Discussion: View Thread

This message has been cross posted to the following eGroups: Social Statistics Section and Statistical Consulting Section .
-------------------------------------------

I run crosstab in spss and I received the following warning

Warning # 3211: On at least one case, the value of the weight variable was zero, negative, or missing. Such cases are invisible to statistical procedures and graphs which need positively weighted cases, but remain on the file and are processed by non-statistical facilities such as LIST and SAVE.

but the analysis and the tables run without any problem or other unusual outputs.
Cn you help me please, what I have to do for this? Aren't my results reliable?


-------------------------------------------
Efthalia Massou
PhD candidate - Researcher
Panteion University of Social and Political Sciences
-------------------------------------------

Have you examined the weight variable?
Are you using a PUF of survey?
-------------------------------------------
David Smith
-------------------------------------------

The message is just to let you know that at least one case has an invalid weight variable value and will not be used. If you located the case(s) in question and remove them, then reran the analysis, the numerical results would be identical, but the warning would no longer appear. So unless the invalid weight value(s) is/are erroneous, the message doesn't indicate a problem you need to worry about. In data that's been entered in aggregated form for use in CROSSTABS, people sometimes specify all combinations of variables, even if there are empty cells (0 counts) for some cells. This is probably the most common reason for this message occurring when running CROSSTABS. ------------------------------------------- David Nichols Lead Statistician, SPSS Support IBM -------------------------------------------
Original Message: Sent: 01-17-2015 17:12 From: Efthalia Massou Subject: warning 3211 in spss This message has been cross posted to the following eGroups: Social Statistics Section and Statistical Consulting Section . ------------------------------------------- I run crosstab in spss and I received the following warning Warning # 3211: On at least one case, the value of the weight variable was zero, negative, or missing. Such cases are invisible to statistical procedures and graphs which need positively weighted cases, but remain on the file and are processed by non-statistical facilities such as LIST and SAVE. but the analysis and the tables run without any problem or other unusual outputs. Cn you help me please, what I have to do for this? Aren't my results reliable? ------------------------------------------- Efthalia Massou PhD candidate - Researcher Panteion University of Social and Political Sciences -------------------------------------------

Ok.I understand.Many thanks for your responses.

-------------------------------------------
Efthalia Massou
PhD candidate - Researcher
Panteion University of Social and Political Sciences
-------------------------------------------



Original Message:
Sent: 1/17/2015 10:12:14 PM
From: dpnichols@gmail.com
Subject: RE: warning 3211 in spss

The message is just to let you know that at least one case has an invalid weight variable value and will not be used. If you located the case(s) in question and remove them, then reran the analysis, the numerical results would be identical, but the warning would no longer appear. So unless the invalid weight value(s) is/are erroneous, the message doesn't indicate a problem you need to worry about. In data that's been entered in aggregated form for use in CROSSTABS, people sometimes specify all combinations of variables, even if there are empty cells (0 counts) for some cells. This is probably the most common reason for this message occurring when running CROSSTABS. ------------------------------------------- David Nichols Lead Statistician, SPSS Support IBM -------------------------------------------