Skip to main content

Table 3 Analysis results of longitudinal association between CRP and mSASSS when CRP levels were imputed by different imputation methods

From: A multiple imputation method based on weighted quantile regression models for longitudinal censored biomarker data with missing values at early visits

 

log(CRP)

Method

adj. RR (95% CI)

p-value

CC-DL/2

1.001 (0.98, 1.02)

0.9867

MI-MCMC 2

1.006 (0.99, 1.03)

0.5586

MI-CQR

1.010 (0.995, 1.02)

0.1839

MI-wCQR 2

1.018 (1.004, 1.03)

0.0095

  1. CC-DL/2: CC with CRP imputed by DL/2; MI-MCMC 2: MI-MCMC imputing both censored and missing CRP; MI-CQR: MI-unweighted CQR; MI-wCQR 2: MI-weighted CQR using estimated probability from censored CRP imputed by DL/2; adj. RR: adjusted Rate Ratio after controlling for sex, race, disease duration, co-morbidity, education, smoking status, BASDAI and medication usages of TNFi and NSAIDs