st: Rosenbaum bounds

["Andreas Drichoutis" <adrihout@aua.gr>]

Dear all, 

I'm using rbounds in Stata to estimate Rosenbaum bounds. I'm having trouble
interpreting the results and I'm wondering if anyone could help me on this.
The outputs I'm getting are:

Rosenbaum bounds for delta (N = 124 matched pairs)

Gamma           sig+      sig-    t-hat+    t-hat-       CI+       CI-
----------------------------------------------------------------------
    1        .024276   .024276  -.989259  -.989259  -1.99563  -.010508  
 1.05        .013593   .041164  -1.09486  -.871538  -2.11529   .114061  
  1.1        .007438   .065004  -1.23337  -.754544  -2.23221   .223098  
 1.15        .003988   .096542  -1.34225  -.659663  -2.33022   .363695  
  1.2          .0021   .135973   -1.4584  -.572131  -2.43786   .475387  
 1.25        .001088   .182883  -1.55182  -.477338  -2.53495   .591911  
  1.3        .000556   .236304  -1.64733  -.395234  -2.64671    .70233  
 1.35         .00028   .294825  -1.72267   -.30371  -2.74657   .803875  
  1.4         .00014    .35676  -1.80649  -.200846  -2.84001   .913011  
 1.45        .000069   .420317  -1.88641  -.118181  -2.93458   1.00083  
  1.5        .000034   .483759  -1.97703  -.026009  -3.02697   1.07932  
 1.55        .000016   .545528  -2.05637   .058753  -3.10961   1.15946  
  1.6        7.8e-06   .604328  -2.13758   .123807  -3.19796   1.24323  
 1.65        3.7e-06   .659171  -2.20982   .200346  -3.27974   1.31663  

Rosenbaum bounds for delta5 (N = 124 matched pairs)

Gamma           sig+      sig-    t-hat+    t-hat-       CI+       CI-
----------------------------------------------------------------------
    1         .15746    .15746    .16711    .16711  -.207092   .559691  
 1.05        .220799   .107302   .127509   .207875   -.26072    .59591  
  1.1         .29273   .071221    .08576   .248338  -.302407   .634022  
 1.15        .370097   .046167   .058032   .301428  -.342646   .667442  
  1.2        .449461   .029296   .019351   .351714   -.37594   .708266  
 1.25        .527562   .018239  -.015399   .393774  -.414271   .747596  
  1.3        .601658    .01116  -.053361   .434011  -.447165   .792062  
 1.35        .669711   .006724  -.087199    .46632  -.489421   .846049  
  1.4        .730438   .003994  -.127532   .503433  -.516807    .88467  
 1.45        .783248   .002343  -.161377   .525761  -.557254   .923198  
  1.5        .828124   .001358  -.200148   .555109  -.583892   .950405  
 1.55        .865472   .000779  -.235254   .575835  -.625121   .975681  
  1.6        .895976   .000443  -.266339   .603737  -.655814   1.00472  
 1.65        .920469   .000249  -.295253   .626526  -.704532   1.02704  

* gamma  - log odds of differential assignment due to unobserved factors
  sig+   - upper bound significance level
  sig-   - lower bound significance level
  t-hat+ - upper bound Hodges-Lehmann point estimate
  t-hat- - lower bound Hodges-Lehmann point estimate
  CI+    - upper bound confidence interval (a=  .95)
  CI-    - lower bound confidence interval (a=  .95)

Regards,

Andreas Drichoutis


*
*   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/