Jmp pro version 17

For the statistical analyses, the decimal visual acuity was converted to a logarithm of the minimum angle of resolution (logMAR) units. The clinical characteristics of the patients treated with IVA and IVF were compared with those not treated using the chi-squared test or Fisher’s exact test for non-numeric data and the Wilcoxon test for numeric data. A one-way analysis of variance was used to assess changes in the BCVA, CRT, and CCT in each group. The rate of eyes with residual exudative changes was compared between the IVA and IVF groups using the chi-squared test. The changes in the three parameters at each time point between the two groups were compared using the unpaired t-test. All statistical analyses were performed using JMP Pro version 17 software (SAS Institute Inc., Cary, NC, USA). A p-value < 0.05 was considered statistically significant.

We tested the effects of litter quality (two levels: natural vs. poor), warming (three levels: Ambient, + 2 °C, and + 4 °C), and their interaction on growth rate and leaf consumption rate by each detritivore taxon (Polypedilum, Atalophlebiinae, and Calamoceratidae) using generalized least square model (GLS) in the nlme package⁶⁴ . Because residuals were highly heteroscedastic, we modeled the variance using the function varIdent, using litter quality and temperature as the stratum. Since our experiment aimed to evaluate the individual response of each detritivore species to decreasing litter quality and warming, we conducted separate models for each species. To interpret models with significant interaction terms, post-hoc Tukey’s HSD tests were carried out using the multcomp package in R 3.1.3^{66 (link)}.
We used survival-reliability analysis to compare the survivorship of each detritivore taxon in response to leaf litter quality and warming⁶⁷ . We tested the effects of leaf litter quality and warming using Cox's proportional hazard model. We conducted the survival-reliability analyses in JMP Pro version 17 (SAS 2022).

Each set of data was tested to determine if assumptions for normal distribution were met utilizing Shapiro-Wilk. Normally distributed data were tested with a 2 × 2 factorial ANOVA to assess the main and interaction effects of condition (sham vs. SCI) and time (30d vs. 180d post-injury) within each bone site. If the model p-value was statistically different (p < 0.05), a Tukey HSD test was run to assess pairwise comparisons. If normality assumptions were not met for data, a Kruskal-Wallis test was performed. If the test was statistically different, a Steel-Dwass All Pairs test was completed to assess pairwise comparisons. When non-parametric tests were used, the Kruskal-Wallis is noted in parentheses with the p-value. The main and interaction effects are reported for normally distributed data. All data are presented as box and whiskers plots with all individual data points shown. All statistical analyses were completed on JMP Pro version 17 (SAS, Cary, NC, USA).