Journal: Bioinformatics Advances
Article Title: A hierarchical negative-binomial model for analysis of correlated sequencing data: practical implementations
doi: 10.1093/bioadv/vbaf126
Figure Lengend Snippet: Estimates of the mean-structure coefficients of the two-level model for the different software implementations and the 9112 genes, for which the model was successfully fitted for all the implementations. The densities of the estimates are shown along the diagonal. The lower triangle contains Bland–Altman plots of the estimates for pairs of different software implementations, with the red dashed line indicating the mean difference and the black dashed lines marking the 95% limits of agreement. The upper triangle presents the numerical values of the limits. Panel A: β 1 ; Panel B: β 2 ; Panel C: β 3 . LME4L — lme4 with the Laplace approximation; LME4A — lme4 with the AGHQ approximation; GLMMa — GLMMadaptive ; TMB — glmmTMB ; SAS — PROC NLMIXED ; STATA — menbreg .
Article Snippet: In the remainder of the paper, we will refer to the use of menbreg command with the AGHQ as “STATA.”
Techniques: Software