Posted by
Ornelas, Fermin on
Mar 06, 2007; 4:33pm
URL: http://spssx-discussion.165.s1.nabble.com/SPSS-warning-from-regression-tp1074315p1074319.html
In theory when building a statistical model, prior to undertaking the
actual estimation one must carry out some exploratory analysis to ensure
the integrity of the data. That is things like what percentage of values
for each variable are missing, what are the range values for the
predictors, are the values consistent with a priori considerations
derived either from personal experience or past research studies. Some
correlation analysis between the response variable and the predictors
could give a hint on what to expect from the final estimation.
Once one is satisfied and verified some of the exploratory analysis then
it is time to do the actual estimation. Doing those preliminary steps
will limit the possibility of getting non sense results. Furthermore,
once the final model is obtained one must verify that certain model
assumptions are met such as normality, constant variance, independence,
an outliers. If the model passes those filters then one still has to
consider things such as parameter significance, signs expectations for
the parameter estimates, R^2, etc.
Fermin Ornelas, Ph.D.
Management Analyst III, AZ DES
Tel: (602) 542-5639
E-mail:
[hidden email]
-----Original Message-----
From: Hector Maletta [mailto:
[hidden email]]
Sent: Tuesday, March 06, 2007 8:19 AM
To: Ornelas, Fermin;
[hidden email]
Subject: RE: SPSS warning from regression
This is not exactly a case of "not finding the dependent
variable"
or "one of the dependent variables having missing values". The problem
is
that any case for which at least one variable in the equation (dependent
or
independent) has a missing value is excluded from the analysis. If all
the
cases have a missing value for at least one of the relevant variables,
then
all cases were be excluded and there would be no cases left for the
analysis; in such a situation SPSS reports there are no valid cases
found
and no equation can be built.
Facing such plight, you should analyze the pattern of missing
values. If it is mainly the responsibility of one specific variable,
excluding that variable from the analysis may be enough to leave you
with
enough cases, though perhaps that variable may be essential to your
theoretical pursuit. Another approach is imputation of values (e.g.
using
regression, as in the SPSS Missing Values module) in order to have valid
(albeit not really observed) values for all variables and cases, though
this
approach may be disputable if applied indiscriminately. One should also
analyze whether the missing values are distributed randomly or following
some pattern.
Hector
-----Mensaje original-----
De: SPSSX(r) Discussion [mailto:
[hidden email]] En nombre de
Ornelas, Fermin
Enviado el: 06 March 2007 16:08
Para:
[hidden email]
Asunto: Re: SPSS warning from regression
This is telling you that for some reason SPSS is not finding the
dependent variable. Therefore it reports it to you as missing
and
does
nothing on the regression equation.
I actually find frustrating trying to learn SPSS.
Fermin Ornelas, Ph.D.
Management Analyst III, AZ DES
Tel: (602) 542-5639
E-mail:
[hidden email]
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On
Behalf Of
Nivruti Hinge
Sent: Monday, March 05, 2007 9:40 PM
To:
[hidden email]
Subject: Re: SPSS warning from regression
One of the dependent variable must be having many missing values
so
please
check for the missing values in the dependent variable list.
-Regards,
Nivruti Hinge
Senior Member Of Technical Staff
Persistent Systems Pvt. Ltd.
http://www.persistentsys.com Direct : +91 (20) 30235627
________________________________________________________________________
____
_______________
Persistent Systems - Software Development Partner for
Competitive
Advantage.
Persistent Systems provides custom software product development
services.
With over 15 years, 140 customers, and 700 release cycles
experience, we
deliver unmatched value of higher quality, faster time to market
and
lowe
total costs.
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On
Behalf Of
Yifan Lu
Sent: Tuesday, March 06, 2007 4:20 AM
To:
[hidden email]
Subject: SPSS warning from regression
Dear list,
I am running multiple regression, but SPSS keeps telling me:
Warnings
There are no valid cases for models with dependent variable
alldays.
Statistics cannot be computed.
No valid cases found. Equation-building skipped.
I checked the data and it seems all right. I also ran
descriptives
and
the results come out right. Anybody also had such problem
before?
Any
suggestions to fix the problem? Thank you!
Regards,
Yifan Lu
DISCLAIMER
==========
This e-mail may contain privileged and confidential information
which is
the property of Persistent Systems Pvt. Ltd. It is intended only
for
the
use of the individual or entity to which it is addressed. If you
are
not
the intended recipient, you are not authorized to read, retain,
copy,
print, distribute or use this message. If you have received this
communication in error, please notify the sender and delete all
copies
of this message. Persistent Systems Pvt. Ltd. does not accept
any
liability for virus infected mails.
NOTICE: This e-mail (and any attachments) may contain PRIVILEGED
OR
CONFIDENTIAL information and is intended only for the use of the
specific individual(s) to whom it is addressed. It may contain
information that is privileged and confidential under state and
federal
law. This information may be used or disclosed only in
accordance
with
law, and you may be subject to penalties under law for improper
use
or
further disclosure of the information in this e-mail and its
attachments. If you have received this e-mail in error, please
immediately notify the person named above by reply e-mail, and
then
delete the original e-mail. Thank you.