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

From |
Inna Becher <inna.becher@uni-konstanz.de> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: implementation of variance formula |

Date |
Fri, 13 Mar 2009 10:16:54 +0100 |

Best regards, Inna Robert A Yaffee schrieb:

Inna, You should do about 10000 replications. If I remember correctly, that is what Efron suggested. You could estimate the mean of the varianceor the variance itself, each time you resample. I like the percentile method,myself. It assumes an unbiased sample, but it will not work with smallsamples. If you know the distribution, you can do a bias correction. - Bob Robert A. Yaffee, Ph.D. Research Professor Silver School of Social Work New York University Biosketch: http://homepages.nyu.edu/~ray1/Biosketch2008.pdf CV: http://homepages.nyu.edu/~ray1/vita.pdf ----- Original Message ----- From: Inna Becher <inna.becher@uni-konstanz.de> Date: Thursday, March 12, 2009 10:27 am Subject: Re: st: implementation of variance formula To: statalist@hsphsun2.harvard.eduThank you, Robert. Are there two way of variance estimation: 1)H-T-variance-estimation for each of 1000 replications and then mean ofthis variances as estimation of population variance and 2) H-T-meanforeach replication and a bootstrap-estimation of variance? Is there atheoretical difference between these two ways?Robert A Yaffee schrieb:Inna, That could be an alternative to the H-T variance estimator. - Bob Robert A. Yaffee, Ph.D. Research Professor Silver School of Social Work New York University Biosketch: http://homepages.nyu.edu/~ray1/Biosketch2008.pdf CV: http://homepages.nyu.edu/~ray1/vita.pdf ----- Original Message ----- From: Inna Becher <inna.becher@uni-konstanz.de> Date: Thursday, March 12, 2009 4:38 am Subject: Re: st: implementation of variance formula To: statalist@hsphsun2.harvard.eduRobert,I simulate 1000 samples from a population and for each sample Icalculate the H-T-estimator for the mean and I have to calculatethevariance for the H-T-mean. Afterwards I'll investigate theirdistribution over 1000 samples.Robert A Yaffee schrieb:Inna, Can you jacknife or bootstrap to obtain your variances? - Bob Robert A. Yaffee, Ph.D. Research Professor Silver School of Social Work New York University Biosketch: http://homepages.nyu.edu/~ray1/Biosketch2008.pdf CV: http://homepages.nyu.edu/~ray1/vita.pdf ----- Original Message ----- From: Inna Becher <inna.becher@uni-konstanz.de> Date: Wednesday, March 11, 2009 4:50 am Subject: Re: st: implementation of variance formula To: statalist@hsphsun2.harvard.eduI can calculate the probability for each network (=cluster) to beincluded in the sample. I also cancalculate for each pair of selected clusters to be included inthesample. My problem is: this probabilities are to be savedsomewhere.Should it be a matrix? I have not yet worked with matrices tocalculatevariances. The version of H-T-estimator I need is not implementedin svy-.I wrote an ado for sampling design that I need and implementedH-T-estimator for the mean, but not for the variance.Steven Samuels schrieb:Inna:You don't say which version of the H-T estimator you want; therearemany versions. The estimates themselves depend on knowing foreachcluster the probability that would be included in the sample.Thisquantity must be supplied with the data set. It might or mightnotbea simple function of the cluster "size" measure.Thel formulas for the variance of the classical H-T estimatorsarealso functions of the probability that each pair of selectedclusterswould be included in the sample; if there are m clusters in astratum,there are m(m-1)/2 of these probabilities. Were theysuppliedwith the data set? Even if you have them, you would still havetowrite your own (probably MATA) code to utilize them.There is an alternative. Stata's survey commands producemodifiedH-T estimates . You can obtain appropriate standard errors ifyou-syset- your data according to the design.On Mar 10, 2009, at 7:07 AM, Inna Becher wrote:Dear statalisters,I have to implement a formula of the variance of modifiedhorvitz-thompson-estimator. My dataset is very large, so Icannotproduce a lot of new variables in order to do that. Should Iusemata? Are there any examples of implementing variance formulasinstata?* * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/* * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/* * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**References**:**st: implementation of variance formula***From:*Inna Becher <inna.becher@uni-konstanz.de>

**Re: st: implementation of variance formula***From:*Steven Samuels <sjhsamuels@earthlink.net>

**Re: st: implementation of variance formula***From:*Inna Becher <inna.becher@uni-konstanz.de>

**Re: st: implementation of variance formula***From:*Robert A Yaffee <bob.yaffee@nyu.edu>

**Re: st: implementation of variance formula***From:*Inna Becher <inna.becher@uni-konstanz.de>

**Re: st: implementation of variance formula***From:*Robert A Yaffee <bob.yaffee@nyu.edu>

**Re: st: implementation of variance formula***From:*Inna Becher <inna.becher@uni-konstanz.de>

**Re: st: implementation of variance formula***From:*Robert A Yaffee <bob.yaffee@nyu.edu>

- Prev by Date:
**RE: st: Bivariate Negative Binomial using -ml-** - Next by Date:
**Re: st: Does -insheet- read data incorrectly?** - Previous by thread:
**Re: st: implementation of variance formula** - Next by thread:
**Re: st: implementation of variance formula** - Index(es):

© Copyright 1996–2015 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |