nma

Frequentist random-effects network meta-analysis using the netmeta R package (DL estimator, t-distribution confidence intervals).

Parameters

• df: Data frame with columns studlab (chr), treat1 (chr), treat2 (chr), TE (num, mean difference treat1 − treat2), seTE (num).
• greater_is_better: Logical. If TRUE, higher values rank better (e.g. accuracy). If FALSE, lower values rank better (e.g. error rate).

Return value

A named list with:

• ranking: Named numeric vector of P-scores (0–1, higher = better rank).
• league: Named list with matrices md, lower, upper, z, pval. Each is a treatment × treatment matrix. Diagonal entries are NA.
• heterogeneity: Named list with tau2, tau, i2, i2_lower, i2_upper, q, q_df, q_pval.
• prediction: Named list with matrices lower and upper (95% prediction intervals). Diagonal entries are NA.