A study for development of statistical literacy scale for undergraduate students

Abstract

Statistical literacy was defined as the ability to understand basic concepts, vocabulary and symbol of statistics, and some probability; and critically evaluate statistical information in everyday life situations. The aim of this study was to develop a valid and reliable instrument measuring statistical literacy for university students. Statistics content covered in previous instruments on statistics learning (CAOS- Web ARTIST Project, 2005; Statistical Literacy Skills Survey, Schield, 2008; ARTIST Topic Scales, 2006) and 6-12 grades curricula implemented in Turkey were examined. A Statistical Content Rating Form (SLCRF) was formed in the light of knowledge and skills involved in the related domain. Scholars who were offering statistics and research methods courses were asked which statistics topics undergraduate students are required to know for being statistically literate. Content coverage was determined according to scholars’ answers, and then questions were selected among existing instruments in the literature. For topics that questions in the literature are insufficient then new questions were written by the researcher. Suggested questions were examined by experts and the 42 questions were chosen and tried out with a pilot study with 33 participants. Based on the results, the number of questions was reduced to 20 and it was tried again with a sample consisting of 90 participants. Then, the number of questions was reduced to 17 and Statistical Literacy Scale (SLS) was developed. SLS was administered to 476 undergraduate students. The construct validity of SLS was examined with experts’ item based opinions and results of factor analysis. Content validity was assured with SLCRF results. From the data gathered from 476 participants the Cronbach alpha coefficient was calculated as .532. It is possible to say that SLS has the attributes of construct, content, and curricular validity.