When using the Heckman selection model with the O-B decomposition for whether an individual is disabled or not (DIS =1 or = 0, respectively), i.e:

Code:
 oaxaca logGRSSWK $wageeq, by(DIS) model1(heckman, twostep select($seleq))
model2(heckman, twostep select($seleq)) weight(1) noisily relax
the output for heckman models 1 and 2, as well as the O-B decomposition, are all displayed.

However, when delving into disability, assessing its extent (DISTYPE =1 if work-limited disabled, 2 if daily activity-limited disabled, 4 = non-disabled), i.e:
Code:
 oaxaca logGRSSWK $wageeq if inlist(DISTYPE,1,4), by(DISTYPE) model1(heckman, twostep select($seleq))
model2(heckman, twostep select($seleq)) weight(0) relax
only the O-B output is displayed.

I wish to assess the correction using Heckman regarding lambda but without the output tables I am unsure if I can.

I initially thought it may be due to small sample size, i.e:

HTML Code:
tab DISTYPE if logGRSSWK != .

   RECODE of |
      DISEXT |      Freq.     Percent        Cum.
-------------+-----------------------------------
         WLD |        122        9.45        9.45
        DALD |         94        7.28       16.73
Non-disabled |      1,075       83.27      100.00
-------------+-----------------------------------
       Total |      1,291      100.00
But the coefficients have changed using heckman, so I do believe it is being used but I am unsure why it is not being displayed in the latter's case?

Any help regarding this issue would be greatly appreciated, many thanks.