Back to Annual Meeting Page
|
133rd Annual Meeting & Exposition December 10-14, 2005 Philadelphia, PA |
||
Frank J. Potter, PhD, Mathematica Policy Research, Inc, P.O. Box 2393, Princeton, NJ 08543, 609-936-2799, FPOTTER@Mathematica-MPR.COM
Response rates are measures of the “potential” for nonresponse bias and of the quality of a survey. High response rates imply a smaller potential for nonresponse bias and better survey quality than lower response rates. Various response rate algorithms are in the literature (Lessler and Kalsbeek 1992, AAPOR 2000). Response rates can be dichotomized into unweighted or weighted response rates. Unweighted response rates generally measure the proportion of the sample that resulted in useable information for analysis. Weighted response rates can be used to estimate the proportion of the survey population for which useable information is available. In some instances, the two response rates can result in identical values (if a sample is selected with equal probability). The two response rates may result in different values if a sample is selected with different selection probabilities (for example, oversampling or undersampling specific subpopulations). Unweighted and weighted response rates can be considered as distinct measures for evaluating the quality of a survey and may be useful in different situations and for different survey designs. The purpose of this paper is to discuss the differences between unweighted and weighted response rates, what these rates measure, and situations for their use.
Learning Objectives:
Keywords: Public Health Research, Evaluation
Presenting author's disclosure statement:
I wish to disclose that I have NO financial interests or other relationship with the manufactures of commercial products, suppliers of commercial services or commercial supporters.
The 133rd Annual Meeting & Exposition (December 10-14, 2005) of APHA