Question

Nonresponse. When responses are not obtained from some of the individuals in the sample because either those individuals cannot be reached or refuse to participate, we have nonresponse bias.

(a) Discuss some of the dangers of nonresponse.

(b) Many sample surveys that are reported in the media have rates as low as 10%. Explain the consequences of such low response rates in trying to generalize the results to the entire population.

Short answer

Part (a) The resultant predicted value may be too high or too low.

Part (b) Overestimation or underestimation will result.

Step-by-step solution

Part (a) Step 1. Given information.

The given statement is:

When responses are not obtained from some of the individuals in the sample because either those individuals cannot be reached or refuse to participate, we have nonresponse bias.

Part (a) Step 2. Some of the dangers of nonresponse.

If some of the people in a sample do not complete the survey or have refused to participate, then the estimate will be different than if everyone in the sample completes it.

This results in a nonresponse bias in the study. The predicted value would be either too high or too low due to the nonresponse for the said survey.

Part (b) Step 1. Explanation.

When media reports on sample surveys, the response rate might be as low as 10%.

If the response rate is low, the estimate is more likely to have a nonresponse bias.

Hence. When the results are used to generalize the results to the population, it is evident that the estimate either overestimates or underestimates.