Turning Research into Action: Using Factor Analysis to Enhance Program Evaluation

摘要

Purpose: Sexual activity among adolescents in the United States remains high. Nearly 46% of students grades 9-12 have engaged in sexual intercourse. One of the more recent statistical tools employed in evaluation efforts includes factor analysis. The objective of this study was to investigate the underlying dimensions of a survey instrument that assesses a youth character development program, which focuses on avoiding high-risk behaviors. Method: The 76-item survey instrument was administered to adolescents (age 12-18). During the 2009-2010 school year, 652 participants in the intervention group and 1110 participants in the comparison group completed the pre-, post-, and 6-month follow-up survey. Results: Using Ajzen’s theory of planned behavior groupings, 27 survey items were selected. Through iterative principal axis factoring, four factors were extracted and rotated. A visual scree plot was generated to determine the number of acceptable factors. The extracted factors accounted for 52.53% of the total variance. Factors were subjected to Equimax rotation with Kaiser normalization and converged after six iterations. Variables with patterned weights less than 0.44 were excluded. A reliability analysis demonstrated internal consistency. Conclusions: Identified factors included: 1) Teenagers’ attitudes toward sexual health behaviors;2) Teenagers’ perceptions of the consequences of sexual health behaviors;3) Parental or guardian expectations;and 4) Teenagers’ relationships with parents or guardians. This study’s results indicated that all factors can be described within Ajzen’s theoretical framework consistent with previous research findings. Results may be used to enhance delivery of the intervention.