本人编了个程序 但是输出结果看不懂 求分析
The MI Procedure
Model Information
Data Set WORK.AN
Method MCMC
Multiple Imputation Chain Single Chain
Initial Estimates for MCMC EM Posterior Mode
Start Starting Value
Prior Jeffreys
Number of Imputations 3
Number of Burn-in Iterations 200
Number of Iterations 100
Seed for random number generator 1000
Missing Data Patterns
---------Group Means--------
Group fd yd Freq Percent fd yd
1 X X 10 83.33 1427.200000 1552.700000
2 X . 1 8.33 1670.000000 .
3 . X 1 8.33 . 1500.000000
EM (Posterior Mode) Estimates
_TYPE_ _NAME_ fd yd
MEAN 1443.583323 1566.268834
COV fd 20297 18105
COV yd 18105 19171
Multiple Imputation Variance Information
Relative Fraction
-----------------Variance----------------- Increase Missing Relative
Variable Between Within Total DF in Variance Information Efficiency
fd 67.570675 2296.676071 2386.770304 9.0144 0.039228 0.039115 0.987129
yd 134.311789 2310.170846 2489.253232 8.5565 0.077519 0.076709 0.975068
Multiple Imputation Parameter Estimates
Variable Mean Std Error 95% Confidence Limits DF Minimum Maximum Mu0
fd 1447.967609 48.854583 1337.478 1558.457 9.0144 1440.499848 1456.775451 0
yd 1567.960956 49.892417 1454.198 1681.724 8.5565 1555.076264 1577.533848 0
Multiple Imputation Parameter Estimates
t for H0:
Variable Mean=Mu0 Pr > |t|
fd 29.64 <.0001
yd 31.43 <.0001