| Message/Author |
|
|
| Daniel posted on Wednesday, March 23, 2005 - 6:19 am
|
|
|
Hi, I'm trying to run the following model, but I'm getting an error message that I do not understand. For sake of parsimony, I only present code for 9th grade. Can you please provide some assistance?
My code, excluding the data statement and list of variables.
missing is .;
idvariable is id;
usevariables=smoker9-smoker12
u9-u12 y9-y12;
categorical are smoker9-smoker12;
define:
u9=1;
if (smoker9 eq 0) then u9=0;
if (smoker9 eq .) then u9=.;
y9=smoker9;
if (smoker9 eq 0) then y9=.;
analysis: type=basic;
Error message
*** ERROR
(SMOKER9 EQ .)
^
ERROR
*** ERROR
.
^
ERROR
*** ERROR
.
^
ERROR |
|
|
|
|
| IT looks like you have = . What do you mean by . That is not a valid statement except for the MISSING option. In the DEFINE command, use _MISSING to refer to a missing value. |
|
|
| Daniel posted on Wednesday, March 23, 2005 - 7:54 am
|
|
|
| Yes, . is missing in my data set. Do I need to recode my missing value. I'm not sure what you mean by _missing. |
|
|
|
|
No, you don't need to recode your missing vlaues. The _MISSING option is described in the Mplus User's Guide. Instead of
if (smoker9 eq .) then u9=.;
you would say
if (smoker9 eq .) then u9= _MISSING; |
|
|
| Daniel posted on Wednesday, March 23, 2005 - 8:39 am
|
|
|
Linda, I'm still getting the same error messages. Here is my code for 9th grade, two-part growth model, and the resulting error message.
!missing are .;
idvariable is id;
usevariables=smoker9-smoker12
y9 y10 y11 y12 u9 u10 u11 u12;
define:
u9=1;
if (smoker9 eq 0) then u9 = 0;
if (smoker9 eq .) then u9= _MISSING;
y9=smoker9;
if (smoker9 eq 0) then y9 = _missing;
Error message received
*** ERROR
(SMOKER9 EQ .)
^
ERROR
*** ERROR
(SMOKER10 EQ .)
^
ERROR
*** ERROR
(SMOKER11 EQ .)
^
ERROR
*** ERROR
(SMOKER12 EQ .)
^
ERROR
*** ERROR
(SMOKER9 EQ .)
^
ERROR
*** ERROR
Missing matching right parenthesis.
*** ERROR
(SMOKER10 EQ .)
^
ERROR
*** ERROR
Missing matching right parenthesis.
*** ERROR
(SMOKER11 EQ .)
^
ERROR
*** ERROR
Missing matching right parenthesis.
*** ERROR
(SMOKER12 EQ .)
^
ERROR
*** ERROR
Missing matching right parenthesis.
*** ERROR
Invalid symbol in data file:
"." at record #: 30, field #: 23 |
|
|
| bmuthen posted on Wednesday, March 23, 2005 - 10:10 am
|
|
|
Instead of
if (smoker9 eq .) then u9= _MISSING;
Try
if (smoker9 eq _MISSING) then u9= _MISSING;
If that doesn't work, send your input, output, and data to support@statmodel.com, giving your license number. |
|
|
| Daniel posted on Wednesday, March 23, 2005 - 11:02 am
|
|
|
| All messages sent to the email address support@statmodel.com are being kicked back as not deliverable. |
|
|
| bmuthen posted on Wednesday, March 23, 2005 - 11:10 am
|
|
|
| Not to worry - your message will be read. |
|
|
| MPI posted on Monday, April 11, 2016 - 1:34 am
|
|
|
Hi Linda and Bengt,
I am trying to fit a two-part growth curve model using repeated measure data from 20 time points. The dependent variable has a lot of zeros and missing values due to mortality during follow-up. As the missing due to mortality is likely to be missing not at random, I would like to combine the two-part model with the non-ignorable models. So far I fitted the data by two-part model (MAR) and two-part pattern-mixture model. When fitting the Diggle & Kenward’s two-part growth model, the computation is extremely slow (in fact, it is still running for days). The sample I am running is only 10% of our original sample (around 15,000 out of 150,000).
I think the extremely slow computing is related to the fact that I have too many dropout indicators (19 in total) in the model. If possible, is there a way to speed up the computation? Or there may be something wrong in my model, for example, trying to combine two-part model with the selection model?
Many thanks in advance. |
|
|
|
|
Check how many dimensions of integration you have (top of TECH8 screen output). If more than 3-4 you should switch to Montecarlo integration using fewer points. For instance, 4 dimensions gives 15*15*15*15 = 50625 points using regular integration. Here you can instead use Montecarlo integration with 5000 points.
Also, start with a smaller sample - perhaps 5% instead of 10. |
|
|
| MPI posted on Wednesday, April 13, 2016 - 6:07 am
|
|
|
Many thanks for your suggestions!
I just have a following-up question that, in the MNAR models, should I model the dropout/survival indicators in both the Y-part and U-part of the two-part model?
In my case, theoretically the survival is related to both U- and Y-part. |
|
|
|
|
| I don't think so. Dropout is the same for Y and U. |
|
|
| Back to top |
