Skip to main content

Table 1 Time series regression on the percentage of male births in East Germany, 1946-2011

From: Economic stress or random variation? Revisiting German reunification as a natural experiment to investigate the effect of economic contraction on sex ratios at birth

 

Model 1

Model 2

Model 3

Model 4

Model 5

 

Least squares model

ARMA (1,1)

Weighted least squares models

ARMA(1,1), ARCH(2)

Weighted by birth counts

Weights of models 3 & 4 combined

 

β (SE)

β (SE)

β (SE)

β (SE)

β (SE)

(Intercept)

30.225***

20.833***

30.282***

30.918***

31.221***

 

(8.729)

(.731)

(8.220)

(8.069)

(7.838)

Time Series

.581***

.724***

.580***

.575***

.569***

(West Germany)

(.136)

(.014)

(.127)

(.122)

(.117)

Year

-.004***

-.003***

-.004***

-.005***

-.005***

(.001)

(.000)

(.001)

(.001)

(.001)

Year = 1991

-.300*

-.138

-.299*

-.294

-.293

(.120)

(.108)

(.134)

(.152)

(.174)

AR(1)

 

.549***

.145

  
  

(.125)

(.385)

  

MA(1)

 

-1.000***

-.486

  
  

(.044)

(.365)

  

AIC

-88.2

-95.1

-91.5

-92.8

-92.7

R2

.683

-

.698

.710

.716

Adj. R2

.668

-

.684

.696

.702

Num. obs.

66

66

66

66

66

  1. Data source: Human Mortality Database[50], own calculations; ***p < .001, **p < .01, *p < .05.