non-response bias

Examples of non-response bias in the following topics:

• Telephone Surveys

  • As some people do not answer calls from strangers, or may refuse to answer the poll, poll samples are not always representative samples from a population due to what is known as non-response bias.
  • However, if those who do not answer have different opinions, then the results have bias.
  • In terms of election polls, studies suggest that bias effects are small, but each polling firm has its own techniques for adjusting weights to minimize selection bias.
  • Undercoverage is a highly prevalent source of bias.
  • In addition, if the pollsters only conduct calls between 9:00 a.m and 5:00 p.m, Monday through Friday, they are likely to miss a huge portion of the working population—those who may have very different opinions than the non-working population.

• Sampling from a population

  • This introduces bias into a sample.
  • The act of taking a simple random sample helps minimize bias, however, bias can crop up in other ways.
  • Even when people are picked at random, e.g. for surveys, caution must be exercised if the non-response is high.
  • This non-response bias can skew results.
  • Due to the possibility of non-response, surveys studies may only reach a certain group within the population.

• How Well Do Probability Methods Work?

  • Failure to use probability sampling may result in bias or systematic errors in the way the sample represents the population.
  • This is especially true of voluntary response samples--in which the respondents choose themselves if they want to be part of a survey-- and convenience samples--in which individuals easiest to reach are chosen.
  • A third example of bias is called response bias.
  • Careful training of pollsters can greatly reduce response bias.
  • Finally, another source of bias can come in the wording of questions.

• Sampling Bias

  • This section discusses various types of sampling biases including self-selection bias and survivorship bias.
  • Many of the admittedly "non-scientific" polls taken on television or web sites suffer greatly from self-selection bias.
  • A self-selection bias can result when the non-random component occurs after the potential subject has enlisted in the experiment.
  • Survivorship bias occurs when the observations recorded at the end of the investigation are a non-random set of those present at the beginning of the investigation.
  • Therefore, there is a bias toward selecting better-performing funds.

• Chance Error and Bias

  • Chance error and bias are two different forms of error associated with sampling.
  • In statistics, sampling bias is a bias in which a sample is collected in such a way that some members of the intended population are less likely to be included than others.
  • It results in a biased sample, a non-random sample of a population in which all individuals, or instances, were not equally likely to have been selected.
  • Participants' decision to participate may be correlated with traits that affect the study, making the participants a non-representative sample.
  • Exclusion bias, or exclusion of particular groups from the sample.

• Estimation

  • Random errors occur in all data sets and are sometimes known as non-systematic errors.
  • Bias is sometimes known as systematic error.
  • Bias in a data set occurs when a value is consistently under or overestimated.
  • Bias can also arise from forgetting to take into account a correction factor or from instruments that are not properly calibrated.
  • Bias leads to a sample mean that is either lower or higher than the true mean .

• Confounding

  • When there is not a large sample population of non-smokers or non-drinkers in a particular occupation, the risk assessment may be biased towards finding a negative effect on health.
  • Confounding by indication occurs when prognostic factors cause bias, such as biased estimates of treatment effects in medical trials.
  • By preventing the observers from knowing of their membership, there should be no bias from researchers treating the groups differently or from interpreting the outcomes differently.
  • A randomized controlled trial is a method where the study population is divided randomly in order to mitigate the chances of self-selection by participants or bias by the study designers.
  • Break down why confounding variables may lead to bias and spurious relationships and what can be done to avoid these phenomenons.

• Inferential Statistics

  • Instead, we query a relatively small number of Americans, and draw inferences about the entire country from their responses.
  • That might affect the outcome, contributing to the non-representative nature of the sample (if the school is co-ed).
  • There are other reasons why choosing just the Z's may bias the sample.
  • In experimental research of this kind, failure to assign subjects randomly to groups is generally more serious than having a non-random sample.
  • A non-random sample (the latter error) simply restricts the generalizability of the results.

• A Closer Look at the Gallup Poll

  • Gallup still has to deal with the effects of nonresponse bias, because people may not answer their cell phones.
  • Because of this selection bias, the characteristics of those who agree to be interviewed may be markedly different from those who decline.
  • Response bias may also be a problem, which occurs when the answers given by respondents do not reflect their true beliefs.
  • Finally, there is still the problem of coverage bias.

• Exercises

  • (AM) Calculate the 95% confidence interval for the difference between the mean Anger-In score for the athletes and non-athletes.
  • (AT) What is the correlation between the participants' correct number of responses after taking the placebo and their correct number of responses after taking 0.60 mg/kg of MPH?