366b - Testing Controversial Health Claims: A Step-by-Step Data Analysis Using Python

In this tutorial, we use Python to explore how data analysis can help evaluate controversial health claims. Focusing on correlation analysis, we examine NHANES data on blood lead levels and cognitive function in older adults. You'll learn how to interpret correlation strength, direction, and significance, understand why correlation does not imply causation, and apply critical thinking to assess scientific claims. This video combines coding and statistics to show how real data informs reliable conclusions. Code available here: https://github.com/bnsreenu/python_for_microscopists/blob/master/366b_Correlation_in_NHANES_Lead_vs_Cognition.ipynb *Download data from here:* https://wwwn.cdc.gov/nchs/nhanes/continuousnhanes/default.aspx?BeginYear=2013 *Laboratory Data (2013-2014):* "Lead, Cadmium, Total Mercury, Selenium, and Manganese - Blood" This contains the blood lead levels you need File name will be something like PBCD_H.XPT (the "H" indicates 2013-2014 cycle) *Questionnaire Data (2013-2014): "Cognitive Functioning"* This includes the CERAD Word Learning/Recall, Animal Fluency, and Digit Symbol Substitution Test (DSST) assessments About the National Health and Nutrition Examination Survey Cognitive Performance Assessments | Healthy Aging Data | CDC File name will be something like CFQ_H.XPT *Demographics Data (2013-2014)* Essential for controlling confounders like age, sex, race/ethnicity, education Also contains the survey weights needed for proper statistical analysis File name will be DEMO_H.XPT