Research Paper Volume 16, Issue 4 pp 3056—3067

Multiple imputation of systematically missing data on gait speed in the Swedish National Study on Aging and Care

class="figure-viewer-img"

Figure 1. Simulated sampling distribution of the combined adjusted odds ratio of gait speed on 5-years mortality. The black line represents the combined adjusted effect OR1 = 0.55 for the second level of gait speed (0.8-1.2 vs ≤ 0.8 m/s), and OR2 = 0.29 for the third level of gait speed (>1.2 vs ≤ 0.8 m/s). The three imputation methods that are compared are the fully conditional specification (FCS), multivariate normal (MVN), and conditional quantile imputation (CQI). Simulations are based on 1 000 replications with 100 imputations including four synthetic studies based on the Swedish National Study on Aging and Care. Adjustments were made for severe disability (ADL), mild disability (IADL), cognitive functional status measured with the Mini-Mental State Examination (MMSE), number of chronic diseases (comorbidities), all-cause mortality (5-years mortality), sex (female), and age (in years).