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 on April 23, and its replacement, is already up and running.

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

st: Re: jackknifing and loop question [was: <meaningless title>]

From   Nick Cox <>
To   "" <>
Subject   st: Re: jackknifing and loop question [was: <meaningless title>]
Date   Tue, 12 Mar 2013 20:06:49 +0000

I was guessing at 10 provinces. Dieter is from South Africa, and I
just checked. It may well be the 9 provinces of South Africa he is
thinking of. Each province is either in or out of the equation, so
that is 2^9 = 512 possible equations. It is doable, but they are not

-tuples- (SSC) might help.


On Tue, Mar 12, 2013 at 4:00 PM, Nick Cox <> wrote:
> You have to think about a loop. The analogy with jackknifing here is far too
> tenuous to be pertinent to your programming.
> But before you think about a loop, have you done the combinatorics here? For
> 10 provinces, I count about 1000 regressions, and naturally they are highly
> dependent.
> Nick
> On 12 Mar 2013, at 15:36, "Von Fintel, Dieter <>"
> <> wrote:
>> I have a question about delete k jackknife estimation. However, I would
>> like to delete k groups at a time, rather than k observations.
>> Basically I want to run a regression of the type:
>> reg y  i.province othercontrols
>> I then want to leave out all combinations of 1 province (with a dataset
>> saving coefficients).
>> Then I want to leave out all combinations of 2 provinces, all combinations
>> of 3 provinces, etc
>> Up to this point,  all that I see would be possible is all combinations of
>> deleting 1 observation at a time, or deleting 1 cluster at a time. I could
>> define province as my cluster, but this will still only leave out one at a
>> time. Other than writing a loop, is there any way that you know of how I
>> could use the jackknife command to achieve this.
*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index