Conditional estimates and 95% credible intervals for lnRR and lnCVR, obtained from contrast multilevel regression (MLMR) models to assess the effect of sex on infarct volume.

Usui, Takuji; Macleod, Malcolm R.; McCann, Sarah K.; Senior, Alistair M.; Nakagawa, Shinichi

doi:10.1371/journal.pbio.3001009.s012

pbio.3001009.s012.docx (24.55 kB)

Conditional estimates and 95% credible intervals for lnRR and lnCVR, obtained from contrast multilevel regression (MLMR) models to assess the effect of sex on infarct volume.

journal contribution

posted on 2021-05-19, 17:49 authored by Takuji Usui, Malcolm R. Macleod, Sarah K. McCann, Alistair M. Senior, Shinichi Nakagawa

The intercept here represents studies in which “Both” sexes were used. Bold italicized estimates indicate that the 95% credible intervals do not span zero. lnCVR, log coefficient of variation ratio; lnRR, log response ratio; MLMR, multilevel meta-regression.

(DOCX)