Thanks for your help Nick. Yes, both are up-to-date.
Nick Cox wrote:
Thanks. My experiments indicate that neither the number of predictors
nor the length of their names
are problematic here, at least with Stata/SE. I can't see what the
problem is. Are your Stata executable and ados both fully
up-to-date?
Nick [email protected]
Rubiana Chamarbagwala
The exact syntax I used was:
bootstrap "dprobit ftptw p_rate m_rate year88 year93 year99 hhchild
f_primary f_middle f_high f_college m_primary m_middle m_high m_college
workmom lnpced asset age agesq urban lowcaste muslim season2 season3
season4 male p_rate_male m_rate_male year88_male year93_male year99_male
hhchild_male f_primary_male f_middle_male f_high_male f_college_male
m_primary_male m_middle_male m_high_male m_college_male workmom_male
lnpced_male asset_male age_male agesq_male urban_male lowcaste_male
muslim_male season2_male season3_male season4_male state1 state2
state3 state4
state5 state6 state7 state8 state9 state10 state11 state12 state13
state14 state15 state16 state17 state18 state19 state20 state21
state22 state23 state24 state25 state26
state27 state28 state30 state31" "_b[p_rate] _b[m_rate]
_b[p_rate_male] _b[m_rate_male]", reps(1000) cluster(year_state)
Nick Cox wrote:
If you did in fact type
...
as part of your command then that is invalid syntax. If you didn't
type that, then the same comment applies: we need to see _exactly_
what you typed.
Nick [email protected]
Rubiana Chamarbagwala
Nick - thanks for the information. Here is the syntax I used.
(1) bootstrap "dprobit y x1 x2 x3 x4 x5" "_b[x1] _b[x2]",
reps(1000)
cluster(x6) -- this worked.
(2) bootstrap "dprobit y x1 x2 x3 x4 x5 x7 x8 x9 x10 ...
x50" "_b[x1]
_b[x2]", reps(1000) cluster(x6) -- this returned "invalid syntax".
The variables in (2) above include dummies and interctions with
dummies.
Nick Cox wrote:
-whelp limits- indicates various limits.
It is always worth including examples of the invalid syntax you used.
I doubt that the explanation of your problem lies in the direction
you are looking. The error message you got would be normally be
produced well before trying to apply the -regress-
command. However, without indications of what you actually typed
it is difficult to help further.
Nick [email protected]
Rubiana Chamarbagwala
Hi - I am trying to estimate a probit model with lots of
independent
variables and estimate bootstrapped standard errors for 4
variables.
Stata keeps returning "invalid syntax" when I include all the
independent variables. However, when I include only a few
variables, it works. Does anyone know whether or not there is a
limit to the number of variables one can include in a regression
when one uses the bootstrap command?
*
* 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/
