---+ Binary Response, Random Sample of 1000 Patients from the SUPPORT Study, Missing Data Analyze the =[[http://biostat.mc.vanderbilt.edu/twiki/pub/Main/DataSets/support.html support]]= dataset available at http://biostat.mc.vanderbilt.edu/twiki/pub/Main/DataSets/support.sav (an R =save= file that can also be downloaded and <tt>load</tt>ed using the =Hmisc getHdata= function) to develop a model to predict the probability that a patient dies in the hospital. Consider the following predictors: =age, sex, dzgroup, num.co, scoma, race, meanbp, hrt, temp, pafi, alb=. As part of your analysis do the following: 1 Make a single chart showing proportions of deaths stratified by each of the other variables listed above 1 Characterize patterns of missing values in the predictors by plotting missingness tendencies of single predictors and jointly of two predictors at a time, and by using recursive partitioning to determine what kind of patients tended to have a higher proportion of missing measurements for the predictor that is missing most often 1 Initially estimate marginal relationships between continuous predictors and outcome using a nonparametric smoother 1 Use marginal potential predictive discrimination of predictors to decide on how to spend degrees of freedom 1 Impute missing lab data using [[http://biostat.mc.vanderbilt.edu/twiki/pub/Main/DataSets/support.html "most normal"]] values; impute =race= using the most frequent category (hint: see the =Hmisc impute= function) 1 Fit a multivariable model with minimal observations deleted due to <tt>NA</tt>s 1 Test partial effects of all predictors 1 Graphically interpret the model three distinct ways 1 Validate the model for discrimination and calibration ability
This topic: Main
>
WebHome
>
CE
>
Puzzlers
>
Puzzler2
Topic revision:
15 Aug 2006,
AyumiShintani
(raw view)
Copyright © 2013-2022 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Vanderbilt Biostatistics Wiki?
Send feedback