st: bootstrapping reps don't match

["Jeannette Wicks-Lim" <janetlim@econs.umass.edu>]

Hi,

I'm trying to get bootstrapped SEs using 1000 reps for my quantile 
regression estimates, but when I get the output it appears that for some 
coefficients the bootstrapped SEs are based on fewer than 1000 (996 to be 
exact) while others _are_ based on 1000. Why would the number of reps vary 
for a given run? Any info would be greatly appreciated!

The command I used and the output is appended below:

version 7: bs "qreg lnrwage repeal labcon after5  lconafter5 repafter5 
lconrep lconrepon5 if ((bc==1 & con~=1) | labcon==1) [aweight=earnwt], 
quantile(.25)"
"_b[repeal] _b[labcon] _b[after5] _b[lconafter5] _b[repafter5] _b[lconrep] 
_b[lconrepon5]", reps(1000) dots cluster(state);

command:     qreg lnrwage repeal labcon after5  lconafter5 repafter5 lconrep 
lconrepon5 if ((bc==1 & con~=1) | labcon==1) [aweight=earnwt], quantile(.25)
statistics:  _b[repeal] _b[labcon] _b[after5] _b[lconafter5] _b[repafter5] 
_b[lconrep] _b[lconrepon5]
(clusters=37)


Bootstrap statistics

Variable |   Reps   Observed       Bias   Std. Err.   [95% Conf. Interval]
---------+-------------------------------------------------------------------
    bs1 |    996  -.0088742  -.0010679   .0357292   -.0789874  .0612391 
(N)
        |                                           -.0773206   .065186 
(P)
        |                                           -.0736758  .0700037 
(BC)
---------+-------------------------------------------------------------------
    bs2 |   1000  -.0139583   .0030501   .0180475   -.0493737  .0214571 
(N)
        |                                           -.0422667  .0294387 
(P)
        |                                           -.0433663  .0254573 
(BC)
---------+-------------------------------------------------------------------
    bs3 |   1000  -.0542786  -.0063605   .0174601   -.0885412  -.020016 
(N)
        |                                           -.0894208  -.024021 
(P)
        |                                           -.0802566 -.0093782 
(BC)
---------+-------------------------------------------------------------------
    bs4 |   1000  -.0120196   .0072499   .0229287   -.0570137  .0329744 
(N)
        |                                           -.0491159  .0423729 
(P)
        |                                           -.0621785  .0286664 
(BC)
---------+-------------------------------------------------------------------
    bs5 |    996  -.0552994   .0130774   .0522246   -.1577824  .0471836 
(N)
        |                                           -.1127735  .0867525 
(P)
        |                                           -.1220639  .0609865 
(BC)
---------+-------------------------------------------------------------------
    bs6 |    996  -.0482843  -.0047492   .0543789   -.1549948  .0584262 
(N)
        |                                           -.1467928   .061617 
(P)
        |                                           -.1405596  .0730383 
(BC)
---------+-------------------------------------------------------------------
    bs7 |    996   .0206529   .0078368   .0569606   -.0911238  .1324296 
(N)
        |                                           -.0858363  .1387922 
(P)
        |                                            -.123576  .1232235 
(BC)
-----------------------------------------------------------------------------
                             N = normal, P = percentile, BC = 
bias-corrected

Jeannette Wicks-Lim
Department of Economics
University of Massachusetts, Amherst
(413) 577-0820 
*
*   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/