1
$\begingroup$

I am a graduate student in biochemistry, and I am looking at cancer death rates for the Canadian population in 2010. Basically, I have acquired from Statistics Canada:

1) The estimates of individuals per age category

2) The number of registered deaths related to cancer overall per age category. I also have death rates for specific cancer types.

I want plot death rates from 1) and 2) but I am not sure about standardizing age. I think I might have to do so because I'll compare rates from different age classes. The thing with cancer is that it is age-dependent (in general, 25-74). I would appreciate the community's feedback.

Moreover, is there an R package that I could use?

Thank you!

$\endgroup$
  • $\begingroup$ Typically, death rates are plotted as a function of age by year, or by age groups if there are few cases of interest in individual years of age. What beyond that do you mean by "standardizing"? It would also help greatly to know what you want to do with the plotted death rates. As a student, you should consult with an epidemiologist or statistician at your institution before you go too far down this path on your own, as those will be the people reviewing any results you intend to publish and you can learn a lot from them. They may also learn something about biochemistry from you. $\endgroup$ – EdM Apr 10 '15 at 22:25
0
$\begingroup$

As regards the standardization in R look at this page on SO site.

As regards if it is correct to standardize data or not, I suggest you that it is always better to not treat data unless it is impossible analyze the dataset without to do that; in your case, I think it is mandatory choice to do that in order to compare data. Alternatively, you could analyze the dataset without standardizing data in the case the classes are populated enough (e.g. # obs > 1000).

$\endgroup$

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.