Estimating Eligibility Rates: A Crucial Component of the Calculation for Response Rates

Abstract

Response rates are used by analysts to assess survey quality: higher response rates are usually desired to reduce the incidence of non-response bias. The response rate is simply defined as the ratio of the number of completed interviews divided by the number of eligible sample units. However, due to the inconsistency of the definition of response rates often quoted in travel surveys, it is difficult to explicitly state that declining response rates are the result of less people willing to participate in surveys or are attributed to the calculation of response rates. It is most likely to be a combination of these two factors. This paper describes two well known formulas used to calculate response rates; the Council of American Survey Research Organizations (CASRO) formula and the American Association for Public Opinion Research (AAPOR) formula. The real difference between these formulas lies in the estimate of eligible sample units amongst the sample units of unknown eligibility. Through examination of two call history files, the recruitment phase for two household travel surveys, eligibility rate estimates for the sample units of unknown eligibility were calculated and used in the response rate formulas. It was found that the rates of eligibility for the sample units of unknown eligibility were higher than the eligibility rates for the units of known eligibility. These results were not expected and further confirm that agencies need to treat units of unknown eligibility carefully when calculating response rates.