Question

A pollster surveys people at a boxing match, asking them if they had even struck their spouse. Of the 32 people surveyed, 30 said no and the other 2 did not respond. What type of bias is in this sample?

Answer 1

Bias in Survey Sampling: In survey sampling, bias refers to the tendency of a sample statistic to systematically over- or under-estimate a population parameter. Here, p is the population parameter ; where, p=proportion of not striking spouse (NO). AND, (1-p) be the proportion of striking the spouse.

sample proportion p=30/32

Bias Due to Measurement Error:A poor measurement process lead to bias that includes the environment in which the survey is conducted, the way that questions are asked, and the state of the survey respondent. Response bias is one of them.

Due to Social desirability, most people like to present themselves in a favorable light. They won't admit that they have bad attitude, or are fraud themselves. Instead, their responses may be biased toward what they believe is socially desirable. Here, "struck their spouse" is not socially desirable.So even if they may be striking their spouses, they do not accept it; they may answer "NO (not striking)". This results in Bias called Response bias due to social desirability.

Also, in this example, 2 people have not responded. Thus, there also exists small non-response bias.