摘要：AbstractThough numerous measures of problem solving skills in mathematics have been presented in the literature, procedures used to evaluate the construct validity of these measures are often incomplete. Few studies have examined multiple measures using dat a from the same sample or similar samples. The purpose of this study was to re-evaluate construct validity of theScale for Problem Solving Skills in Mathematics. This study was designed to improve this newly developed instrument by following the processes of construct validity on similar sample. Using a cluster sampling of 7th and 8th grade students, 416 respondents were included in the study. Of the participants, 218 (52.4%) were female and 198 (47.6%) were male. The Scale for Problem Solving Skills in Mathematics was developed by Uysal (2007) in order to determine the level of school students‟ problem solving skills in mathematics. This self-report instrument consists of 28 items scored on a five-point Likert type scale with responses ranging between 1 (never) to 5 (always) and has three subscales. To evaluate construct validity of the instrument, exploratory and confirmatory factor analyses were conducted. The data were analyzed by LISREL 8.7 and SPSS 17. The results of analyses based on responses to the items of 416 subjects indicated that there were problems with some of the subscales and individual items.
