|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: how to do Bonferroni test after MANOVA
I did a MANOVA analysis:
manova y1 y2 y3 y4 y5 y6 y7 y8 y9 = pcp6 age health2 medpay insusf exc
hinfoc enabm pcputil pcpsatisf
xi3: mvreg y1 y2 y3 y4 y5 y6 y7 y8 y9 = i.pcp6 age health2 i.medpay
i.insusf i.exc i.hinfoc i.enabm i.pcputil i.pcpsatisf
y1-y9 are means of 9 subscales of the health care quality measurement
instrument. pcp6 has 5 levels indicating 5 types of health care
facilities. The main purpose here is to compare the adjusted means in
each of 9 subscales across 5 types of health care facilities to see
whether each of the 9 adjusted means differ significantly by health
care facility types. Finally I hope to come up with a table below:
Facility 1 Facility 2 Facility 3 Facility 4
Facility 5 P-values for group level comparisons
y1 adjusted
mean (AM) AM AM AM AM
??????
..
y8 - - - -
- -----
y9 AM AM AM AM
AM ??????
Is the method here Bonferroni? Does the Bonferroni here mean
accounting for analysis of 9 dependent variables or for analysis of 5
facilities?
How to do Bonferroni in stata for my case? If involving matrix, what
should the matrix be in my case? The matrix is killing me!
Thanks so much!
Lindsey
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/