Statistical Analyses

ES Eric L. Simpson
MV Miguel Villarreal
BJ Brett Jepson
NR Nick Rafaels
GD Gloria David
JH Jon Hanifin
PT Patricia Taylor
MB Mark Boguniewicz
TY Takeshi Yoshida
AB Anna De Benedetto
KB Kathleen C. Barnes
DL Donald Y.M. Leung
LB Lisa A. Beck
ask Ask a question
Favorite

Demographics, AD clinical features and aeroallergen sensitization were compared between diagnostic groups using Fisher’s exact test for categorical measures and Wilcoxon 2-sample test for continuous measures; results are displayed as count (%) or mean (standard deviation) for discrete and continuous measures, respectively.

Comparisons between diagnostic groups in skin barrier measures (TEWL, SC hydration and surface pH), and serum and blood biomarkers were analyzed using a general linear regression model, adjusting for age, gender, study site and FLG genotype. Least squares means or geometric means (for non-normally distributed values) were estimated by diagnostic group. For normally distributed markers, estimates of the mean difference between diagnostic groups and 95% confidence interval were calculated. Non-normally distributed markers were log10 transformed prior to analysis, and results were back-transformed to estimate least squares geometric mean ratios and 95% confidence intervals between diagnostic groups. Except for the TEWL AUC comparison between the AD S. aureus+ and AD S. aureus− groups, all p-values reported were considered descriptive. No adjustments for multiple comparisons were made. SAS version 9.4 software (SAS Institute, Inc., Cary, NC) was used for all analyses.

Do you have any questions about this protocol?

Post your question to gather feedback from the community. We will also invite the authors of this article to respond.

post Post a Question
0 Q&A