Skip to main content

Table 3 Multilevel logistic regression on higher education

From: Social origin and educational attainment in China: a historical analysis of 70 birth cohorts

 

Model 1

Model 2

Model 3

Coef. (std.error)

Coef. (std.error)

Coef. (std.error)

Intercept (γ00)

− 2.0297(.1109)***

− 2.7717(.1273)***

− 2.7697(.1282)***

Male (γ10)

 

.4324 (.0344)***

.5438 (.0489)***

Urban (γ20)

 

.5720 (.0366)***

.4813 (.0528)***

Fmedu (γ30)

 

.1557 (.0052)***

.1506 (.0067)***

Fmisei (γ40)

 

.0354 (.0015)***

.0372 (.0019)***

 

Variance component

Variance component

Variance component

Intercept (σ2u0)

.8037***

1.0180***

1.0270***

Male (σ2u1)

  

7.108e−02***

Urban (σ2u2)

  

8.291e−02***

fmedu (σ2u3)

  

1.130e−03***

fmisei (σ2u4)

  

3.518e−05***

Error variance (σ2ε)

0.8655

.7856

0.7808

AIC

2787.6

22872.2

22751.1

BIC

27887.5

2293.0

22920.5

− log likelihood

13933.3

1143.0

11355.5

Individual observation

35400

35400

35400

Group observation

70

70

70

  1. AIC Akaike information criterion, BIC Bayesian information criterion
  2. ***p < 0.001