Logistic Regression

[Mary-33]

Logistic Regression.

I am trying to build a regression model of 'levels of agreement'. My
dependent variable is dichotomous consisting of two categories - agree and
disagree. I have however uneven numbers in each cell.

 My question is as follows:

1.Is it important assumption to have relatively even numbers of subjects in
each category.


Perhaps someone could recommend a reference that covers these questions?

Thanks in advance,

Mary

[Pirritano, Matthew]

For Logistic regression I've found that there ain't nothing better than
"Applied Logistic Regression Analysis 2nd Ed" by Scott Menard. It's one
of those little Sage books in the Quantitative Applications in the
Social Sciences Series. I just bought it online.

Matthew Pirritano, Ph.D.
Assistant Professor of Psychology
Smith Hall 116C
Chapman University
Department of Psychology
One University Drive
Orange, CA 92866
Telephone [phone]
FAX [phone]

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Mary
Sent: Monday, April 23, 2007 9:02 AM
To: [hidden email]
Subject: Logistic Regression

Logistic Regression.

I am trying to build a regression model of 'levels of agreement'. My
dependent variable is dichotomous consisting of two categories - agree
and
disagree. I have however uneven numbers in each cell.

 My question is as follows:

1.Is it important assumption to have relatively even numbers of subjects
in
each category.


Perhaps someone could recommend a reference that covers these questions?

Thanks in advance,

Mary

[Ornelas, Fermin]

I am not sure what you mean by this I assume that the count on binary
variable is not evenly distributed. But if that were the case it would
not matter.

Fermin Ornelas, Ph.D.
Management Analyst III, AZ DES
Tel: [phone]
E-mail: [hidden email]

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Mary
Sent: Monday, April 23, 2007 9:02 AM
To: [hidden email]
Subject: Logistic Regression

Logistic Regression.

I am trying to build a regression model of 'levels of agreement'. My
dependent variable is dichotomous consisting of two categories - agree
and
disagree. I have however uneven numbers in each cell.

 My question is as follows:

1.Is it important assumption to have relatively even numbers of subjects

in
each category.


Perhaps someone could recommend a reference that covers these questions?

Thanks in advance,

Mary

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.

[Ornelas, Fermin]

There are a couple of books written for SAS that do very decent job on
the subject. The names escape my mind but if you go to the SAS site you
will find it. Green is also a good source for this.

Fermin Ornelas, Ph.D.
Management Analyst III, AZ DES
Tel: [phone]
E-mail: [hidden email]


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Pirritano, Matthew
Sent: Monday, April 23, 2007 10:21 AM
To: [hidden email]
Subject: Re: Logistic Regression

For Logistic regression I've found that there ain't nothing better than
"Applied Logistic Regression Analysis 2nd Ed" by Scott Menard. It's one
of those little Sage books in the Quantitative Applications in the
Social Sciences Series. I just bought it online.

Matthew Pirritano, Ph.D.
Assistant Professor of Psychology
Smith Hall 116C
Chapman University
Department of Psychology
One University Drive
Orange, CA 92866
Telephone [phone]
FAX [phone]

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Mary
Sent: Monday, April 23, 2007 9:02 AM
To: [hidden email]
Subject: Logistic Regression

Logistic Regression.

I am trying to build a regression model of 'levels of agreement'. My
dependent variable is dichotomous consisting of two categories - agree
and
disagree. I have however uneven numbers in each cell.

 My question is as follows:

1.Is it important assumption to have relatively even numbers of subjects
in
each category.


Perhaps someone could recommend a reference that covers these questions?

Thanks in advance,

Mary

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.

[Ornelas, Fermin]

I almost forgot that when the count in one of the outcomes of the event
is too low you may have to come up with some kind of weight for the
observations whose count is low. It is also likely that you will not
find much discussion on this in a formal textbook.

Fermin Ornelas, Ph.D.
Management Analyst III, AZ DES
Tel: [phone]
E-mail: [hidden email]


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Mary
Sent: Monday, April 23, 2007 9:02 AM
To: [hidden email]
Subject: Logistic Regression

Logistic Regression.

I am trying to build a regression model of 'levels of agreement'. My
dependent variable is dichotomous consisting of two categories - agree
and
disagree. I have however uneven numbers in each cell.

 My question is as follows:

1.Is it important assumption to have relatively even numbers of subjects

in
each category.


Perhaps someone could recommend a reference that covers these questions?

Thanks in advance,

Mary

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.

[Mark A Davenport MADAVENP]

IMHO Hosmer and Lemeshow is the sacred text of logistic regression.  If
you are using SAS, I would suggest you read the David Schlotzhauer
article:

Some Issues in Using the LOGISTIC Procedure for Binary Losgistic
Regression

You can find it here.

http://www.ats.ucla.edu/stat/sas/library/ts274.pdf

***************************************************************************************************************************************************************
Mark A. Davenport Ph.D.
Senior Research Analyst
Office of Institutional Research
The University of North Carolina at Greensboro
336.256.0395
[hidden email]

'An approximate answer to the right question is worth a good deal more
than an exact answer to an approximate question.' --a paraphrase of J. W.
Tukey (1962)






"Ornelas, Fermin" <[hidden email]>
Sent by: "SPSSX(r) Discussion" <[hidden email]>
04/23/2007 02:24 PM
Please respond to
"Ornelas, Fermin" <[hidden email]>


To
[hidden email]
cc

Subject
Re: Logistic Regression






There are a couple of books written for SAS that do very decent job on
the subject. The names escape my mind but if you go to the SAS site you
will find it. Green is also a good source for this.

Fermin Ornelas, Ph.D.
Management Analyst III, AZ DES
Tel: [phone]
E-mail: [hidden email]


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Pirritano, Matthew
Sent: Monday, April 23, 2007 10:21 AM
To: [hidden email]
Subject: Re: Logistic Regression

For Logistic regression I've found that there ain't nothing better than
"Applied Logistic Regression Analysis 2nd Ed" by Scott Menard. It's one
of those little Sage books in the Quantitative Applications in the
Social Sciences Series. I just bought it online.

Matthew Pirritano, Ph.D.
Assistant Professor of Psychology
Smith Hall 116C
Chapman University
Department of Psychology
One University Drive
Orange, CA 92866
Telephone [phone]
FAX [phone]

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Mary
Sent: Monday, April 23, 2007 9:02 AM
To: [hidden email]
Subject: Logistic Regression

Logistic Regression.

I am trying to build a regression model of 'levels of agreement'. My
dependent variable is dichotomous consisting of two categories - agree
and
disagree. I have however uneven numbers in each cell.

 My question is as follows:

1.Is it important assumption to have relatively even numbers of subjects
in
each category.


Perhaps someone could recommend a reference that covers these questions?

Thanks in advance,

Mary

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.

[Ornelas, Fermin]

Yes, I could not remember the name. The other book is by Paul...
Now that you have given the UCLA site there are several textbooks at
that site including Applied Linear Regression with SAS code on how to
run logistic regression. Excellent site I go often there.

Fermin Ornelas, Ph.D.
Management Analyst III, AZ DES
Tel: [phone]
E-mail: [hidden email]


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Mark A Davenport MADAVENP
Sent: Monday, April 23, 2007 11:46 AM
To: [hidden email]
Subject: Re: Logistic Regression

IMHO Hosmer and Lemeshow is the sacred text of logistic regression.  If
you are using SAS, I would suggest you read the David Schlotzhauer
article:

Some Issues in Using the LOGISTIC Procedure for Binary Losgistic
Regression

You can find it here.

http://www.ats.ucla.edu/stat/sas/library/ts274.pdf

************************************************************************
************************************************************************
***************
Mark A. Davenport Ph.D.
Senior Research Analyst
Office of Institutional Research
The University of North Carolina at Greensboro
336.256.0395
[hidden email]

'An approximate answer to the right question is worth a good deal more
than an exact answer to an approximate question.' --a paraphrase of J.
W.
Tukey (1962)






"Ornelas, Fermin" <[hidden email]>
Sent by: "SPSSX(r) Discussion" <[hidden email]>
04/23/2007 02:24 PM
Please respond to
"Ornelas, Fermin" <[hidden email]>


To
[hidden email]
cc

Subject
Re: Logistic Regression






There are a couple of books written for SAS that do very decent job on
the subject. The names escape my mind but if you go to the SAS site you
will find it. Green is also a good source for this.

Fermin Ornelas, Ph.D.
Management Analyst III, AZ DES
Tel: [phone]
E-mail: [hidden email]


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Pirritano, Matthew
Sent: Monday, April 23, 2007 10:21 AM
To: [hidden email]
Subject: Re: Logistic Regression

For Logistic regression I've found that there ain't nothing better than
"Applied Logistic Regression Analysis 2nd Ed" by Scott Menard. It's one
of those little Sage books in the Quantitative Applications in the
Social Sciences Series. I just bought it online.

Matthew Pirritano, Ph.D.
Assistant Professor of Psychology
Smith Hall 116C
Chapman University
Department of Psychology
One University Drive
Orange, CA 92866
Telephone [phone]
FAX [phone]

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Mary
Sent: Monday, April 23, 2007 9:02 AM
To: [hidden email]
Subject: Logistic Regression

Logistic Regression.

I am trying to build a regression model of 'levels of agreement'. My
dependent variable is dichotomous consisting of two categories - agree
and
disagree. I have however uneven numbers in each cell.

 My question is as follows:

1.Is it important assumption to have relatively even numbers of subjects
in
each category.


Perhaps someone could recommend a reference that covers these questions?

Thanks in advance,

Mary

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.