Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Recovering the discrete time (interval) baseline hazard function


From   Urmi Bhattacharya <ub3@indiana.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Recovering the discrete time (interval) baseline hazard function
Date   Tue, 26 Apr 2011 19:15:20 -0400

Dear Statalisters,

I am interested in plotting the discrete time (interval) baseline
hazard function against the discrete failure time. I am illustrating
what I have done so far.

use cancer.dta
ge id=_n
lab var id "subject identifier"
expand studytim
bysort id:ge j= _n
lab var j"spell month"

bysort id:ge dead = died==1 & _n==_N
lab var dead "binary depvar for discrete hazard model"

ta j,ge(d)
ge dur1=d1+d2+d3+d4+d5+d6
ge dur2=d7+d8+d9+d10+d11+d12
ge dur3=d13+d14+d15+d16+d17+d18
ge dur4=d19+d20+d21+d22+d23+d24
ge dur5=d25+d26+d27+d28+d28+d30
ge dur6=d31+d32+d33+d34+d35+d36+d37+d38+d39

So far the code is exactly as provided by Prof Stephen Jenkins in
(Survival Analysis with Stata: Module EC968: Part II: Lesson 6)

Then I use the cloglog model which gives the following coefficient table:


cloglog dead drug age dur1 dur2 dur3 dur4 dur5 dur6,nocons nolog

Complementary log-log regression                Number of obs     =        744
                                                                Zero
outcomes     =        713

Nonzero outcomes  =         31

                                                              Wald
chi2(8)      =     236.62
Log likelihood = -113.84096                     Prob > chi2       =     0.0000

------------------------------------------------------------------------------
        dead |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
        drug |   -1.55814   .2962569    -5.26   0.000    -2.138793   -.9774874
         age |   .0333702    .021577     1.55   0.122      -.00892    .0756604
        dur1 |  -2.732428   1.100091    -2.48   0.013    -4.888567   -.5762891
        dur2 |  -2.246698   1.067769    -2.10   0.035    -4.339487   -.1539086
        dur3 |   -2.23858   1.107324    -2.02   0.043    -4.408894   -.0682651
        dur4 |  -1.285214   1.083815    -1.19   0.236    -3.409453    .8390242
        dur5 |  -.1979354   .9196818    -0.22   0.830    -2.000479    1.604608
        dur6 |  -.5873695   1.405062    -0.42   0.676     -3.34124    2.166501
------------------------------------------------------------------------------

Now  to generate the piecewise baseline hazard function I do the following:

generate h0=-2.732428 *dur1 + -2.246698*dur2 + -2.23858*dur3 +
-1.285214*dur4 + -.1979354*dur5 + -.5873695*dur6

twoway (connect h0 j, sort msymbol(t) connect (J)),xlabel (1(1)39)

My question is if this would give me the piecewise constant baseline
discrete hazard function?

Thanks for any help in advance

Urmi Bhattacharya
*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index