Suchergebnisse

A 1992 national survey of 1,072 Medicare beneficiaries who had surgery for prostate cancer also evaluated how the mode of data collection affected responses. The samples outside of MA were randomly assigned to either mail or telephone strategies. In MA, the two primary modes were mail & personal in-home interviews. Of the 51 questions compared, there were 25 statistically significant differences between the mail & telephone responses. Differences were concentrated among questions asking for current self-descriptions. The mail responses indicated more problems or worse health status 22 times. When mail responses & personal interviews were compared, there were only nine significant differences, of which four indicated more problems via mail response. Results highlight the need for better generalizations about which questions are affected by mode & how to minimize mode effects to facilitate multimode surveys. 3 Tables, 1 Appendix, 22 References. Modified AA