1
$\begingroup$

I am using data from this website (data is at the bottom of the page) for a case-study. For the sake of question lets stick to any of FluWatch sheet say FluWatch-Alberta. I am coming up with a question of my own, i.e., if one disease has any relation with another one. What kind of statistical technique should I use here?

What i have thought so far

  • The data is nominal so correlation wouldn't work
  • Should I do some sort of cross classified observation? (I just read it somewhere not sure what it is)
  • Or I am on wrong track and I can just do correlation/regression to check if disease A is related with disease B
$\endgroup$
1
$\begingroup$

One can find correlations for this data, but not any causal relationships. There is a pronounced seasonal variation, which if ignored, would result in spurious correlation. I think you would need additional or different data to find any causal relationship.

$\endgroup$
3
  • $\begingroup$ okay thanks. so for just the given data, not any additional, what can i do to see if one disease is related with other? I don't have any other data so not sure what else to do. Assuming that we ignore seasonal variation, how can relate one disease to other? $\endgroup$ – Em Ae Nov 22 '16 at 15:58
  • $\begingroup$ For example, if you theory is that disease A can cause susceptibility to disease B, you need to know how many subjects get disease A when, how many also get disease B after what period of time, and you would need (among other things) to plot the times between getting diseases A and B to see if there is an increased probability at a particular time interval. $\endgroup$ – Carl Nov 22 '16 at 16:18
  • $\begingroup$ The "among other things" comment includes an adjustment or comparison for reducing seasonal epidemiology effects. For example, if for those who get diseases A or B but not both, disease A occurs sooner than disease B, it may be that the disease incubation times or otherwise epidemiology of disease identification times differ, such that that "A or B but not both A and B" frequency data becomes the control for the A then B test group. $\endgroup$ – Carl Nov 22 '16 at 21:35

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.