Experiments offer more reliable evidence on causation than observational studies, which is not to gainsay the contribution to knowledge from observation. Experiments should be analyzed as experiments, not as observational studies. A simple comparison of rates might be just the right tool, with little value added by "sophisticated" models. This…

Field experiences with external (qualitative) evaluation audits based on the work of E. G. Guba and Y. S. Lincoln (1981, 1985) are detailed, including evaluation contexts and purposes, procedures, and findings. Such audits represent a viable meta-evaluative tool for assessing the quality of naturalistic evaluation results. (SLD)

A study of the use of verbal active parental consent, obtained via telephone, for drug abuse prevention research among 2,948 adolescents is reported. Using this approach as a follow up to mailings requesting written consent, researchers were able to contact a parent for 96 percent of the students. (TJH)

The historical linkages between the evolution of the survey research method and applied social research is reviewed. It is argued that most or all of the elements of the modern survey were developed in response to immediate, practical (as opposed to academic) concerns. (TJH)

During the winter and spring of 2003, the Survey Research Laboratory conducted a survey of residents of the Ida Wells and Madden Park housing developments on Chicago's near-south side. This article reviews existing research findings on using indigenous interviewers and reports the findings about the benefits and challenges of using residents as…

Three methods of estimating tobacco products experimentation were examined in 13 junior high and 6 high schools. The methods were aggregated students' self-reports of tobacco experimentation, school personnel prevalence estimates of student tobacco experimentation, and school outdoor refuse evidence. The school personnel method proved the most…

Use of the bootstrap resampling technique (BRT) is assessed in its application to resampling analysis associated with measurement of payment allocation errors by federally funded Family Assistance Programs. The BRT is applied to a food stamp quality control database in Oregon. This analysis highlights the outlier-sensitivity of the…

This study assessed the nature of response bias in a two-stage data-collection design (telephone interviews followed by a questionnaire mailing), which was used to examine the effectiveness of a state-level pharmaceutical assistance program for the elderly. Demographic and health factors affecting response (N=1,705 elderly persons) are discussed.…