Suchergebnisse

Discusses the problem of deteriorating survey response rates, arguing that empirical evidence does not support the widely accepted belief among researchers that response rates will continue to decline sharply. Analysis of 57 time series covering 51 surveys indicates that, although nonresponse has increased in more time series than it has declined, this pattern is less sweeping than previously depicted & indicates nondirectional trends, not regular gains or losses. Possible explanations for an increase in nonresponse include methodological & procedural changes, eg, increased use of telephone surveys, in addition to market factors & changes in labor force participation & household structure. It is argued that researchers should be concerned with why some rates are high & others are low rather than with a supposed universal nonresponse rise. 5 Tables, 40 References. S. Davies

Higher response to postal surveys typically results from use of the following: (1) more expensive mail services, such as certified delivery, reserved for a wave of later reminders to non-R's; (2) a covering letter containing an explanation of the study & the place of the R within it, a moderate level of ingratiation, sender's title under the "signature," & some form of official sponsorship rather than a completely private address; (3) questionnaire that is not overly long (though this makes less difference that was formerly thought), that contains interesting items, & that avoids objectionable ones; (4) a premium (perhaps 50 cents) enclosed with the initial forms; (5) a return envelope bearing an actual postage stamp; &, especially, (6) a postcard "reminder/thank you" sent a few days after the initial survey, followed by a series of reminders (with replacement questionnaires) to non-R's. AA.

Examines response rates of several large-scale Japanese public opinion surveys, including some of the most important recurring personal surveys (the Kokumin Seikatsu ni kansuru Yoron Chosa, the Shakai Ishiki ni kansuru Yoron Chosa, the Nihonjin no Kokuminsei, & the Toshi Seikatsu ni kansuru Yoron Chosa). Since the mid-1970s, overall response rates in Japanese surveys have declined by about 10% points. Males had lower response rates than females by about 10% points. Younger persons' response rates were lower than those of older persons, the lowest being those of persons in their 20s. There were differences in the size of the decline for males & females of different age groups. Metropolitan areas had the lowest response rates & showed steeper declines than rural areas. Also, the components of nonresponse were compared across the years. Most noteworthy was the increase in the number of refusals. The findings are discussed, & recommendations are made. 2 Tables, 4 Figures, 1 Appendix, 25 References. Adapted from the source document.

It has been well documented that response rates to cross-sectional surveys have declined over the past few decades. It is less clear whether response rates to longitudinal surveys have experienced similar changes over time. This article examines trends in response rates in several major, national longitudinal surveys in the United States and abroad. The authors find that for most of these surveys, the wave-to-wave response rate has not declined. This article also describes the various approaches that these surveys use to minimize attrition. [Reprinted by permission of Sage Publications Inc., copyright The American Academy of Political and Social Science.]

It has been well documented that response rates to cross-sectional surveys have declined over the past few decades. It is less clear whether response rates to longitudinal surveys have experienced similar changes over time. This article examines trends in response rates in several major, national longitudinal surveys in the United States and abroad. The authors find that for most of these surveys, the wave-to-wave response rate has not declined. This article also describes the various approaches that these surveys use to minimize attrition.

An experimental comparison of university versus newspaper sponsorship in a random digit dial telephone survey produced no significant response rate difference, but a clear difference in response distributions on one issue. Hypothesizes that the result was due to the newspaper having taken a clear position on the issue. (Abstract amended)

Background: Federally funded evaluation research projects typically strive for an 80% survey response rate, but the increasing difficulty and expense in reaching survey respondents raises the question of whether such a threshold is necessary for reducing bias and increasing the accuracy of survey estimates. Objectives: This analysis focuses on a particular component of survey methodology: the survey response rate and its relationship to nonresponse bias. Following a review of the literature, new analysis of data from a large, multisite random assignment experiment explores the relationship between survey response rates and measured nonresponse bias. Research Design: With detailed survey disposition data, the analysis simulates nonresponse bias at lower response rates. The subjects included 12,000 individuals who were fielded for 16 identical surveys as part of the Employment Retention and Advancement evaluation. Results: The results suggest scant relationship between survey nonresponse bias and response rates. The results also indicate that the pursuit of high response rates lengthens the fielding period, which can create other measurement problems. Conclusions: The costly pursuit of a high response rate may offer little or no reduction of nonresponse bias. Achieving such a high rate of response requires considerable financial resources that might be better applied to methods and techniques shown to have a greater effect on the reduction of nonresponse bias.

An attempt was made to determine the influence of precoding mailed questionnaires on response rates. Precoding facilitates tabulation & analysis of returned data. One authority on mailed surveys had suggested that precoding a questionnaire would reduce the response rate & therefore was not advisable. An experimental design using 2 experimental groups was employed to study the relationship. 200 Southern U students were randomly selected from a pool of 500 names & divided into the 2 groups. One group was sent a precoded questionnaire & the other group an identical questionnaire which was not precoded. There was no significant difference in response rates between the 2 groups at the .05 level of significance. Precoding mailed questionnaires does not appear to influence response rates. Modified AA.