Date:         Mon, 27 Feb 2012 08:09:55 -0800
Reply-To:     David Marso <david.marso@gmail.com>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         David Marso <david.marso@gmail.com>
Subject:      Re: Influence Analysis
In-Reply-To:  <1330331088856-5518256.post@n5.nabble.com>
Content-Type: text/plain; charset=us-ascii

See REGRESSION and GLM.
For the Hat matrix defined as X*INV(X'X)*X' you can use the MATRIX language.
data list /Y X1 to x9 (10F1).
begin data
6246524526
7467677375
8628634856
7365786578
3675836578
3656375676
7823653265
8726785623
7562378562
3876586587
2658365638
5623756782
3657835432
END DATA.
REGRESSION /DEP Y /METHOD ENTER X1 TO X9 / SAVE SDRESID COOK.
MATRIX .
GET Y / VAR Y.
GET X / VAR X1 TO X9.
COMPUTE HAT=X*GINV(T(X)*X)*T(X).
COMPUTE HAT2=X*GINV(X).
PRINT HAT.
PRINT HAT2.
END MATRIX.

Kgomotso Mahole wrote
>
> where in IBM SPSS Statistics 20 can i go to to perform a hat matrix,
> studentized deleted residuals and cook's distance statistic?
>


--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Influence-Analysis-tp5518256p5519376.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
LISTSERV@LISTSERV.UGA.EDU (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