Sophie,
You are mistaken. ANOVA, ANCOVA, regression etc, can adjust for either continuous or categorical variables (i.e. for explanatory variables that are on the right-hand side of the equals sign). On the other hand, ANOVA, ANCOVA, regression, etc., require a continuous outcome variable (i.e. the variable on the left-had side of the equals sign.) If you have a categorical outcome variable you need to use logistic or Poisson regression, which is not your case.
John
John David Sorkin M.D., Ph.D.
Chief, Biostatistics and Informatics
University of Maryland School of Medicine Division of Gerontology
Baltimore VA Medical Center
10 North Greene Street
GRECC (BT/18/GR)
Baltimore, MD 21201-1524
(Phone) 410-605-7119
(Fax) 410-605-7913 (Please call phone number above prior to faxing)
>>> Sophie <[log in to unmask]> 8/3/2009 3:32 AM >>>
Dear all,
Here is my question. I'm interested in quality of life of two groups :
cancer people and healthy people.
I'd like to see if there is a quality of life difference betwenn them two
controlling for two categorical variables : education level (high, middle,
little) and financial situation (difficult, ok, good).Education level are
not the same betwenn the two groups, as well as financial difficult
So, at first I thought to use ANCOVA, but I think I can't because the two
covariates (education and finances) are not the same in the two groupes, and
also because they are categorical variables, and I think covariates have to
be continuous variables.
So, what can I do?
May be, I could use hierachical regression with covariates in the first step
with dummy coding, and group in the second step also with dummy coding.
what do you think?
Best, sophie
Confidentiality Statement:
This email message, including any attachments, is for the sole use of the intended recipient(s) and may contain confidential and privileged information. Any unauthorized use, disclosure or distribution is prohibited. If you are not the intended recipient, please contact the sender by reply email and destroy all copies of the original message.
|