Hi,
I am trying to make sense out of the following output.
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\
. mhodds cc gbrfed2, by(moslbir2)
Score test for trend of odds with gbrfed2
by moslbir2
(The Odds Ratio estimate is an approximation to the odds ratio
for a one unit increase in gbrfed2)
-------------------------------------------------------------------------------
moslbir2 | Odds Ratio chi2(1) P>chi2 [95% Conf. Interval]
----------+--------------------------------------------------------------------
>=12 mon | 0.817831 1.30 0.2537 0.57901 1.15515
<12 mont | 0.470904 1.40 0.2366 0.13530 1.63894
-------------------------------------------------------------------------------
Mantel-Haenszel estimate controlling for moslbir2
----------------------------------------------------------------
Odds Ratio chi2(1) P>chi2 [95% Conf. Interval]
----------------------------------------------------------------
0.786306 2.00 0.1568 0.563709 1.096803
----------------------------------------------------------------
Test of homogeneity of ORs (approx): chi2(1) = 0.70
Pr>chi2 = 0.4031
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\
I have 2 questions:
1) Odds ratio is less than 1 and 95% confidence interval contains
one. P value of 0.4031 also indicates insignificant results. What
would you recommend me to do in such situation to be able to still
draw some meaningful conclusions?
2) Can I draw any conclusions on measure of dose response here, or do
I need to use tabodds separately for that?
Thanks in advance.
Igor
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
