SECONDARY ANALYSIS IN THE DEVELOPING AREAS

In: Public opinion quarterly: journal of the American Association for Public Opinion Research, Volume 31, Issue 2, p. 272-278

Abstract

Old sample surveys from the developing areas can be used for a number of purposes not adequately discussed in the soc sci literature. Examples from field res conducted on the Turkish bur'cy were used to describe the possibilities for secondary analysis. It was suggested that longitudinal survey res might be designed around studies performed by other investigators; the opportunities for panel & trend studies were particularly emphasized. The Turkish res was also aided by the fact that the old surveys could be utilized to estimate nonresponse bias; from 2 studies conducted in 1956 a great deal of information on nonresponse bias in 1965 was made available. Finally, the possibilities for combining data from several surveys were mentioned; from the Turkish material it becomes possible to explore the personal characteristics of admin'ors which led to a favorable or unfavorable evaluation by the villagers. AA.