Error No. 59 ?! PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Mehdi Tav posted on Sunday, March 25, 2012 - 8:18 am
Hi, I have developed a CFA model using summary data but at the first step an error occurred as below:
*** ERROR
(Err#: 59)
Error reading summary data

I tried and searched a lot, but couldn't find what is it about

my code is:
TITLE: Project
DATA:
FILE IS 'final.dat';
TYPE IS CORR MEANS STDEVIATIONS ;
NOBSERVATIONS ARE 263;
VARIABLE:
NAMES ARE w1 w2 w3 fort uf1 uf2 das1 das2 das3 eba stt mii;
ANALYSIS:
ESTIMATOR = ML ;
MODEL:
job by w1* w2 w3;
subj by fort* uf1 uf2;
dys by das1* das2 das3;
constr by eba* stt mii;

dys on constr;
subj on dys;
job on subj;
job on dys;
constr@1;
dys@1;
subj@1;
job@1;

OUTPUT: TECH1 TECH8;
sampstat; stand; res;

Would you please kindly help me?
best
 Linda K. Muthen posted on Sunday, March 25, 2012 - 8:32 am
See pages 456-457 of the user's guide to see how the data should be set up for TYPE IS CORR MEANS STDEVIATIONS ; If this does not help, send your input, data, output, and license number to support@statmodel.com.
 Russell Warne posted on Monday, July 30, 2018 - 1:45 pm
I'm having the same problem on Version 6.11. Pages 456-457 of the user's manual don't help. I can't even get the example data to work.

I think the problem is in how the datafile is set up, but I'm not sure. I have the first line of the data file as the means. The second line is the SD's. The next lines are the bottom triangle in the correlation matrix. I have each number in the lines separated by a space.

Thanks, in advance.
 Linda K. Muthen posted on Monday, July 30, 2018 - 3:36 pm
If your data are in the form of means, standard deviations, and correlations, the data should appear as follows with means on line 1, standard deviations on line 2, and correlations in one of the two ways shown below. These are in an external file which is references in the FILE option.

.4 .6 .3 .5 .5
.2 .5 .4 .5 .6
1.0
.86 1.0
.56 .76 1.0
.78 .34 .48 1.0
.65 .87 .32 .56 1.0

or alternatively:

.4 .6 .3 .5 .5
.2 .5 .4 .5 .6
1.0 .86 1.0 .56 .76 1.0 .78 .34 .48 1.0 .65 .87 .32 .56 1.0
 Russell Warne posted on Tuesday, July 31, 2018 - 10:44 am
The first version is exactly what I have for the datafile. Here is my input:

TITLE: Example CFA
DATA: FILE is DS1.txt;
TYPE is CORRELATION MEANS STDEVIATIONS;
NOBSERVATIONS are 204;
VARIABLE: NAMES are Y1-Y5;
MODEL: f1 BY Y1-Y5;
f1@1;
OUTPUT: STANDARDIZED;


When I run that, I get:
*** ERROR
(Err#: 59)
Error reading summary data
 Linda K. Muthen posted on Tuesday, July 31, 2018 - 11:52 am
Open the summary data file is Excel. Say Save as. Is the file unicode? If so resave it as a DOS txt file.
 Russell Warne posted on Tuesday, July 31, 2018 - 12:07 pm
That fixed it. Thank you!
 Gizem posted on Tuesday, June 09, 2020 - 5:30 am
I have the same problem; tried the solutions mentioned above, but could not fix it. Would you please recommend something?

I want to test the unidimensionality of my test items (11 items from a scale) and here is the simplified version of my syntax. I am not sure, why I keep receiving the error.

Looking forward to your feedback!

data:
file = xxx;
type = covariance;
nobservations = xx;

variable:
names = xxx;
usevar = xxx;

model:

F1 BY xxx yyy zzz qqq;


*** ERROR
(Err#: 59)
Error reading summary data
 Linda K. Muthen posted on Tuesday, June 09, 2020 - 1:07 pm
Please send the output, data set, and your license number to support@statmodel.com.
 David Francis posted on Saturday, June 20, 2020 - 1:36 pm
For what it's worth, I encountered this problem and tried all of the recommendations above without success. When I saved the file as a .prn file (printer file that is space delimited), MPLUS read the file correctly.
 Gizem posted on Tuesday, June 23, 2020 - 8:18 am
Thanks for the suggestion David. I tried it, however it did not work out for me.

Dear Linda,
I have been struggling with the problem for a while and couldn't get any help from the MPlus discussion forum. I can't send the data set either because of the data protection policies of my research project, and the problem couldn't be solved, when I only sent my output to the support e-mail.

I have been using the same data file to test other stuff, so I belive it shouldn't be the problem, it's probably rather something in the syntax. Do you have any suggestions; what could be the problem?

Thank you.
 Linda K. Muthen posted on Tuesday, June 23, 2020 - 9:51 am
Please send the output, data set, and your license number to support@statmodel.com.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: