8

You are right that this is a very common scenario in medical research. "I should note that these studies are not meant to invent a new method of treatment or change protocols, they are used to see what variables are of interest for future research." OK, I take this to mean that you are interested in causal inference, not in prediction. And from the ...


8

It depends on how those predictions (whatfor) are made. Say you do a study on the influence of alcoholic products on health. Say you measure the number of occurances of cardiovascular disease as dependent variable and you have, among other beverages, separately white wine consumption and red wine consumption as independent variables. For a lot of people, ...


7

This is a situation where mathematical abstraction is a huge help. In the following I will not introduce any new ideas, nor carry out any calculations, but will only exploit basic, simple definitions of linear algebra to present an effective way of thinking about collinearity. The definitions needed to understand this are vector space, subspace, linear ...


3

I'm afraid I don't know Stata (at all...), so I'm making some guesses here. Your real data differ somehow, or Stata is doing something I can't divine, because you have yhats for two patients with missing responses. Using complete case analysis, I replicated the logistic regression model in R. Your yhats are predicted probabilities from a standard ...


3

The only way to accomplish this is through constraints on coefficients. This will not be a standard linear regression though. It'll be similar to regularization except the shrinkage coefficient will be a vector, not scalar. For instance, you define a problem as a typical least squares with a penalty on coefficients: $$\min_{\beta_j} \sum_i(y_i-\beta_0-\sum_{...


3

From a Cox model you get log hazard ratios because you do not estimate the baseline hazard. If you want to get predictions for the expected survival times, you can use accerelated failure time models. These are provided via function survreg().


1

Deviance residuals shouldn't necessarily be normally distributed, even when everything is perfectly fine. So they needn't match a normal / follow a straight line on a qq-plot when that plot is based on a normal distribution. Although I use a logistic regression model as my example instead of Poisson, it may help you to read my answer here: Interpretation ...


Only top voted, non community-wiki answers of a minimum length are eligible