Applying bootstrapped regression coefficients to orginal dataset

[jeweetwel]

Dear list,
To internally validate a predicting model I have performed bootstrapping method (200 iterations) with generated logistic regression coefficients saved as spss data file. This file contains four columns. Each column belongs to the same variable. Each row of the column represents each bootstrap cycle.
The next step is to apply each of the calculated regression coefficients (bootstrap sample starting from 1 to 200) to the original data set using i.e. compute logit= constant + B1*var1 + B2*var2 etc.
Is it possible to achieve this with syntax or macro?
thanks in advance

[SR Millis-3]

Frank Harrell has developed a set of routines that perform the bootstrap along with providing summary statistics and graphs.  His programs are available in the free, open source R statistical package.  Harrell's book, Regression Modeling Strategies, shows you how to implement the programs.


Scott R Millis, PhD, ABPP (CN,CL,RP), CStat, CSci
Professor & Director of Research
Dept of Physical Medicine & Rehabilitation
Associate - Dept of Emergency Medicine

Wayne State University School of Medicine
261 Mack Blvd
Detroit, MI 48201
Email:  [hidden email]
Tel: [phone]
Fax: [phone]


--- On Sun, 3/22/09, jeweetwel <[hidden email]> wrote:

> From: jeweetwel <[hidden email]>
> Subject: Applying bootstrapped regression coefficients to orginal dataset
> To: [hidden email]
> Date: Sunday, March 22, 2009, 4:11 PM
> Dear list,
> To internally validate a predicting model I have performed
> bootstrapping
> method (200 iterations) with generated logistic regression
> coefficients
> saved as spss data file. This file contains four columns.
> Each column
> belongs to the same variable. Each row of the column
> represents each
> bootstrap cycle.
> The next step is to apply each of the calculated regression
> coefficients
> (bootstrap sample starting from 1 to 200) to the original
> data set using
> i.e. compute logit= constant + B1*var1 + B2*var2 etc.
> Is it possible to achieve this with syntax or macro?
> thanks in advance
> --
> View this message in context:
> http://www.nabble.com/Applying-bootstrapped-regression-coefficients-to-orginal-dataset-tp22650031p22650031.html
> Sent from the SPSSX Discussion mailing list archive at
> Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> [hidden email] (not to SPSSX-L), with no body
> text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the
> command
> INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD