Statistical test with SPSS

[Juan Pablo Sandoval]

Hi:

I have 2 independent samples, I need to check if both samples were correctly
taken from the population, hence being able to say that both are comparable.
What I would like to do is use some variables to test if the differences
between them are to big to blame then on randomness.

If my variable were age I know I could do an independent samples t-test, but
the variable would like to use is a categorical variable, like so:

1. Married
2. Single
3. Widow
4. Divorced

The variable was asked on both samples.

Thanks to all for your time!!!

=====================
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]

I think a chi-square test would work. Analyze->Nonparametric Tests->Chi
Square...

Can anyone verify if this is correct?
____________________________________

Justin Meyer

Rowland Reading Foundation

phone: [phone]  fax: [phone]

____________________________________

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Juan Pablo Sandoval
Sent: Wednesday, February 20, 2008 11:40 AM
To: [hidden email]
Subject: Statistical test with SPSS

Hi:

I have 2 independent samples, I need to check if both samples were
correctly
taken from the population, hence being able to say that both are
comparable.
What I would like to do is use some variables to test if the differences
between them are to big to blame then on randomness.

If my variable were age I know I could do an independent samples t-test,
but
the variable would like to use is a categorical variable, like so:

1. Married
2. Single
3. Widow
4. Divorced

The variable was asked on both samples.

Thanks to all for your time!!!

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

[bdates]

The best approach is to use Analyze->Descriptives->Crosstabs.  The
sample numbers are the row or column variable, and the categories are
the other variable.  In "Statistics" check "Chi-square" (and whatever
other statistics you might want.) Then run the test.

Brian

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Justin Meyer
Sent: Wednesday, February 20, 2008 12:53 PM
To: [hidden email]
Subject: Re: Statistical test with SPSS

I think a chi-square test would work. Analyze->Nonparametric Tests->Chi
Square...

Can anyone verify if this is correct?
____________________________________

Justin Meyer

Rowland Reading Foundation

phone: [phone]  fax: [phone]

____________________________________

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Juan Pablo Sandoval
Sent: Wednesday, February 20, 2008 11:40 AM
To: [hidden email]
Subject: Statistical test with SPSS

Hi:

I have 2 independent samples, I need to check if both samples were
correctly
taken from the population, hence being able to say that both are
comparable.
What I would like to do is use some variables to test if the differences
between them are to big to blame then on randomness.

If my variable were age I know I could do an independent samples t-test,
but
the variable would like to use is a categorical variable, like so:

1. Married
2. Single
3. Widow
4. Divorced

The variable was asked on both samples.

Thanks to all for your time!!!

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

[Sparling, Steven J MAJ MIL USA SA]

Classification:  UNCLASSIFIED
Caveats: NONE

If you are testing each sample against a known distrbution in the
population use Analyze->Nonparametric Tests->Chi Square and specify the
distribution in the gui.  This is the chi square goodness of fit test.

If you are comparing the samples against eachother us
Analyze->Descriptives->Crosstabs.  This is the chi square test for
independence.

good luck.


Steve

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Dates, Brian
Sent: Wednesday, February 20, 2008 1:10 PM
To: [hidden email]
Subject: Re: [SPSSX-L] Statistical test with SPSS

The best approach is to use Analyze->Descriptives->Crosstabs.  The
sample numbers are the row or column variable, and the categories are
the other variable.  In "Statistics" check "Chi-square" (and whatever
other statistics you might want.) Then run the test.

Brian

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Justin Meyer
Sent: Wednesday, February 20, 2008 12:53 PM
To: [hidden email]
Subject: Re: Statistical test with SPSS

I think a chi-square test would work. Analyze->Nonparametric Tests->Chi
Square...

Can anyone verify if this is correct?
____________________________________

Justin Meyer

Rowland Reading Foundation

phone: [phone]  fax: [phone]

____________________________________

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Juan Pablo Sandoval
Sent: Wednesday, February 20, 2008 11:40 AM
To: [hidden email]
Subject: Statistical test with SPSS

Hi:

I have 2 independent samples, I need to check if both samples were
correctly taken from the population, hence being able to say that both
are comparable.
What I would like to do is use some variables to test if the differences
between them are to big to blame then on randomness.

If my variable were age I know I could do an independent samples t-test,
but the variable would like to use is a categorical variable, like so:

1. Married
2. Single
3. Widow
4. Divorced

The variable was asked on both samples.

Thanks to all for your time!!!

=====================
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
Classification:  UNCLASSIFIED
Caveats: NONE

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