Skip to main content
Fig. 3 | Health and Quality of Life Outcomes

Fig. 3

From: Comparison of statistical methods for the analysis of patient-reported outcomes (PROs), particularly the Short-Form 36 (SF-36), in randomised controlled trials (RCTs) using standardised effect size (SES): an empirical analysis

Fig. 3

Estimated SES from different statistical methods against MLR. The x-axis of the scatter plots is the SES estimated by MLR, and the y-axis is the SES estimated by other statistical methods. The black dash line represents the method that produces the same SES as MLR. BB, beta-binomial regression; BLN, binomial-logit-normal regression; BR, beta regression; CLAD, censored least absolute deviation regression; Frac, fractional logistic regression; Median, median regression; MLR, multiple linear regression; OL, ordered logit model, OP, ordered probit model; Tobit, Tobit regression; SES, standardised effect size

Back to article page

Health and Quality of Life Outcomes

ISSN: 1477-7525

Contact us