S. DebRoy's scientific contributions

Citations

... (R Core Team, 2018). We used the mgcv package (Wood, 2019) for generalized additive mixed models (GAMMs), nlme package (Pinheiro et al., 2015) for linear mixed-effect models, and Vegan (Oksanen et al., 2015) for multivariate analysis. ...
... Finally, to account for repeated measurements an autocorrelation structure of order one was entered, with time as a continuous covariate and dragonfly ID as a grouping effect. The model was performed using the R packages MASS [65] and nlme [75]. A posthoc test was performed to observe differences between treatments using the R package emmeans [76]. ...
... Linear models on log-transformed data as log(GIT content mass) = log(a) + b log(body mass) were performed in R v 3.3.2 (R_Core_Team, 2015) with the 'nlme' package (Pinheiro et al., 2011); model estimates are given with their 95%CI. Models were performed on the whole dataset, and additionally with the inclusion of group (joey-in-pouch or adult) as a cofactor and the group × body mass interaction, using the small sample corrected Akaike's information criterion (AICc) to compare model performance, considering models that differed by more than 2 (ΔAICc >2) as providing a different fit to the data (Burnham et al., 2011). ...
... A multiple pairwise comparison test was performed by using a Bayes factor analysis between group levels with corrections for multiple testing. All analyses were performed by using the function "lme" and "pairwise_comparisons" in the packages "nlme" [27] and "pairwiseComparisons" [28] of R [29]. Results are expressed as Lsmeans ± SE, and significance was declared at p < 0.05. ...