted by a procedure that produces the correct result on the average is said to be unbiased. • A study conducted by a procedure that tends to overestimate or underestimate the true value is said to be biased. Objective 2 Identify sources of bias Identifying Sources of Bias In practice, it is important to design studies to have as little bias as possible. Unfortunately, some studies are highly biased, and the conclusions drawn from them are not reliable. Here are some common types of bias. Voluntary response bias Recall that a voluntary response survey is one in which people are invited to log on to a website, send a text message, or call a phone number, in order to express their opinions on an issue. In many cases, the opinions of the people who choose to participate in such surveys do not reflect those of the population as a whole. In particular, people with strong opinions are more likely to participate. In general, voluntary response surveys are highly biased. Self-interest bias Many advertisements contain data that claim to show that the product being advertised is superior to its competitors. Of course, the advertiser will not report any data that tend to show that the product is inferior. Even more seriously, many people are concerned about a trend for companies to pay scientists to conduct studies involving their products. In particular, physicians are sometimes paid by drug companies to test their drugs and to publish the results of these tests in medical journals. People who have an interest in the outcome of an experiment have an incentive to use biased methods. Social acceptability bias People are reluctant to admit to behavior that may reflect negatively on them. This characteristic of human nature affects many surveys. For example, in political polls it is important for the pollster to determine whether the person being interviewed is likely to vote. A good way to determine whether someone is likely to vote in the next election is to find out whether they voted in the last election. It might seem reasonable to ask the following question: “Did you vote in the last presidential election?” The problem with this direct approach is that people are reluctant to answer “No,” because they are concerned that not voting is socially less acceptable than voting. Here is how the Pew Research Center asked the question in a 2010 poll: “In the 2008 presidential election between Barack Obama and John McCain, did things come up that kept you from voting, or did you happen to vote?” People are more likely to answer this version of the question truthfully. Leading question bias Sometimes questions are worded in a way that suggests a particular response. For example, a political group that supports lowering taxes sent out a survey that included the following question: “Do you favor decreasing the heavy tax burden on middle-class families?”
navidi_monk_essential_statistics_1e_ch1_3
To see the actual publication please follow the link above