How to estimate two level random effects model using M-Plus?

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

I am attempting to conduct a complex twolevel random analysis in Mplus. There are two cluster variables: TID (class) and TUTORG (tutor group). We're examining the effects of two active tutoring treatments (TRT) on performance (ponavgline). We also are controlling for pretesting on performance (pravgline). I am interested in examining the random effects of tutoring clusters. Does anyone know how to estimate two level random effects model using M-Plus?

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：estimate effects Effect random model interested complex conduct active where

DEFINE: CENTER prnavgline (GRANDMEAN); VARIABLE:
    NAMES ARE STID TID TUTORG TRT prnavgline ponavgline PRcalc POcalc prnptot ponptot
    activetx;
USEVARIABLES ARE TID TUTORG  prnavgline ponavgline;

    USEOBSERVATIONS ARE activetx eq 1;
    WITHIN = prnavgline;
    cluster = TID TUTORG;
    missing are blank;


    ANALYSIS:
      TYPE = COMPLEX TWOLEVEL RANDOM;
      MODEL:
     %WITHIN%
    s1 | ponavgline ON prnavgline;
    %BETWEEN%
    ponavgline s1;
    ponavgline with s1;

Hello,
Concerning the model below, I've determined that the random effects due to the TUTORG group are negligable.  I am therefore interested in running a TWOLEVEL analysis (no longer including the COMPLEX specification e and no longer accounting for the TUTORG clusters). I also removed the random slope of pre-performance predicting postperformance, and thus the need for the RANDOM specification.  Treatments 1 and 2 are included as dummy variables relative to a control group. However, when I attempt to specify the model, I obtain the error noted below.  Does anyone have experience with this error?  Is there a way to run the model ignoring the TUTORG cluster?
ERROR:
One or more between-level variables have variation within a cluster for   one or more clusters.  Check your data and format statement.

     Between    Cluster ID with variation in this variable
     Variable     (only one cluster ID will be listed)

      TRT_1      56
      TRT_2      48


Here is the model:


DEFINE: CENTER PRcalc(GRANDMEAN);
VARIABLE:
NAMES ARE STID TID TUTORG TRT prnl02avgdif ponl02avgdif PRcalc POcalc prnptot ponptot
  trt_1 trt_2 control trt1vs2 activetx;

USEVARIABLES ARE TID trt_1 trt_2 PRcalc POcalc;
WITHIN = PRcalc;
BETWEEN = trt_1 trt_2;
cluster = TID;
missing are blank;

ANALYSIS:
TYPE = TWOLEVEL;

      MODEL:
     %WITHIN%
  POcalc ON PRcalc ;
    %BETWEEN%
  POcalc;
  POcalc ON trt_1;
  POcalc ON trt_2;