Mplus model502 模型讲解

来自图书《MPlus中介调节模型》

Mplus教程:平行多重中介模型(模型502)

  • 理论模型
  • 数学模型
  • 模型公式
  • 代码解读

理论模型

数学模型

数学公式1

模型公式:
Y1 = b0 + b1M + c1'X;
Y2 = b0 + b2M + c2'X;
M = a0 + a1X;

数学公式2

模型公式:
Y1 = b0 + b1M + c1'X;
Y2 = b0 + b2M + c2'X;
M = a0 + a1X;
代入和展开:
Y1 = b0 + b1(a0 + a1X) + c1'X;
Y2 = b0 + b2(a0 + a1X) + c2'X;
展开后:
Y1 = b0 + a0b1 + a1b1X + c1'X;
Y2 = b0 + a0b2 + a1b2X + c2'X;

数学公式3

模型公式:
Y1 = b0 + b1M + c1'X;
Y2 = b0 + b2M + c2'X;
M = a0 + a1X;
代入和展开:
Y1 = b0 + b1(a0 + a1X) + c1'X;
Y2 = b0 + b2(a0 + a1X) + c2'X;
展开后:
Y1 = b0 + a0b1 + a1b1X + c1'X;
Y2 = b0 + a0b2 + a1b2X + c2'X;
整理成 Y = a + bX 的形式:
Y1 = (b0 + a0b1) + (a1b1 + c1')X;
Y2 = (b0 + a0b2) + (a1b2 + c2')X;

数学公式4

模型公式:
Y1 = b0 + b1M + c1'X;
Y2 = b0 + b2M + c2'X;
M = a0 + a1X;
代入和展开:
Y1 = b0 + b1(a0 + a1X) + c1'X;
Y2 = b0 + b2(a0 + a1X) + c2'X;
展开后:
Y1 = b0 + a0b1 + a1b1X + c1'X;
Y2 = b0 + a0b2 + a1b2X + c2'X;
整理成 Y = a + bX 的形式:
Y1 = (b0 + a0b1) + (a1b1 + c1')X;
Y2 = (b0 + a0b2) + (a1b2 + c2')X;
效应:
X 对 Y1 的间接效应: a1b1
X 对 Y2 的间接效应: a1b2
X 对 Y1 的直接效应: c1'
X 对 Y2 的直接效应: c2'

代码解读1

! Predictor variables - X
! Mediator variable(s) – M
! Moderator variable(s) - none
! Outcome variable - Y1, Y2

代码解读2

! Predictor variables - X
! Mediator variable(s) – M
! Moderator variable(s) - none
! Outcome variable - Y1, Y2
USEVARIABLES = X1 M Y1 Y2;

代码解读3

! Predictor variables - X
! Mediator variable(s) – M
! Moderator variable(s) - none
! Outcome variable - Y1, Y2
USEVARIABLES = X1 M Y1 Y2;
ANALYSIS:
 TYPE = GENERAL;
 ESTIMATOR = ML;
 BOOTSTRAP = 10000;

代码解读4

! Predictor variables - X
! Mediator variable(s) – M
! Moderator variable(s) - none
! Outcome variable - Y1, Y2
USEVARIABLES = X1 M Y1 Y2;
ANALYSIS:
 TYPE = GENERAL;
 ESTIMATOR = ML;
 BOOTSTRAP = 10000;
! In model statement name each path using parentheses
MODEL:

代码解读5

! Predictor variables - X
! Mediator variable(s) – M
! Moderator variable(s) - none
! Outcome variable - Y1, Y2
USEVARIABLES = X1 M Y1 Y2;
ANALYSIS:
 TYPE = GENERAL;
 ESTIMATOR = ML;
 BOOTSTRAP = 10000;
! In model statement name each path using parentheses
MODEL:
Y1 ON M (b1);
Y2 ON M (b2);
Y1 ON X (cdash1);
Y2 ON X (cdash2);
M ON X (a1);

代码解读6

! Predictor variables - X
! Mediator variable(s) – M
! Moderator variable(s) - none
! Outcome variable - Y1, Y2
USEVARIABLES = X1 M Y1 Y2;
ANALYSIS:
 TYPE = GENERAL;
 ESTIMATOR = ML;
 BOOTSTRAP = 10000;
! In model statement name each path using parentheses
MODEL:
Y1 ON M (b1);
Y2 ON M (b2);
Y1 ON X (cdash1);
Y2 ON X (cdash2);
M ON X (a1);
! Use model constraint to calculate indirect and total effects
MODEL CONSTRAINT:
 NEW(a1b1 a1b2 TOTALY1 TOTALY2);
a1b1 = a1*b1;
a1b2 = a1*b2;
TOTALY1 = a1*b1 + cdash1;
TOTALY2 = a1*b2 + cdash2;

代码解读7

! Predictor variables - X
! Mediator variable(s) – M
! Moderator variable(s) - none
! Outcome variable - Y1, Y2
USEVARIABLES = X1 M Y1 Y2;
ANALYSIS:
 TYPE = GENERAL;
 ESTIMATOR = ML;
 BOOTSTRAP = 10000;
! In model statement name each path using parentheses
MODEL:
Y1 ON M (b1);
Y2 ON M (b2);
Y1 ON X (cdash1);
Y2 ON X (cdash2);
M ON X (a1);
! Use model constraint to calculate indirect and total effects
MODEL CONSTRAINT:
 NEW(a1b1 a1b2 TOTALY1 TOTALY2);
a1b1 = a1*b1;
a1b2 = a1*b2;
TOTALY1 = a1*b1 + cdash1;
TOTALY2 = a1*b2 + cdash2;
OUTPUT:
 STAND CINT(bcbootstrap);

代码解读8

! Predictor variables - X
! Mediator variable(s) – M
! Moderator variable(s) - none
! Outcome variable - Y1, Y2
USEVARIABLES = X1 M Y1 Y2;
ANALYSIS:
 TYPE = GENERAL;
 ESTIMATOR = ML;
 BOOTSTRAP = 10000;
! In model statement name each path using parentheses
MODEL:
Y1 ON M (b1);
Y2 ON M (b2);
Y1 ON X (cdash1);
Y2 ON X (cdash2);
M ON X (a1);
! Use model constraint to calculate indirect and total effects
MODEL CONSTRAINT:
 NEW(a1b1 a1b2 TOTALY1 TOTALY2);
a1b1 = a1*b1;
a1b2 = a1*b2;
TOTALY1 = a1*b1 + cdash1;
TOTALY2 = a1*b2 + cdash2;
OUTPUT:
 STAND CINT(bcbootstrap);
MODEL:
 Y1 ON X M;
 Y2 ON X M;
 M ON X;

代码解读9

! Predictor variables - X
! Mediator variable(s) – M
! Moderator variable(s) - none
! Outcome variable - Y1, Y2
USEVARIABLES = X1 M Y1 Y2;
ANALYSIS:
 TYPE = GENERAL;
 ESTIMATOR = ML;
 BOOTSTRAP = 10000;
! In model statement name each path using parentheses
MODEL:
Y1 ON M (b1);
Y2 ON M (b2);
Y1 ON X (cdash1);
Y2 ON X (cdash2);
M ON X (a1);
! Use model constraint to calculate indirect and total effects
MODEL CONSTRAINT:
 NEW(a1b1 a1b2 TOTALY1 TOTALY2);
a1b1 = a1*b1;
a1b2 = a1*b2;
TOTALY1 = a1*b1 + cdash1;
TOTALY2 = a1*b2 + cdash2;
OUTPUT:
 STAND CINT(bcbootstrap);
MODEL:
 Y1 ON X M;
 Y2 ON X M;
 M ON X;
MODEL INDIRECT:
 Y1 IND X;
 Y2 IND X;

资源汇总

  • 本视频讲义地址: https://mlln.cn/mplus-model-templates/model502.html
  • 图书《MPlus中介调节模型》打包下载: 点击下载
  • 图书《MPlus中介调节模型》在线看: 点击查看
  • 视频教程: 点击这里打开视频
  • Mplus 模型模板教程列表: https://mlln.cn/mplus-model-templates
  • 统计咨询: https://wx.zsxq.com/group/88888188828842