This is following discussion with @schoffelen regarding resampling to achieve differential privacy in the results.
Right now it only computes the mean age. The data also contains many other variables, like sex, Height, Weight (*), and a number of questionaire outcomes. I suggest to include height and weight, which gives three variables between which I would anticipate some (but not too much) correlation.
The output results.txt should be reformatted to not include any headers.
(*) Note that Height and Weight are both present in the participant.tsv starting with a capita, whereas age and sex are without capitall
This is following discussion with @schoffelen regarding resampling to achieve differential privacy in the results.
Right now it only computes the mean age. The data also contains many other variables, like sex, Height, Weight (*), and a number of questionaire outcomes. I suggest to include height and weight, which gives three variables between which I would anticipate some (but not too much) correlation.
The output
results.txt
should be reformatted to not include any headers.(*) Note that Height and Weight are both present in the participant.tsv starting with a capita, whereas age and sex are without capitall