errors in DeCarlo's macro for multivariate normality

classic Classic list List threaded Threaded
11 messages Options
Reply | Threaded
Open this post in threaded view
|

errors in DeCarlo's macro for multivariate normality

Debbie Hahs-Vaughn
I am trying to run DeCarlo's (1997) macro for multivariate normality using SPSS version 22.  I have used the sample data online (iris) as well as my own data but am getting multiple (and the same) errors in the output regardless which data I use.  It appears that most of the output is provided (I've pasted this below), but the graph is not (error statements received with that are provided below as well).  I've tried all the reasonable solutions (e.g., moving the files so they are not buried in folders, moved files to different directories, etc.), and I'm sure there is a simple fix to this.  I would be happy to forward the syntax and output offline if that may be helpful.  Thanks in advance for any assistance.

DeCarlo, L. T. (1997). On the meaning and use of kurtosis. Psychological Methods, 2, 292-307.

----------------------------------------------

Run MATRIX procedure:
 
Number of observations:
    50
 
Number of variables:
     4
 
Measures and tests of skew:
           g1   sqrt(b1)      z(b1)    p-value
x1      .1201      .1165      .3740      .7084
x2      .0412      .0399      .1285      .8978
x3      .1064      .1032      .3315      .7403
x4     1.2539     1.2159     3.2998      .0010
 
Measures and tests of kurtosis:
           g2       b2-3      z(b2)    p-value
x1     -.2527     -.3458     -.2330      .8157
x2      .9547      .7442     1.3961      .1627
x3     1.0216      .8046     1.4585      .1447
x4     1.7191     1.4343     2.0125      .0442
 
Omnibus tests of normality (both chisq, 2 df):
 
  D'Agostino & Pearson K sq    Jarque & Bera LM test
         K sq    p-value         LM    p-value
x1      .1942      .9075      .3621      .8344
x2     1.9657      .3742     1.1672      .5579
x3     2.2370      .3268     1.4374      .4874
x4    14.9387      .0006    16.6066      .0002
 
*************** Multivariate Statistics ***************
 
Tests of multivariate skew:
 
  Small's test (chisq)
         Q1         df    p-value
    11.0243     4.0000      .0263
 
  Srivastava's test
   chi(b1p)         df    p-value
     7.4678     4.0000      .1131
 
Tests of multivariate kurtosis:
 
  A variant of Small's test (chisq)
        VQ2         df    p-value
     8.5374     4.0000      .0738
 
  Srivastava's test
        b2p     N(b2p)    p-value
     3.5988     1.7286      .0839
 
  Mardia's test
        b2p     N(b2p)    p-value
    26.5377     1.2950      .1953
 
Omnibus test of multivariate normality:
 
  (based on Small's test, chisq)
        VQ3         df    p-value
    19.5617     8.0000      .0121
 
>Error # 34 in column 21.  Text: temp
>SPSS Statistics cannot access a file with the given file specification.  The
>file specification is either syntactically invalid, specifies an invalid
>drive, specifies a protected directory, specifies a protected file, or
>specifies a non-sharable file.
>Execution of this command stops.
 
------ END MATRIX -----

----------------------------------------------
These are the error statements with the graph:
 
>Error # 61 in column 10.  Text: temp
>The filename is not valid.
>Execution of this command stops.
 
>Error # 701 in column 15.  Text: top
>An undefined variable name, or a scratch or system variable was specified in a
>variable list which accepts only standard variables.  Check spelling and
>verify the existence of this variable.
>Execution of this command stops.
 
>Error # 4285 in column 7.  Text: case
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 19.  Text: a01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 19.  Text: a05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 15.  Text: f01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 15.  Text: f05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 31.  Text: fc05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 31.  Text: fc01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4070.  Command name: end if
>The command does not follow an unclosed DO IF command.  Maybe the DO IF
>command was not recognized because of an error.  Use the level-of-control
>shown to the left of the SPSS Statistics commands to determine the range of
>LOOPs and DO IFs.
>Execution of this command stops.
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
>Error # 4285 in column 7.  Text: top
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 18.  Text: top
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4070.  Command name: end if
>The command does not follow an unclosed DO IF command.  Maybe the DO IF
>command was not recognized because of an error.  Use the level-of-control
>shown to the left of the SPSS Statistics commands to determine the range of
>LOOPs and DO IFs.
>Execution of this command stops.
 
>Error # 4285 in column 26.  Text: rnk
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

=====================
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
Reply | Threaded
Open this post in threaded view
|

Re: errors in DeCarlo's macro for multivariate normality

Bruce Weaver
Administrator
Is this the macro you're using?

  http://www.columbia.edu/~ld208/normtest.sps

DeCarlo's e-mail address is on his webpage (http://www.columbia.edu/~ld208/).  Have you tried contacting him?  He's in a much better position to help you than most regulars here will be (unless one of them happens to be familiar with the macro).  



Debbie Hahs-Vaughn wrote
I am trying to run DeCarlo's (1997) macro for multivariate normality using SPSS version 22.  I have used the sample data online (iris) as well as my own data but am getting multiple (and the same) errors in the output regardless which data I use.  It appears that most of the output is provided (I've pasted this below), but the graph is not (error statements received with that are provided below as well).  I've tried all the reasonable solutions (e.g., moving the files so they are not buried in folders, moved files to different directories, etc.), and I'm sure there is a simple fix to this.  I would be happy to forward the syntax and output offline if that may be helpful.  Thanks in advance for any assistance.

DeCarlo, L. T. (1997). On the meaning and use of kurtosis. Psychological Methods, 2, 292-307.

----------------------------------------------

Run MATRIX procedure:
 
Number of observations:
    50
 
Number of variables:
     4
 
Measures and tests of skew:
           g1   sqrt(b1)      z(b1)    p-value
x1      .1201      .1165      .3740      .7084
x2      .0412      .0399      .1285      .8978
x3      .1064      .1032      .3315      .7403
x4     1.2539     1.2159     3.2998      .0010
 
Measures and tests of kurtosis:
           g2       b2-3      z(b2)    p-value
x1     -.2527     -.3458     -.2330      .8157
x2      .9547      .7442     1.3961      .1627
x3     1.0216      .8046     1.4585      .1447
x4     1.7191     1.4343     2.0125      .0442
 
Omnibus tests of normality (both chisq, 2 df):
 
  D'Agostino & Pearson K sq    Jarque & Bera LM test
         K sq    p-value         LM    p-value
x1      .1942      .9075      .3621      .8344
x2     1.9657      .3742     1.1672      .5579
x3     2.2370      .3268     1.4374      .4874
x4    14.9387      .0006    16.6066      .0002
 
*************** Multivariate Statistics ***************
 
Tests of multivariate skew:
 
  Small's test (chisq)
         Q1         df    p-value
    11.0243     4.0000      .0263
 
  Srivastava's test
   chi(b1p)         df    p-value
     7.4678     4.0000      .1131
 
Tests of multivariate kurtosis:
 
  A variant of Small's test (chisq)
        VQ2         df    p-value
     8.5374     4.0000      .0738
 
  Srivastava's test
        b2p     N(b2p)    p-value
     3.5988     1.7286      .0839
 
  Mardia's test
        b2p     N(b2p)    p-value
    26.5377     1.2950      .1953
 
Omnibus test of multivariate normality:
 
  (based on Small's test, chisq)
        VQ3         df    p-value
    19.5617     8.0000      .0121
 
>Error # 34 in column 21.  Text: temp
>SPSS Statistics cannot access a file with the given file specification.  The
>file specification is either syntactically invalid, specifies an invalid
>drive, specifies a protected directory, specifies a protected file, or
>specifies a non-sharable file.
>Execution of this command stops.
 
------ END MATRIX -----

----------------------------------------------
These are the error statements with the graph:
 
>Error # 61 in column 10.  Text: temp
>The filename is not valid.
>Execution of this command stops.
 
>Error # 701 in column 15.  Text: top
>An undefined variable name, or a scratch or system variable was specified in a
>variable list which accepts only standard variables.  Check spelling and
>verify the existence of this variable.
>Execution of this command stops.
 
>Error # 4285 in column 7.  Text: case
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 19.  Text: a01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 19.  Text: a05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 15.  Text: f01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 15.  Text: f05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 31.  Text: fc05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 31.  Text: fc01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4070.  Command name: end if
>The command does not follow an unclosed DO IF command.  Maybe the DO IF
>command was not recognized because of an error.  Use the level-of-control
>shown to the left of the SPSS Statistics commands to determine the range of
>LOOPs and DO IFs.
>Execution of this command stops.
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
>Error # 4285 in column 7.  Text: top
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 18.  Text: top
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4070.  Command name: end if
>The command does not follow an unclosed DO IF command.  Maybe the DO IF
>command was not recognized because of an error.  Use the level-of-control
>shown to the left of the SPSS Statistics commands to determine the range of
>LOOPs and DO IFs.
>Execution of this command stops.
 
>Error # 4285 in column 26.  Text: rnk
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

=====================
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
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.
Reply | Threaded
Open this post in threaded view
|

Re: errors in DeCarlo's macro for multivariate normality

David Marso
Administrator
In reply to this post by Debbie Hahs-Vaughn
Debbie ,
">Error # 34 in column 21.  Text: temp
>SPSS Statistics cannot access a file with the given file specification.  The
>file specification is either syntactically invalid, specifies an invalid
>drive, specifies a protected directory, specifies a protected file, or
>specifies a non-sharable file.
>Execution of this command stops. "

Ah!!!!! Run SPSS as administrator!
If you can't do that then change the relevant DATASET DECLARE to a FILE HANDLE and use GET FILE to access the file rather than DATASET ACTIVATE.
ie
*DATASET DECLARE temp.
FILE HANDLE temp = "C:\TEMP\monte.sav'.

*DATASET ACTIVATE temp.
GET FILE temp.

I am only guessing at the exact specifics because I don't know to which macro you referring.
This is one of those silly MATRIX bugs which will HOPEFULLY be fixed in a 22 patch (I can't afford to upgrade to ver 23).
HTH, David
 
------ END MATRIX -----
Debbie Hahs-Vaughn wrote
I am trying to run DeCarlo's (1997) macro for multivariate normality using SPSS version 22.  I have used the sample data online (iris) as well as my own data but am getting multiple (and the same) errors in the output regardless which data I use.  It appears that most of the output is provided (I've pasted this below), but the graph is not (error statements received with that are provided below as well).  I've tried all the reasonable solutions (e.g., moving the files so they are not buried in folders, moved files to different directories, etc.), and I'm sure there is a simple fix to this.  I would be happy to forward the syntax and output offline if that may be helpful.  Thanks in advance for any assistance.

DeCarlo, L. T. (1997). On the meaning and use of kurtosis. Psychological Methods, 2, 292-307.

----------------------------------------------

Run MATRIX procedure:
 
Number of observations:
    50
 
Number of variables:
     4
 
Measures and tests of skew:
           g1   sqrt(b1)      z(b1)    p-value
x1      .1201      .1165      .3740      .7084
x2      .0412      .0399      .1285      .8978
x3      .1064      .1032      .3315      .7403
x4     1.2539     1.2159     3.2998      .0010
 
Measures and tests of kurtosis:
           g2       b2-3      z(b2)    p-value
x1     -.2527     -.3458     -.2330      .8157
x2      .9547      .7442     1.3961      .1627
x3     1.0216      .8046     1.4585      .1447
x4     1.7191     1.4343     2.0125      .0442
 
Omnibus tests of normality (both chisq, 2 df):
 
  D'Agostino & Pearson K sq    Jarque & Bera LM test
         K sq    p-value         LM    p-value
x1      .1942      .9075      .3621      .8344
x2     1.9657      .3742     1.1672      .5579
x3     2.2370      .3268     1.4374      .4874
x4    14.9387      .0006    16.6066      .0002
 
*************** Multivariate Statistics ***************
 
Tests of multivariate skew:
 
  Small's test (chisq)
         Q1         df    p-value
    11.0243     4.0000      .0263
 
  Srivastava's test
   chi(b1p)         df    p-value
     7.4678     4.0000      .1131
 
Tests of multivariate kurtosis:
 
  A variant of Small's test (chisq)
        VQ2         df    p-value
     8.5374     4.0000      .0738
 
  Srivastava's test
        b2p     N(b2p)    p-value
     3.5988     1.7286      .0839
 
  Mardia's test
        b2p     N(b2p)    p-value
    26.5377     1.2950      .1953
 
Omnibus test of multivariate normality:
 
  (based on Small's test, chisq)
        VQ3         df    p-value
    19.5617     8.0000      .0121
 
>Error # 34 in column 21.  Text: temp
>SPSS Statistics cannot access a file with the given file specification.  The
>file specification is either syntactically invalid, specifies an invalid
>drive, specifies a protected directory, specifies a protected file, or
>specifies a non-sharable file.
>Execution of this command stops.
 
------ END MATRIX -----

----------------------------------------------
These are the error statements with the graph:
 
>Error # 61 in column 10.  Text: temp
>The filename is not valid.
>Execution of this command stops.
 
>Error # 701 in column 15.  Text: top
>An undefined variable name, or a scratch or system variable was specified in a
>variable list which accepts only standard variables.  Check spelling and
>verify the existence of this variable.
>Execution of this command stops.
 
>Error # 4285 in column 7.  Text: case
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 19.  Text: a01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 19.  Text: a05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 15.  Text: f01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 15.  Text: f05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 31.  Text: fc05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 31.  Text: fc01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4070.  Command name: end if
>The command does not follow an unclosed DO IF command.  Maybe the DO IF
>command was not recognized because of an error.  Use the level-of-control
>shown to the left of the SPSS Statistics commands to determine the range of
>LOOPs and DO IFs.
>Execution of this command stops.
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
>Error # 4285 in column 7.  Text: top
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 18.  Text: top
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4070.  Command name: end if
>The command does not follow an unclosed DO IF command.  Maybe the DO IF
>command was not recognized because of an error.  Use the level-of-control
>shown to the left of the SPSS Statistics commands to determine the range of
>LOOPs and DO IFs.
>Execution of this command stops.
 
>Error # 4285 in column 26.  Text: rnk
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

=====================
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
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
Reply | Threaded
Open this post in threaded view
|

Re: errors in DeCarlo's macro for multivariate normality

David Marso
Administrator
In reply to this post by Bruce Weaver
Bruce,
This is that F'd up MATRIX bug I've been bitching about for the past 1.5 years or so ;-)
http://spssx-discussion.1045642.n5.nabble.com/SERIOUS-problem-with-Multiple-datasets-in-MATRIX-procedure-td5722765.html
David
----
Bruce Weaver wrote
Is this the macro you're using?

  http://www.columbia.edu/~ld208/normtest.sps

DeCarlo's e-mail address is on his webpage (http://www.columbia.edu/~ld208/).  Have you tried contacting him?  He's in a much better position to help you than most regulars here will be (unless one of them happens to be familiar with the macro).  



Debbie Hahs-Vaughn wrote
I am trying to run DeCarlo's (1997) macro for multivariate normality using SPSS version 22.  I have used the sample data online (iris) as well as my own data but am getting multiple (and the same) errors in the output regardless which data I use.  It appears that most of the output is provided (I've pasted this below), but the graph is not (error statements received with that are provided below as well).  I've tried all the reasonable solutions (e.g., moving the files so they are not buried in folders, moved files to different directories, etc.), and I'm sure there is a simple fix to this.  I would be happy to forward the syntax and output offline if that may be helpful.  Thanks in advance for any assistance.

DeCarlo, L. T. (1997). On the meaning and use of kurtosis. Psychological Methods, 2, 292-307.

----------------------------------------------

Run MATRIX procedure:
 
Number of observations:
    50
 
Number of variables:
     4
 
Measures and tests of skew:
           g1   sqrt(b1)      z(b1)    p-value
x1      .1201      .1165      .3740      .7084
x2      .0412      .0399      .1285      .8978
x3      .1064      .1032      .3315      .7403
x4     1.2539     1.2159     3.2998      .0010
 
Measures and tests of kurtosis:
           g2       b2-3      z(b2)    p-value
x1     -.2527     -.3458     -.2330      .8157
x2      .9547      .7442     1.3961      .1627
x3     1.0216      .8046     1.4585      .1447
x4     1.7191     1.4343     2.0125      .0442
 
Omnibus tests of normality (both chisq, 2 df):
 
  D'Agostino & Pearson K sq    Jarque & Bera LM test
         K sq    p-value         LM    p-value
x1      .1942      .9075      .3621      .8344
x2     1.9657      .3742     1.1672      .5579
x3     2.2370      .3268     1.4374      .4874
x4    14.9387      .0006    16.6066      .0002
 
*************** Multivariate Statistics ***************
 
Tests of multivariate skew:
 
  Small's test (chisq)
         Q1         df    p-value
    11.0243     4.0000      .0263
 
  Srivastava's test
   chi(b1p)         df    p-value
     7.4678     4.0000      .1131
 
Tests of multivariate kurtosis:
 
  A variant of Small's test (chisq)
        VQ2         df    p-value
     8.5374     4.0000      .0738
 
  Srivastava's test
        b2p     N(b2p)    p-value
     3.5988     1.7286      .0839
 
  Mardia's test
        b2p     N(b2p)    p-value
    26.5377     1.2950      .1953
 
Omnibus test of multivariate normality:
 
  (based on Small's test, chisq)
        VQ3         df    p-value
    19.5617     8.0000      .0121
 
>Error # 34 in column 21.  Text: temp
>SPSS Statistics cannot access a file with the given file specification.  The
>file specification is either syntactically invalid, specifies an invalid
>drive, specifies a protected directory, specifies a protected file, or
>specifies a non-sharable file.
>Execution of this command stops.
 
------ END MATRIX -----

----------------------------------------------
These are the error statements with the graph:
 
>Error # 61 in column 10.  Text: temp
>The filename is not valid.
>Execution of this command stops.
 
>Error # 701 in column 15.  Text: top
>An undefined variable name, or a scratch or system variable was specified in a
>variable list which accepts only standard variables.  Check spelling and
>verify the existence of this variable.
>Execution of this command stops.
 
>Error # 4285 in column 7.  Text: case
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 19.  Text: a01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 19.  Text: a05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 15.  Text: f01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 15.  Text: f05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 31.  Text: fc05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 31.  Text: fc01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4070.  Command name: end if
>The command does not follow an unclosed DO IF command.  Maybe the DO IF
>command was not recognized because of an error.  Use the level-of-control
>shown to the left of the SPSS Statistics commands to determine the range of
>LOOPs and DO IFs.
>Execution of this command stops.
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
Critical values (Bonferroni) for a single multivar. outlier:
 
 
5 observations with largest Mahalanobis distances:
 
>Error # 4285 in column 7.  Text: top
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4285 in column 18.  Text: top
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
 
>Error # 4070.  Command name: end if
>The command does not follow an unclosed DO IF command.  Maybe the DO IF
>command was not recognized because of an error.  Use the level-of-control
>shown to the left of the SPSS Statistics commands to determine the range of
>LOOPs and DO IFs.
>Execution of this command stops.
 
>Error # 4285 in column 26.  Text: rnk
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

=====================
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
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"
Reply | Threaded
Open this post in threaded view
|

Re: errors in DeCarlo's macro for multivariate normality

Ryan Black
In reply to this post by Debbie Hahs-Vaughn
One could check for multivariate kurtosis (using Mardia's formula) as well as univariate and multivariate outliers in AMOS very easily, if that's of interest to the OP.

Ryan

On Wed, Nov 12, 2014 at 1:40 PM, Debbie Hahs-Vaughn <[hidden email]> wrote:
I am trying to run DeCarlo's (1997) macro for multivariate normality using SPSS version 22.  I have used the sample data online (iris) as well as my own data but am getting multiple (and the same) errors in the output regardless which data I use.  It appears that most of the output is provided (I've pasted this below), but the graph is not (error statements received with that are provided below as well).  I've tried all the reasonable solutions (e.g., moving the files so they are not buried in folders, moved files to different directories, etc.), and I'm sure there is a simple fix to this.  I would be happy to forward the syntax and output offline if that may be helpful.  Thanks in advance for any assistance.

DeCarlo, L. T. (1997). On the meaning and use of kurtosis. Psychological Methods, 2, 292-307.

----------------------------------------------

Run MATRIX procedure:

Number of observations:
    50

Number of variables:
     4

Measures and tests of skew:
           g1   sqrt(b1)      z(b1)    p-value
x1      .1201      .1165      .3740      .7084
x2      .0412      .0399      .1285      .8978
x3      .1064      .1032      .3315      .7403
x4     1.2539     1.2159     3.2998      .0010

Measures and tests of kurtosis:
           g2       b2-3      z(b2)    p-value
x1     -.2527     -.3458     -.2330      .8157
x2      .9547      .7442     1.3961      .1627
x3     1.0216      .8046     1.4585      .1447
x4     1.7191     1.4343     2.0125      .0442

Omnibus tests of normality (both chisq, 2 df):

  D'Agostino & Pearson K sq    Jarque & Bera LM test
         K sq    p-value         LM    p-value
x1      .1942      .9075      .3621      .8344
x2     1.9657      .3742     1.1672      .5579
x3     2.2370      .3268     1.4374      .4874
x4    14.9387      .0006    16.6066      .0002

*************** Multivariate Statistics ***************

Tests of multivariate skew:

  Small's test (chisq)
         Q1         df    p-value
    11.0243     4.0000      .0263

  Srivastava's test
   chi(b1p)         df    p-value
     7.4678     4.0000      .1131

Tests of multivariate kurtosis:

  A variant of Small's test (chisq)
        VQ2         df    p-value
     8.5374     4.0000      .0738

  Srivastava's test
        b2p     N(b2p)    p-value
     3.5988     1.7286      .0839

  Mardia's test
        b2p     N(b2p)    p-value
    26.5377     1.2950      .1953

Omnibus test of multivariate normality:

  (based on Small's test, chisq)
        VQ3         df    p-value
    19.5617     8.0000      .0121

>Error # 34 in column 21.  Text: temp
>SPSS Statistics cannot access a file with the given file specification.  The
>file specification is either syntactically invalid, specifies an invalid
>drive, specifies a protected directory, specifies a protected file, or
>specifies a non-sharable file.
>Execution of this command stops.

------ END MATRIX -----

----------------------------------------------
These are the error statements with the graph:

>Error # 61 in column 10.  Text: temp
>The filename is not valid.
>Execution of this command stops.

>Error # 701 in column 15.  Text: top
>An undefined variable name, or a scratch or system variable was specified in a
>variable list which accepts only standard variables.  Check spelling and
>verify the existence of this variable.
>Execution of this command stops.

>Error # 4285 in column 7.  Text: case
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

>Error # 4285 in column 19.  Text: a01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

>Error # 4285 in column 19.  Text: a05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

>Error # 4285 in column 15.  Text: f01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

>Error # 4285 in column 15.  Text: f05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

>Error # 4285 in column 31.  Text: fc05
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

>Error # 4285 in column 31.  Text: fc01
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

>Error # 4070.  Command name: end if
>The command does not follow an unclosed DO IF command.  Maybe the DO IF
>command was not recognized because of an error.  Use the level-of-control
>shown to the left of the SPSS Statistics commands to determine the range of
>LOOPs and DO IFs.
>Execution of this command stops.

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

Critical values (Bonferroni) for a single multivar. outlier:


5 observations with largest Mahalanobis distances:

>Error # 4285 in column 7.  Text: top
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

>Error # 4285 in column 18.  Text: top
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

>Error # 4070.  Command name: end if
>The command does not follow an unclosed DO IF command.  Maybe the DO IF
>command was not recognized because of an error.  Use the level-of-control
>shown to the left of the SPSS Statistics commands to determine the range of
>LOOPs and DO IFs.
>Execution of this command stops.

>Error # 4285 in column 26.  Text: rnk
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.

=====================
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
Reply | Threaded
Open this post in threaded view
|

Re: errors in DeCarlo's macro for multivariate normality

Andy W
In reply to this post by David Marso
That is one problem, and simply changing the below lines should fix that. From:

save mahal /outfile=temp
 /variables=case,rnk,top,dsq,pvar,ddf,ncase,a01,a05.
end matrix.
get file=temp.

with

save mahal /outfile=*
 /variables=case,rnk,top,dsq,pvar,ddf,ncase,a01,a05.
end matrix.
dataset name temp.
dataset activate temp.

Should do the trick.

Also the comments in the file are of the BATCH style, so if you used INSERT with the default SYNTAX=INTERACTIVE (instead of INCLUDE) the commenting causes problems. Ditto if you just copy-paste and run interactively.

Also one of the lines "do if p>1" looked like an error omitting the terminating period - although the results would be pretty innocuous, it just prevents some tables from being printed.

Here I've posted a version with these slight fixes and an example use at the end that runs as expected. https://dl.dropboxusercontent.com/u/3385251/Mult_Macro_fixAndy.sps
Andy W
apwheele@gmail.com
http://andrewpwheeler.wordpress.com/
Reply | Threaded
Open this post in threaded view
|

Re: errors in DeCarlo's macro for multivariate normality

Debbie Hahs-Vaughn
In reply to this post by Debbie Hahs-Vaughn
This was so incredibly helpful.  This completely solved the issue.  Thank you so much!

=====================
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
Reply | Threaded
Open this post in threaded view
|

Re: errors in DeCarlo's macro for multivariate normality

Bruce Weaver
Administrator
In reply to this post by Andy W
Good stuff, Andy & David.  I've e-mailed DeCarlo alerting him to this thread, in case he wants to repair the version on his webpage.  


Andy W wrote
That is one problem, and simply changing the below lines should fix that. From:

save mahal /outfile=temp
 /variables=case,rnk,top,dsq,pvar,ddf,ncase,a01,a05.
end matrix.
get file=temp.

with

save mahal /outfile=*
 /variables=case,rnk,top,dsq,pvar,ddf,ncase,a01,a05.
end matrix.
dataset name temp.
dataset activate temp.

Should do the trick.

Also the comments in the file are of the BATCH style, so if you used INSERT with the default SYNTAX=INTERACTIVE (instead of INCLUDE) the commenting causes problems. Ditto if you just copy-paste and run interactively.

Also one of the lines "do if p>1" looked like an error omitting the terminating period - although the results would be pretty innocuous, it just prevents some tables from being printed.

Here I've posted a version with these slight fixes and an example use at the end that runs as expected. https://dl.dropboxusercontent.com/u/3385251/Mult_Macro_fixAndy.sps
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.
Reply | Threaded
Open this post in threaded view
|

Re: errors in DeCarlo's macro for multivariate normality

burakk
In reply to this post by Debbie Hahs-Vaughn
That link is dead.. Macro is not working.. Could you share it again please?



--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
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
Reply | Threaded
Open this post in threaded view
|

Re: errors in DeCarlo's macro for multivariate normality

Kirill Orlov
Mayby try Google cached...
http://webcache.googleusercontent.com/search?q=cache:MvLiMBwkiQgJ:www.columbia.edu/~ld208




06.02.2020 18:21, burakk пишет:

> That link is dead.. Macro is not working.. Could you share it again please?
>
>
>
> --
> Sent from: http://spssx-discussion.1045642.n5.nabble.com/
>
> =====================
> 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
Reply | Threaded
Open this post in threaded view
|

Re: errors in DeCarlo's macro for multivariate normality

Andy W
And here is an updated dropbox link for my edited version,
https://dl.dropboxusercontent.com/s/an0t91qymssn1dg/Mult_Macro_fixAndy.sps?dl=0.



-----
Andy W
[hidden email]
http://andrewpwheeler.wordpress.com/
--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
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
Andy W
apwheele@gmail.com
http://andrewpwheeler.wordpress.com/