Hi Stata users,
I am a new user of Stata and I am doing a project on squamous cell cancer and smoking habits in the construction workers cohort in Sweden.
I have been trying to do Poisson regression with the xi command, but it has been giving me some trouble. 2 questions have arisen:
1. What is wrong with the xi3 command? I saw on stata list that someone had noticed in february that there is something wrong with it but I never found a good answer. He had the same problem as I have had. Command:
xi: poisson outcome i.variable1*i.varable2*i.variable3, exposure(….
Stata output: varlist not allowed
2. When I use xi with multiple interaction terms, stata tells me he is dropping a bunch of variables due to collinearity, but then it looks like he has not dropped them at all (please see stata output below). But if I then put xi3 in front of the command stata does not say he is dropping any variables and the results are exactly the same!!
. xi: poisson scc i.smokcatn*i.ageband i.smokcatn*i.tertbmi i.tertbmi*i.ageban
> d, e(time_ageband) irr
i.smokcatn _Ismokcatn_1-3 (naturally coded; _Ismokcatn_1 omitted)
i.ageband _Iageband_10-60 (naturally coded; _Iageband_60 omitted)
i.smo~n*i.age~d _IsmoXage_#_# (coded as above)
i.tertbmi _Itertbmi_0-2 (naturally coded; _Itertbmi_0 omitted)
i.smo~n*i.ter~i _IsmoXter_#_# (coded as above)
i.ter~i*i.age~d _IterXage_#_# (coded as above)
note: _Ismokcatn_2 dropped due to collinearity
note: _Ismokcatn_3 dropped due to collinearity
note: _Itertbmi_1 dropped due to collinearity
note: _Itertbmi_2 dropped due to collinearity
note: _Iageband_10 dropped due to collinearity
note: _Iageband_50 dropped due to collinearity
Iteration 0: log likelihood = -3081.9574
Iteration 1: log likelihood = -2975.207
Iteration 2: log likelihood = -2939.4822
Iteration 3: log likelihood = -2936.4882
Iteration 4: log likelihood = -2936.4841
Iteration 5: log likelihood = -2936.4841
Poisson regression Number of obs = 450957
LR chi2(18) = 956.28
Prob > chi2 = 0.0000
Log likelihood = -2936.4841 Pseudo R2 = 0.1400
scc IRR Std. Err. z P>z [95% Conf. Interval]
_Ismokcatn_2 .6198224 .2198933 -1.35 0.178 .3092346 1.242357
_Ismokcatn_3 .9058287 .2208259 -0.41 0.685 .5617427 1.460679
_Iageband_10 .0094563 .004177 -10.55 0.000 .0039786 .0224753
_Iageband_50 .1100253 .0389725 -6.23 0.000 .0549521 .2202927
_IsmoXa~2_10 5.435618 3.145965 2.93 0.003 1.748237 16.90043
_IsmoXa~2_50 1.192367 .4748936 0.44 0.659 .5462543 2.602704
_IsmoXa~3_10 2.043416 1.086089 1.34 0.179 .7210039 5.791301
_IsmoXa~3_50 1.871118 .5963836 1.97 0.049 1.001836 3.494666
_Itertbmi_1 .8919676 .2137564 -0.48 0.633 .5576505 1.426711
_Itertbmi_2 .7871886 .1790034 -1.05 0.293 .5041028 1.229245
_IsmoXte~2_1 1.420636 .5827945 0.86 0.392 .6357558 3.174501
_IsmoXte~2_2 1.275247 .4983443 0.62 0.534 .5928705 2.74302
_IsmoXte~3_1 .8762735 .2716256 -0.43 0.670 .4772938 1.608768
_IsmoXte~3_2 .8243317 .244574 -0.65 0.515 .4608461 1.474511
_IterXa~1_10 .535335 .2989043 -1.12 0.263 .179208 1.599168
_IterXa~1_50 .7190481 .2815366 -0.84 0.400 .3337935 1.548952
_IterXa~2_10 .8560323 .4791763 -0.28 0.781 .2857708 2.564262
_IterXa~2_50 1.616486 .5536023 1.40 0.161 .8261498 3.162898
time_ageband (exposure)
. xi3: poisson scc i.smokcatn*i.ageband i.smokcatn*i.tertbmi i.tertbmi*i.ageba
> nd, e(time_ageband) irr
i.smokcatn _Ismokcatn_1-3 (naturally coded; _Ismokcatn_1 omitted)
i.ageband _Iageband_10-60 (naturally coded; _Iageband_60 omitted)
i.tertbmi _Itertbmi_0-2 (naturally coded; _Itertbmi_0 omitted)
Iteration 0: log likelihood = -3081.9574
Iteration 1: log likelihood = -2975.207
Iteration 2: log likelihood = -2939.4822
Iteration 3: log likelihood = -2936.4882
Iteration 4: log likelihood = -2936.4841
Iteration 5: log likelihood = -2936.4841
Poisson regression Number of obs = 450957
LR chi2(18) = 956.28
Prob > chi2 = 0.0000
Log likelihood = -2936.4841 Pseudo R2 = 0.1400
scc IRR Std. Err. z P>z [95% Conf. Interval]
_Ismokcatn_2 .6198224 .2198933 -1.35 0.178 .3092346 1.242357
_Ismokcatn_3 .9058287 .2208259 -0.41 0.685 .5617427 1.460679
_Iageband_10 .0094563 .004177 -10.55 0.000 .0039786 .0224753
_Iageband_50 .1100253 .0389725 -6.23 0.000 .0549521 .2202927
_Ism2Xag10 5.435618 3.145965 2.93 0.003 1.748237 16.90043
_Ism2Xag50 1.192367 .4748936 0.44 0.659 .5462543 2.602704
_Ism3Xag10 2.043416 1.086089 1.34 0.179 .7210039 5.791301
_Ism3Xag50 1.871118 .5963836 1.97 0.049 1.001836 3.494666
_Itertbmi_1 .8919676 .2137564 -0.48 0.633 .5576505 1.426711
_Itertbmi_2 .7871886 .1790034 -1.05 0.293 .5041028 1.229245
_Ism2Xte1 1.420636 .5827945 0.86 0.392 .6357558 3.174501
_Ism2Xte2 1.275247 .4983443 0.62 0.534 .5928705 2.74302
_Ism3Xte1 .8762735 .2716256 -0.43 0.670 .4772938 1.608768
_Ism3Xte2 .8243317 .244574 -0.65 0.515 .4608461 1.474511
_Ite1Xag10 .535335 .2989043 -1.12 0.263 .179208 1.599168
_Ite1Xag50 .7190481 .2815366 -0.84 0.400 .3337935 1.548952
_Ite2Xag10 .8560323 .4791763 -0.28 0.781 .2857708 2.564262
_Ite2Xag50 1.616486 .5536023 1.40 0.161 .8261498 3.162898
time_ageband (exposure)
Grateful for help!
Regards Åsa Odenbro
Department for Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden.
[email protected]
*
* 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/
