To allow for maximum adjustment of baseline functional status, treat this predictor as nominal (after rounding it to the nearest whole number; fractional values are the result of imputation) in...

To allow for maximum adjustment of baseline functional status, treat this predictor as nominal (after rounding it to the nearest whole number; fractional values are the result of imputation) in remaining steps, so that all dummy variables will be generated. Make a single chart showing proportions of various outcomes stratified (individually) by adlsc, sex, age, meanbp. For continuous predictors use quartiles. You can pass the following function to the summary (summary.formula) function to obtain the proportions of patients having sfdm2 at or worse than each of its possible levels (other than the first level). An easy way to do this is to use the cumcategory function with the Hmisc package’s summary.formula function. cumcategorysummary.formula Print estimates to only two significant digits of precision. Manually check the calculations for the sex variable using table(sex, sfdm2). Then plot all estimates on a single graph using plot(object, which=1:4), where object was created by summary (actually summary.formula). Note: for printing tables you may want to convert sfdm2 to a 0–4 variable so that column headers are short and so that later calculations are simpler. You can use for example: