Skip to main content
Journal for Labour Market Research

Table 3 Fractional logit regression models for RTW in orthopaedics

From: Return to work after medical rehabilitation in Germany: influence of individual factors and regional labour market based on administrative data

Predictors

M1

M2

(M1 + personal and rehabilitation biography)

M3

(M2 + employment biography)

M4

(M3 + interaction)

b

{AME}

s.e

b

{AME}

s.e

b

{AME}

s.e

b

{AME}

s.e

Unemployment rate (UR)

− 0.037 ***

0.004

− 0.040 ***

0.005

− 0.010 **

0.004

− 0.013 ***

0.004

 

{ − 3.1}

 

{ − 2,8}

 

{ − 0.2}

   

Prerehabilitation employment status [not employed, reference: employed]

    

− 1.272 ***

{ − 201.2}

0.012

− 1.338 ***

{ − 201.3}

0.029

UR * [not employed]

      

0.011 *

0.004

 {AME, subgroup “employed”}

      

{ − 0.4}

 

 {AME, subgroup “not employed”}

      

{ 0.2}

 

Random effects

    

 τ00, labour market region

0.01

0.01

 < 0.01

 < 0.01

 τ00, rehabilitation departments

0.05

0.05

0.01

0.01

 Pseudo-R2

0.019

0.144

0.363

0.363

 AIC

369,386

339,216

282,902

282,898

  1. Method is cross-classified fractional logit regression with n labour market regions = 257, n rehabilitation departments = 589, n patients = 305,980, * p < 0.05, ** p < 0.01, *** p < 0.001; estimators for intercept, for personal/rehabilitation biography predictors and employment biography predictors in Additional file 1
  2. M model, b  coefficients, s.e. standard error, AME  average marginal effects (in days), τ00  variance component of labour market region or rehabilitation department, R2  square of the correlation between the model’s predicted values and the actual values, AIC  Akaike-criterion
Back to article page