The purpose of this study was to explore the basis of test anxiety expressed when taking a statistics course using a structural modeling approach. The study involved 219 university students. The data indicated that statistical test anxiety was different from general test anxiety. The females expressed more general and statistical test anxiety than males, and students who had taken more prior math courses had higher math self-concept scores. Math self-concept and achievement in statistics were negatively related to statistical test anxiety, and the students who reported high levels of general anxiety also reported high levels of statistical anxiety. The structural model revealed variables not studied previously to be important in understanding statistical test anxiety.
The CAUSE Research Group is supported in part by a member initiative grant from the American Statistical Association’s Section on Statistics and Data Science Education