SPSSX Discussion

MANCOVA with SPSS base?

Classic

List

Threaded

4 messages Options

Justin Meyer-3

MANCOVA with SPSS base?

SPSS listers:

I am fairly certain I need to run a MANCOVA to answer the question that
has been posed to me: "Is there a statistically significant difference
between the posttest scores (continuous, normally distributed) of
students in half-day kindergarten and students in full-day kindergarten
when individual student pretest score (continuous, normally
distributed), individual student free or reduced lunch status
(dichotomous nominal), and individual student race (white/minority,
dichotomous nominal) are accounted for?"

My questions to you are:

Is this the correct analysis or should I be doing something else?
Outside evaluators working for my organization in the past have used
hierarchical linear modeling using software called HLM 6 (allows the
analysis to take into account the nesting of students within
classrooms), but I do not have that.

Can I do this with SPSS 15.0 base? I only see "univariate" as an option
under "general linear model." I also tried using some syntax for a
MANCOVA that I found on the web, but SPSS returned:

>Error # 7019

>There is no license for SPSS Advanced Models.

>This command not executed.

>Specific symptom number: 18

If you need any other information, please let me know. Thank you for any
thoughts you have and Merry Christmas.

____________________________________

Justin Meyer

Researcher

Rowland Reading Foundation

1 South Pinckney Street, Suite 324

Madison, WI 53703

phone: 866-370-7323 fax: 608-204-3846

www.rowlandreading.org <http://www.rowlandreading.org/>

____________________________________

====================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

peter link

Re: MANCOVA with SPSS base?

Justin -

Look into The MIXED procedure. It should be found this way...

Analyze-->Mixed Models-->Linear

This was the path using SPSS v11.5. Maybe it has changed since?

This would be the SPSS version of hierarchical linear models.

Peter Link
VA San Diego Healthcare System

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]]On Behalf Of
Justin Meyer
Sent: Friday, December 21, 2007 12:29 PM
To: [hidden email]
Subject: MANCOVA with SPSS base?

SPSS listers:

I am fairly certain I need to run a MANCOVA to answer the question that
has been posed to me: "Is there a statistically significant difference
between the posttest scores (continuous, normally distributed) of
students in half-day kindergarten and students in full-day kindergarten
when individual student pretest score (continuous, normally
distributed), individual student free or reduced lunch status
(dichotomous nominal), and individual student race (white/minority,
dichotomous nominal) are accounted for?"

My questions to you are:

Is this the correct analysis or should I be doing something else?
Outside evaluators working for my organization in the past have used
hierarchical linear modeling using software called HLM 6 (allows the
analysis to take into account the nesting of students within
classrooms), but I do not have that.

Can I do this with SPSS 15.0 base? I only see "univariate" as an option
under "general linear model." I also tried using some syntax for a
MANCOVA that I found on the web, but SPSS returned:

>Error # 7019

>There is no license for SPSS Advanced Models.

>This command not executed.

>Specific symptom number: 18

If you need any other information, please let me know. Thank you for any
thoughts you have and Merry Christmas.

____________________________________

Justin Meyer

Researcher

Rowland Reading Foundation

1 South Pinckney Street, Suite 324

Madison, WI 53703

phone: 866-370-7323 fax: 608-204-3846

www.rowlandreading.org <http://www.rowlandreading.org/>

____________________________________

=======
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

Justin Meyer-3

Re: MANCOVA with SPSS base?

Peter:

After doing some searching, I don't think I have the MIXED procedure in
SPSS 15.0. It looks like this is part of SPSS Advanced Models also. The
SPSS website description for Advanced Models says it includes
hierarchical linear modeling.

Based on my previous description of the data, would it be appropriate to
use analyze->general linear model->univariate? I am starting to wonder
if I really need to run a MANCOVA.

____________________________________

Justin Meyer

Rowland Reading Foundation

phone: 866-370-7323 fax: 608-204-3846

____________________________________

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
peter link
Sent: Friday, December 21, 2007 2:55 PM
To: [hidden email]
Subject: Re: MANCOVA with SPSS base?

Justin -

Look into The MIXED procedure. It should be found this way...

Analyze-->Mixed Models-->Linear

This was the path using SPSS v11.5. Maybe it has changed since?

This would be the SPSS version of hierarchical linear models.

Peter Link
VA San Diego Healthcare System

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]]On Behalf Of
Justin Meyer
Sent: Friday, December 21, 2007 12:29 PM
To: [hidden email]
Subject: MANCOVA with SPSS base?

SPSS listers:

I am fairly certain I need to run a MANCOVA to answer the question that
has been posed to me: "Is there a statistically significant difference
between the posttest scores (continuous, normally distributed) of
students in half-day kindergarten and students in full-day kindergarten
when individual student pretest score (continuous, normally
distributed), individual student free or reduced lunch status
(dichotomous nominal), and individual student race (white/minority,
dichotomous nominal) are accounted for?"

My questions to you are:

Is this the correct analysis or should I be doing something else?
Outside evaluators working for my organization in the past have used
hierarchical linear modeling using software called HLM 6 (allows the
analysis to take into account the nesting of students within
classrooms), but I do not have that.

Can I do this with SPSS 15.0 base? I only see "univariate" as an option
under "general linear model." I also tried using some syntax for a
MANCOVA that I found on the web, but SPSS returned:

>Error # 7019

>There is no license for SPSS Advanced Models.

>This command not executed.

>Specific symptom number: 18

If you need any other information, please let me know. Thank you for any
thoughts you have and Merry Christmas.

____________________________________

Justin Meyer

Researcher

Rowland Reading Foundation

1 South Pinckney Street, Suite 324

Madison, WI 53703

phone: 866-370-7323 fax: 608-204-3846

www.rowlandreading.org <http://www.rowlandreading.org/>

____________________________________

=======
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

=====================
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

peter link

Re: MANCOVA with SPSS base?

Justin -

A main reason why using a hierarchical linear model is approriate is due to
students being nested within a classroom. It is important to take this into
consideration when modeling. The short reason is that students within the
same classroom are more similar than students from different classrooms.
The nesting of the data leads to observations that are no longer
independent. This is a violation of an assumption of linear regression
models.

I don't know a lot about Eduactional research. Perhaps someone with more
experience in this field can help in terms of what your options for
analyzing the data may be. My opinion is that due to the nesting of data,
you are best off using a hierarchical linear model and not a linear
reagression model.

Peter Link
VA San Diego Healthcare System

-----Original Message-----
From: Justin Meyer [mailto:[hidden email]]
Sent: Friday, December 21, 2007 1:49 PM
To: peter link; [hidden email]
Subject: RE: Re: MANCOVA with SPSS base?

Peter:

After doing some searching, I don't think I have the MIXED procedure in
SPSS 15.0. It looks like this is part of SPSS Advanced Models also. The
SPSS website description for Advanced Models says it includes
hierarchical linear modeling.

Based on my previous description of the data, would it be appropriate to
use analyze->general linear model->univariate? I am starting to wonder
if I really need to run a MANCOVA.

____________________________________

Justin Meyer

Rowland Reading Foundation

phone: 866-370-7323 fax: 608-204-3846

____________________________________

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
peter link
Sent: Friday, December 21, 2007 2:55 PM
To: [hidden email]
Subject: Re: MANCOVA with SPSS base?

Justin -

Look into The MIXED procedure. It should be found this way...

Analyze-->Mixed Models-->Linear

This was the path using SPSS v11.5. Maybe it has changed since?

This would be the SPSS version of hierarchical linear models.

Peter Link
VA San Diego Healthcare System

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]]On Behalf Of
Justin Meyer
Sent: Friday, December 21, 2007 12:29 PM
To: [hidden email]
Subject: MANCOVA with SPSS base?

SPSS listers:

I am fairly certain I need to run a MANCOVA to answer the question that
has been posed to me: "Is there a statistically significant difference
between the posttest scores (continuous, normally distributed) of
students in half-day kindergarten and students in full-day kindergarten
when individual student pretest score (continuous, normally
distributed), individual student free or reduced lunch status
(dichotomous nominal), and individual student race (white/minority,
dichotomous nominal) are accounted for?"

My questions to you are:

Is this the correct analysis or should I be doing something else?
Outside evaluators working for my organization in the past have used
hierarchical linear modeling using software called HLM 6 (allows the
analysis to take into account the nesting of students within
classrooms), but I do not have that.

Can I do this with SPSS 15.0 base? I only see "univariate" as an option
under "general linear model." I also tried using some syntax for a
MANCOVA that I found on the web, but SPSS returned:

>Error # 7019

>There is no license for SPSS Advanced Models.

>This command not executed.

>Specific symptom number: 18

If you need any other information, please let me know. Thank you for any
thoughts you have and Merry Christmas.

____________________________________

Justin Meyer

Researcher

Rowland Reading Foundation

1 South Pinckney Street, Suite 324

Madison, WI 53703

phone: 866-370-7323 fax: 608-204-3846

www.rowlandreading.org <http://www.rowlandreading.org/>

____________________________________

=======
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

=====================
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