Elementary and middle school teachers in urban schools in India provided responses to the science efficacy instrument (STEBI-A). These responses were evaluated using Rasch analysis and parametric tests. Rasch fit statistics and person-item maps were evaluated. It was found that the instrument worked well for the two groups of teachers, but the differential item functioning analysis found that the teachers utilized several items in the scale differently. Parametric tests suggested that self-efficacy and outcome expectancy measures correlated highly for middle school teachers, for those that did not have a science degree and a written science curriculum. Significant predictors of self-efficacy are-minutes per week science is taught, educational level, number of days in the school year, holding of a science degree, and the presence of a science curriculum. From all of the analyses we conclude that teaching experience is important, but not necessarily enough to increase teachers' outcome expectancy beliefs. The results of this study should benefit educators and policy makers with respect to teacher education in India and around the world. (C) 2004 Wiley Periodicals, Inc.