Share your ideas for the JMP Scripting Unsession at Discovery Summit by September 17th. We hope to see you there!
Choose Language Hide Translation Bar
Level I

Using JMP® To Analyze Factors That Predict Depression

Grant Reeves and Moumita Sen, Oklahoma State University


Best Student Poster Winner


According to the Department of Health and Human Resources, over two million adolescents aged 12-17 suffered from major depressive episodes in the past year. If diagnosed early, it can avoid incidents such as the recent Florida school shooting. We examined the Youth Risk Behavior Survey (YRBS) data obtained from the Center for Disease Control and Prevention website to analyze and predict signs of depression among survey respondents. The YRBS combined data set, contained eighty-nine demographics and lifestyle-related questions. From this, we narrowed down to the top eighteen questions we felt indicated signs of depression based on official symptoms found on multiple medical health websites, such as and CDC website. These symptoms include sadness, hopelessness, guilty feelings, irritability, abuse as well as perceptions about physical features. Once the data was cleaned, a sample size of over 117,000 surveyed answers was available for analysis. JMP Pro 13 was used to determine a correlation between depression and questions that addressed the following: alcohol interaction, drug interaction, suicidal thoughts and tendencies, physical and sexual abuse, violent tendencies, and self-perception. Participant records were flagged based on response to the original question and a composite score of all flags was calculated and analyzed.