Survival analysis was performed in participants without missing in covariates. Event was defined as incidence of loss of independence or death. The entry date of each participants was used as the starting point for survival analysis. Participants were followed up to March 31, 2014. Cox proportional hazard model was used to estimate hazard ratio (HR) and 95% confidential intervals (95% CIs). We calculated HR adjusted by potential confounders (age, male, BMI, cerebrovascular disease, cognitive dysfunction, SF-12 physical functioning, and SF-12 mental health). BMI was adjusted for categorical variables with normal range (18.5 to 24.9) as the reference. In the primary analysis, we analyzed the association of poor oral function with outcome. In the secondary analysis, we analyzed the association of poor oral function classified as having QOL impairment due to dysphagia with outcome.

To consider the effect of selection bias due to missing covariates in the population, we conducted the sensitivity analysis. We performed a multiple imputation procedure using the chained equation method based on the missing-at-random assumption for participants with missing one or more covariates. The missing values were imputed using poor oral function, incidence of loss of independence or death, and covariates. We created 20 imputed datasets, followed by integrated into one data set. Cox proportional hazard model was used to estimate HR and 95% CIs for the integrated dataset using the multiple imputation procedure.

All analyses were conducted using Stata version 15.1 (StataCorp, Texas, USA). A P value <0.05 (two-tailed) was set at statistically significant.

Note: The content above has been extracted from a research article, so it may not display correctly.

Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.

We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.