Correlation between time to event data and continuous data

Question

I want to measure the correlation between the survival time which is a time to event data and the patient's activity count which is measured on continuous scale. What type of correlation coefficient is available to measure the strength of these two variables?

Answer 1

There is nothing wrong with using Pearson's correlation coefficient (frequently called THE correlation coefficient) with these variables. I would also have a look at Spearman's rank correlation coefficient. It is less sensitive to extreme values.

http://en.wikipedia.org/wiki/Spearman%27s_rank_correlation_coefficient

However, both coefficients have the drawback that they only measure linear relationships. Hence it is worthwile to have a look at the scatterplot of the variables. Adding a smoother to the graph can be worthwile too, especially if the plot is clutterd and you have trouble to spot a relationship with the naked eye.

Answer 2

Use Event as Row Label, Time as Column label and Activity as Value in a Pivot. If you're doing this in R, use library(reshape). Using melt and cast functions, you can get a solution to your problem i guess. Let me know if you need any further clarifications.