Homework 10

Due: 2022-11-15, 11:59pm

All homework must be submitted via Blackboard. Your answers must be in a MS Word (DOCX) or PDF format. Your submitted document should have sections corresponding to those in this homework.

Please make sure that you have watched the videos and have done the readings. Everyone should do this independently; you can discuss the process, but the answers are expected to be different.

Include graphs as images in your document. Make sure you comment on the Stata output, figures and tables. Include all code used to complete the homework so that your results can be reproduced (you may edit out irrelevant portions). Use the lecture notes as a guide.

1. Neidert data (100%)

Use the Neidert body composition data for this exercise.

Neidert and colleagues (2016) studied the relationship between body composition measurements: plasma DPP-IV activity, gynoid fat, BMI and lean mass. They recruited 111 subjects from Auburn University (40 men and 71 women) and collected the body composition variables for the study.

The full article may be found here:
Neidert LE, Wainright KS, Zheng C, Babu JR, Kluess HA: Plasma dipeptidyl peptidase IV activity and measures of body composition in apparently healthy people. Heliyon 2016;2:e00097.
https://doi.org/10.1016/j.heliyon.2016.e00097

The data file may be downloaded from this link:
Neidert LE, Wainright KS, Zheng C, Babu JR, Kluess HA: Plasma dipeptidyl peptidase IV activity and measures of body composition in apparently healthy people. Dryad Digital Repository 2016.
https://doi.org/10.5061/dryad.2680t

We will examine the relationship between the fat/lean ratio, BMI, and sex.

  • Make histograms of the fat/lean ratio, and BMI; make side-by-side dotplots separating by sex. Make a scatterplot of fat/lean ratio and BMI. Comment on what you observe.
  • Calculate the correlation coefficient between fat/lean ratio and BMI. Calculate the 95% confidence interval and p-value.
  • Calculate the p-value for the correlation coefficient using 10000 permutations. Does it agree with the above?
  • Regress fat/lean ratio on BMI, i.e. fit a line to predict the former using the latter. Overlay this line on the scatterplot of the two variables; put the fat/lean ratio in the y-axis. What is the intercept and the slope of this line, and what does this tell you about the relationship between BMI and fat/lean ratio (use both the values and their confidence intervals)?
  • What proportion of the variance in lean/fat ratio is explained by variation in BMI? Is BMI a good predictor of lean/fat ratio?

2. Acknowledgements

Please acknowledge individuals who helped you or resources thay were helpful in completing the homework.