|Date: ||Fri, 17 Jun 2005 08:35:18 -0400|
|Sender: ||"SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>|
|From: ||Rayman Mohamed <firstname.lastname@example.org>|
|Subject: ||Re: Unexpected singularities|
|Content-Type: ||text/plain; charset=us-ascii|
Hector and Jon,
Thanks for your replies and the heads-up on more efficient
syntax. WRT to Jon's comment, I get the same singularity
message even when I drop all the other predictors, i.e., I
use political affiliations as the only predictors.
I have three related issues that might together help me
clear this up.
1. With Hector's coding below, I imagine that I would still
need to declare those cases where democrat = 0. Would I
still use an IF statement of some sort? Using your set up,
would the following be correct for democrats or is there
some "non-IF" statement that would be more efficient.
MISSING VALUES q78a (4,9).
IF (q78a = 2 | q78a = 3 | q78a = 5) democrat = 0 .
2. Thanks for the info on how to set up missing values. I
was about to ask how to do that. However, do I need to
declare missing values? When I create the new variables,
e.g., for Democrat, I would *not* have declared a value for
when the raw data (q78a) = 4 or 9.
In other words, when q78a = 4, democrat contains a period.
Is this period not equivalent to a missing value.
(I realize that you are declaring missing values for q78a
and I am talking about missing values for the field
Democrat. In any case, I do not see why I need to declare
missing values for either q78a or for the field Democrat.
Moreover, suppose I want to perform subsequent analysis on
the "don't knows" would declaring those don't knows as
missing values is q78a not cause me to lose information that
I might need for subsequent analyses. I suspect that an
answer to this question would help me understand just what a
missing value is and why it might be important to declare
3. On a related note, how does one write syntax for a
period. E.g., suppose the interviewer fails to collect any
information for certain cell and the cell turns up as a
period in SPSS. I usually assume that SPSS treats this as
missing data and that I do not have to worry about it --
that case is simply left out the analysis. However, suppose
I wanted to write syntax to manipulate this period, how do I
treat this period?
---- Original message ----
>Date: Fri, 17 Jun 2005 01:01:33 -0300
>From: "Hector Maletta" <email@example.com>
>Subject: RE: Unexpected singularities
>To: <firstname.lastname@example.org>, <SPSSX-L@LISTSERV.UGA.EDU>
>You should be aware that singularities can arise even when
you do everything
>right, just by chance. Entering all the dummies assures
>leaving one category aside does not ensure you do not get
>Besides, your syntax is essentially correct in my view,
>inefficient. Each EXECUTE necessitares reading the file.
You can put just
>one at the end, saving time.
>Also you can create each dummy in a single command each
(but define DON'T
>KNOWS or other excluded values as missing before you do
that, so that the
>dummies are system missing for them). I assume 9 and 4 are
to be ignored as
>MISSING VALUES q78a (4,9).
>COMPUTE IND_OTHER=(q78a=3 OR q78a=5).
>> -----Original Message-----
>> From: SPSSX(r) Discussion [mailto:SPSSX-
>> On Behalf Of Rayman Mohamed
>> Sent: Friday, June 17, 2005 12:03 AM
>> To: SPSSX-L@LISTSERV.UGA.EDU
>> Subject: Unexpected singularities
>> Hi all,
>> I have been doing some multinomial logistic regressions.
>> When I use two particular categorical variables (in
>> appropriate dummy form -- see later) in my models I get
>> following message.
>> "Unexpected singularities in the Hessian matrix are
>> encountered. This indicates that either some predictor
>> variables should be excluded or some categories should be
>> This implies that I have redundancy in my dummy variables
>> think). However, I have checked and rechecked but I
>> see where I am going wrong. One of the categorical
>> for which I am getting this message is political
>> I created three dummy variables (democrat, republican,
>> independent/no affiliation) and entered two into the
>> regression model. (There are other categories that I
>> when I created the dummy variables, e.g., the "don't
>> Could anyone think of another reason why I am getting
>> message. Or do you think that perhaps I just looked at
>> too much so I cannot see some rather obvious mistake in
>> syntax to create the dummy variables?
>> Here is the syntax that I used to create the dummy
>> for political affiliation:
>> IF (q78a = 1) democrat_1 = 1 .
>> EXECUTE .
>> IF (q78a = 2 | q78a = 3 | q78a = 5) democrat_1 = 0 .
>> EXECUTE .
>> IF (q78a = 2) republican_1 = 1 .
>> EXECUTE .
>> IF (q78a = 1 | q78a = 3 | q78a = 5) republican_1 = 0 .
>> EXECUTE .
>> IF (q78a = 3 | q78a = 5) Ind_other_1 = 1 .
>> IF (q78a = 1 | q78a = 2) ind_other_1 = 0 .
>> EXECUTE .
>> Thanks for your suggestions,
>> Rayman Mohamed
>> Assistant Professor
>> Wayne State University
>> College of Urban, Labor, and Metropolitan Affairs
>> Department of Geography and Urban Planning
>> 227 State Hall
>> 5143 Cass Avenue
>> Detroit, MI 48202
Wayne State University
College of Urban, Labor, and Metropolitan Affairs
Department of Geography and Urban Planning
227 State Hall
5143 Cass Avenue
Detroit, MI 48202