BACKGROUND: Laboratory studies often involve analyses of highly skewed data for which means are not an adequate measure of central tendency because they are sensitive to outliers. Attempts to transform skewed data to symmetry are not always successful, and medians are better measures of central tendency for such skewed distributions. When medians are compared across groups, confounding can be an issue, so there is a need for adjusted medians. METHODS: We illustrate the use of quantile regression to obtain adjusted medians. The method is illustrated by use of skewed nutrient data obtained from black and white men attending a prostate cancer screening. For 3 nutrients, saturated fats, caffeine, and vitamin K, we obtained medians adjusted by age, body mass index, and calories for men in each race group. RESULTS: Quantile regression, linear regression, and log-normal regression produced substantially different adjusted estimates of central tendency for saturated fats, caffeine, and vitamin K. CONCLUSIONS: Our method was useful for analysis of skewed and other nonnormally distributed continuous outcome data and for calculation of adjusted medians.
BACKGROUND: Laboratory studies often involve analyses of highly skewed data for which means are not an adequate measure of central tendency because they are sensitive to outliers. Attempts to transform skewed data to symmetry are not always successful, and medians are better measures of central tendency for such skewed distributions. When medians are compared across groups, confounding can be an issue, so there is a need for adjusted medians. METHODS: We illustrate the use of quantile regression to obtain adjusted medians. The method is illustrated by use of skewed nutrient data obtained from black and white men attending a prostate cancer screening. For 3 nutrients, saturated fats, caffeine, and vitamin K, we obtained medians adjusted by age, body mass index, and calories for men in each race group. RESULTS: Quantile regression, linear regression, and log-normal regression produced substantially different adjusted estimates of central tendency for saturated fats, caffeine, and vitamin K. CONCLUSIONS: Our method was useful for analysis of skewed and other nonnormally distributed continuous outcome data and for calculation of adjusted medians.
Authors: Anuj K Dalal; Adam Schaffer; Esteban F Gershanik; Ranganath Papanna; Katyuska Eibensteiner; Nyryan V Nolido; Cathy S Yoon; Deborah Williams; Stuart R Lipsitz; Christopher L Roy; Jeffrey L Schnipper Journal: J Gen Intern Med Date: 2018-03-12 Impact factor: 5.128
Authors: Seungyoun Jung; Naomi Allen; Alan A Arslan; Laura Baglietto; Louise A Brinton; Brian L Egleston; Roni Falk; Renée T Fortner; Kathy J Helzlsouer; Annika Idahl; Rudolph Kaaks; Eva Lundin; Melissa Merritt; Charlotte Onland-Moret; Sabina Rinaldi; María-José Sánchez; Sabina Sieri; Helena Schock; Xiao-Ou Shu; Patrick M Sluss; Paul N Staats; Ruth C Travis; Anne Tjønneland; Antonia Trichopoulou; Shelley Tworoger; Kala Visvanathan; Vittorio Krogh; Elisabete Weiderpass; Anne Zeleniuch-Jacquotte; Wei Zheng; Joanne F Dorgan Journal: Fertil Steril Date: 2017-04 Impact factor: 7.329
Authors: Jacob K Kresovich; Peter H Gann; Serap Erdal; Hua Y Chen; Maria Argos; Garth H Rauscher Journal: Epigenomics Date: 2018-03-12 Impact factor: 4.778
Authors: Jing Chen; L Lee Hamm; Myra A Kleinpeter; Fred Husserl; Islam Enver Khan; Chung-Shiuan Chen; Yanxi Liu; Katherine T Mills; Chuan He; Nader Rifai; Eric E Simon; Jiang He Journal: Am J Nephrol Date: 2012-03-27 Impact factor: 3.754
Authors: Naweed S Alzaman; Bess Dawson-Hughes; Jason Nelson; David D'Alessio; Anastassios G Pittas Journal: Am J Clin Nutr Date: 2016-05-18 Impact factor: 7.045
Authors: Casey M Rebholz; Tianying Wu; L Lee Hamm; Robin Arora; Islam E Khan; Yanxi Liu; Chung-Shiuan Chen; Katherine T Mills; Stephanie Rogers; Myra A Kleinpeter; Eric E Simon; Jing Chen Journal: Am J Nephrol Date: 2012-09-13 Impact factor: 3.754
Authors: Susan Cheng; Martin G Larson; Elizabeth L McCabe; Ewa Osypiuk; Birgitta T Lehman; Plamen Stanchev; Jayashri Aragam; Emelia J Benjamin; Scott D Solomon; Ramachandran S Vasan Journal: Circ Cardiovasc Imaging Date: 2013-08-05 Impact factor: 7.792