Psychosocial Predictors of Consistent Condom Use Among Women at Risk of Sexually Transmitted Disease: Comparing Rasch and Classical Methods for Item Selection

• Activity Number: 291
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 8:30 AM to 10:20 AM
• Sponsor: Statistics Without Borders
• Author(s): Resmi Gupta*+ and Richard Ittenbach and Maurizio Macaluso
• Companies: Cincinnati Children's Hospital Medical Center and Cincinnati Children's Hospital Medical Center and Cincinnati Children's Hospital Medical Center
• Keywords: Rasch modeling ; Classical test theory ; Generalized linear model

Abstract

For consulting statisticians routinely encountering large multifactor databases in the area of public health,Rasch methodology (RM)may provide an appealing alternative to classical test theory (CTT)approaches for item reduction.The purpose of this study was to compare methods using data from a prospective study of women attending sexually transmitted disease clinics,who participated in a condom promotion program.Item selection using exploratory factor analysis (EFA)under CTT,and RM led to summary scores that were evaluated for consistency and precision.Scores were used to model the odds of consistent condom use(CCU) at baseline(BL) and during a six-month follow-up(FU) period separately and compared model fit (BIC and QIC).RM identified one six-item attitude scale, one six-item communication scale and one four-item confidence scale.EFA under CTT identified two attitude factors,two communication factors,and one self-efficacy factor.The models had similar fit for CCU at BL (BICRM=1064,BICCTT=1066) and during FU (QICRM=3867, QICCTT=3866.For consulting statisticians RM may offer an efficient and equally informative item-reduction technique to yield the same predictive ability as CTT.