Comprehensive selectivity assessment for a major consumer panel: attitudes toward government regulation of environment, health and safety risks

Researchers acknowledge several reasons for possible non-representativeness in surveys conducted on samples drawn from large consumer panels. We model the selection process for one major consumer panel, maintained by Knowledge Networks, Inc., starting with over 525,000 random-digit-dialed panel-recruitment contacts and ending with one specific sample of 2,911 respondents to an actual survey. We match addresses or telephone exchanges to the appropriate census tract and explain sample selection relative to the initial RDD contact pool using a set of fifteen orthogonal factors based on census tract characteristics, plus county voting percentages in the 2000 Presidential election. To assess sample selectivity, we consider answers to a survey question where respondents were asked for their opinions about the proper role of government in environmental, health and safety regulation. We model these attitudes as a function of individual characteristics. Despite evidence of sample selectivity of a plausible nature, the effect of this selectivity is not statistically significant in explaining the attitudes expressed in the survey. Parameter estimates and inferences change only slightly when we control for non-random survey participation.