最近在写毕业论文,老师让我用Mplus做跨层分析,首先要进行跨层验证性因子分析。
我的语句如下:
DATA:
FILE IS C:\Users\Mplus 匹配 Mplus.dat;
VARIABLE:
MISSING ARE ALL (999);
NAMES ARE GROUP CSE1 CSE2 CSE3 CSE4 CSB1 CSB2 CSB3 CSB4 CSB5
DLA1_1 DLA2_1 DLA3_1 DLA4_1 DLB1_1 DLB2_1 DLB3_1 DLB4_1
DLB5_1 DLB6_1 DLB7_1 DLB8_1 DLB9_1 DLB10_1 DLB11_1 DLB12_1;
USEVARIABLES=GROUP CSE1 CSE2 CSE4 CSB1-CSB5 DLA1_1-DLA3_1 DLB1_1-DLB12_1;
CLUSTER IS GROUP;
BETWEEN=DLA1_1-DLA3_1 DLB1_1-DLB12_1;
ANALYSIS:
ESTIMATOR=MLR;
TYPE=TWOLEVEL;
MODEL:
%WITHIN%
CSEw BY CSE1 CSE2 CSE4;
CSBw BY CSB1-CSB5;
%BETWEEN%
F1 BY DLA1_1-DLA3_1;
F2 BY DLB1_1-DLB3_1;
F3 BY DLB4_1-DLB6_1;
F4 BY DLB7_1-DLB9_1;
F5 BY DLB10_1-DLB12_1;
CSEb BY CSE1 CSE2 CSE4;
CSBb BY CSB1-CSB5;
OUTPUT:SAMPSTAT;
以上语句是可以跑出结果的,但是有三个warning,我想把它们解决掉。
第一个warning:
One or more individual-level variables have no variation within a
cluster for the following clusters.
Variable Cluster IDs with no within-cluster variation
CSE1 12 21 16 42 45 48 40 44 34 49 35 9 39 59 60 17
CSE2 12 8 21 16 42 35 36 9 59 60 17
CSE4 7 12 21 16 42 50 56 49 9 39 60 17
CSB1 7 12 21 16 25 62 18 9 39 60 17
CSB2 7 12 8 21 16 25 11 42 62 9 39 60 17
CSB3 7 12 8 21 16 11 42 48 43 36 39 60 17
CSB4 7 12 8 21 16 25 42 45 62 2 18 54 60 17
CSB5 7 12 21 16 11 42 2 43 18 46 9 39 59 60 17
第二个warning是:
THE MODEL ESTIMATION HAS REACHED A SADDLE POINT OR A POINT WHERE THE
OBSERVED AND THE EXPECTED INFORMATION MATRICES DO NOT MATCH.
AN ADJUSTMENT TO THE ESTIMATION OF THE INFORMATION MATRIX HAS BEEN MADE.
THE CONDITION NUMBER IS -0.864D-04.
THE PROBLEM MAY ALSO BE RESOLVED BY DECREASING THE VALUE OF THE
MCONVERGENCE OR LOGCRITERION OPTIONS OR BY CHANGING THE STARTING VALUES
OR BY USING THE MLF ESTIMATOR.
THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES MAY NOT BE
TRUSTWORTHY FOR SOME PARAMETERS DUE TO A NON-POSITIVE DEFINITE
FIRST-ORDER DERIVATIVE PRODUCT MATRIX. THIS MAY BE DUE TO THE STARTING
VALUES BUT MAY ALSO BE AN INDICATION OF MODEL NONIDENTIFICATION. THE
CONDITION NUMBER IS -0.276D-16. PROBLEM INVOLVING THE FOLLOWING PARAMETER:
Parameter 68, %BETWEEN%: DLB9_1
THE NONIDENTIFICATION IS MOST LIKELY DUE TO HAVING MORE PARAMETERS THAN THE
NUMBER OF CLUSTERS. REDUCE THE NUMBER OF PARAMETERS.
第三个warning是:
THE RESIDUAL COVARIANCE MATRIX (THETA) IS NOT POSITIVE DEFINITE.
THIS COULD INDICATE A NEGATIVE VARIANCE/RESIDUAL VARIANCE FOR AN OBSERVED
VARIABLE, A CORRELATION GREATER OR EQUAL TO ONE BETWEEN TWO OBSERVED
VARIABLES, OR A LINEAR DEPENDENCY AMONG MORE THAN TWO OBSERVED VARIABLES.
CHECK THE RESULTS SECTION FOR MORE INFORMATION.
这些分别都是什么意思呢?我该怎么处理呢?
对第一个warning,我有试着将它指出的数据都删除,最后warning确实消失了,但是数据样本大大减少了,有什么别的颁发能解决呢?