IDENTIFYING SENIOR HIGH SCHOOL STUDENTS' MISCONCEPTIONS ABOUT STATISTICAL CORRELATION, AND THEIR POSSIBLE CAUSES: AN EXPLORATORY STUDY USING CONCEPT MAPPING WITH INTERVIEWS

Correlation is an essential concept in statistics; however, students may hold misconceptions about correlation, even after receiving instruction. This study aimed to elucidate (1) the misconceptions held by senior high school students about correlation, using the tool of concept mapping along with interviewing, (2) the possible causes of these misconceptions, and (3) the effectiveness, advantages, and limitations of the adopted concept mapping using an interviewing technique for identifying student misconceptions. Twenty-five grade-12 students who had received tuition on correlation were the subjects of this study. Concept mapping through interviewing was used to collect and analyze data in order to identify the subjects' misconceptions, and their possible causes. The major study results are as follows. (1) Seven misconceptions about correlation were detected. Of these seven misconceptions, five were newly discovered by this study, while the other two are similar to those found by previous studies. Each of the seven misconceptions was held by 20-68% of the subjects, showing their prevalence and significance. (2) Four major factors related to the development of misconceptions about correlation were identified: learning materials, language, daily-life experiences, and existing mathematical concepts. (3) The concept mapping through the interviewing technique adopted in this study was effective in detecting misconceptions about statistics, especially in revealing new misconceptions, and it was also helpful in exploring their possible causes. However, tremendous effort and the time consumed are the major limitations of this technique. (4) The paper concluded by providing some recommendations for researchers and educators.