Skip to main content
IZA Journal of European Labor Studies

Table 4 Extended specification of matching model

From: Education and retirement: does University education at mid-age extend working life?

 

MALES

FEMALES

 

49-54

55-60

61-66

p-value

49-54

55-60

61-66

p-value

Matching 1:1

.017

.035

.069

.000

.012

.029

.060

.000

Trim 10%

.007

.023

.041

.016

.011

.028

.050

.000

Trim 20%

.008

.017

.032

.032

.009

.022

.046

.000

Trim 30%

.006

.004

.053

.001

.006

.011

.037

.004

Trim 40%

.009

.029

.074

.000

.007

.021

.040

.004

Trim 50%

.001

.008

.046

.017

.011

.022

.042

.005

Matching 4:1

.009

.016

.047

.000

.008

.018

.045

.000

Trim 10%

.008

.024

.057

.000

.009

.024

.053

.000

Trim 20%

.004

.018

.054

.000

.009

.021

.050

.000

Trim 30%

.003

.020

.065

.000

.008

.015

.047

.000

Trim 40%

.005

.024

.072

.000

.008

.012

.044

.000

Trim 50%

.006

.022

.066

.000

.007

.006

.038

.002

  1. Average differences in survival rates at different ages, p-values refer to log-rank tests of no differences.
  2. Note: The extended model includes all variables of the baseline model but also balances treated and matched comparisons on nine possible transitions in labor force status 1990–1991, between employment, unemployment and outside the labor force (OLF). OLF is defined as annual earnings below SEK 20,000 (app. $3,000) and no transfers related to unemployment insurance. Also included are indicator variables of newly married or divorced in 1991 and 1992, changes in amounts of social insurance benefits 1990–1991 and 1991–1992.
Back to article page