TITLE:
this is an example of a linear growth model
with missing data on a continuous outcome
using a missing data correlate to improve
the plausibility of MAR
y's are outcomes, x's covariates,
z missing data correlate.
Note that the variables in the
generated data are in a different
order than in the real-data version
in the User's Guide.
Note also that this is the same Monte Carlo
setup as for mcex11.1
MONTECARLO:
NAMES ARE x1 x2 y1-y4 z;
NOBSERVATIONS = 200;
NREPS = 1;
SEED = 4533;
GENERATE = x1(1);
CATEGORICAL = x1;
MISSING = x1 x2 y1-y4;
save = ex11.6.dat;
MODEL POPULATION:
x2@1; z@1;
[x1$1@0]; [z@0];
[x2@0];
i s | y1@0 y2@1 y3@2 y4@3;
[i*1 s*2];
i*1; s*.2; i WITH s*.1;
y1-y4*.5;
i ON x1*1 x2*.5;
s ON x1*.4 x2*.25;
z WITH y1-y4*.3;
z ON x1-x2*.2;
x1 ON x2*.2;
MODEL MISSING:
[y1-y4@-1];
y1 ON x1*.4 x2*.2;
y2 ON x1*.8 x2*.4;
y3 ON x1*1.6 x2*.8;
y4 ON x1*3.2 x2*1.6;
[x1-x2@-1.5];
ANALYSIS:
ESTIMATOR = ML;
INTEGRATION = MONTECARLO;
MODEL:
z*1;
i s | y1@0 y2@1 y3@2 y4@3;
[i*1 s*2];
i*1; s*.2; i WITH s*.1;
y1-y4*.5;
i ON x1*1 x2*.5;
s ON x1*.4 x2*.25;
z WITH y1-y4*.3;
z ON x1-x2*.2;
x2*1;
[x1$1*0];
x1 ON x2*.2;
z WITH i-s@0;
OUTPUT:
TECH9;