An empirical investigation of sampling strategies in marital research

The ability of marital researchers to interpret and build upon previous research has been hindered by a lack of data on the procedures used to recruit subjects. The current studies address this shortcoming by examining the effects of different sampling techniques on the samples obtained in marital research. In Study I, couples recruited through newspaper advertisements were found to be at greater risk for marital discord than couples recruited through marriage licenses, on the basis of demography, premarital experiences, personality, and marital satisfaction. In Study 2, couples who responded to a mailed solicitation were Sound to be less traditional and of higher status in terms of jobs and education than couples who did not respond, on the basis of data available for all couples from their marriage licenses. Effect-size estimates indicate that sampling technique had greater effects on sample composition than self-selection bias. Based on these findings, Jive recommendations are made for improving the quality of sampling procedures in marital research.