Skip to main content

Table 10 Dependent variable: duration in unemployment, measured in months

From: The unhappily unemployed return to work faster

 

OLS

StCox Model

 

(1)

(2)

(3)

(4)

(5)

(6)

(7)

(8)

 

OLS

OLS

ReturnWork

OLS

Cox

ReturnWork

Cox

SelfEmp

Loss

-1.291**

       
 

(0.507)

       

Δ H a p

 

0.236***

0.198***

0.219***

-0.0247***

-0.0284***

-0.0234**

-0.0223

  

(0.0584)

(0.0686)

(0.0571)

(0.00761)

(0.00951)

(0.0108)

(0.0213)

Men* Δ H a p

      

-0.00779

 
       

(0.0149)

 

Age

0.398**

0.412**

0.340*

0.514***

-0.0490***

-0.0261

-0.0325*

0.0254

 

(0.162)

(0.162)

(0.175)

(0.159)

(0.0179)

(0.0249)

(0.0178)

(0.0515)

Men

2.311***

2.386***

2.311***

3.230***

-0.306***

-0.298***

-0.153

-0.654***

 

(0.520)

(0.515)

(0.517)

(0.527)

(0.0598)

(0.0796)

(0.189)

(0.199)

Ed: Medium

-1.113*

-1.134*

-0.232

-0.371

0.0643

0.0788

0.136**

0.0423

 

(0.668)

(0.668)

(0.719)

(0.649)

(0.0689)

(0.0921)

(0.0680)

(0.218)

Ed: High

-1.756**

-1.755**

-0.608

-0.299

0.0682

0.0666

0.184**

0.563***

 

(0.689)

(0.687)

(0.661)

(0.680)

(0.0762)

(0.0953)

(0.0744)

(0.200)

Income: Benefits

   

0.00543***

-0.000508***

   
    

(0.00124)

(0.000137)

   

Income: Total

   

-0.000217***

2.17e-05***

   
    

(3.16e-05)

(2.93e-06)

   

Constant

-1.694

-2.408

-1.175

-3.117

    
 

(3.778)

(3.738)

(3.838)

(3.687)

    

Observations

1,445

1,445

892

1,445

1,342

822

1,342

161

R-squared

0.091

0.095

0.113

0.138

    

HH controls

Yes

Yes

Yes

Yes

Yes

Yes

Yes

No

Region+Wave

Yes

Yes

Yes

Yes

Yes

Yes

Yes

No

  1. Source: BHPS, waves 1–16, pooled data. Absolute value of t stat in parentheses. *significant at 10%, **significant at 5%, ***significant at 1%. The reference category for education is low educational achievement. Household controls include size, number of children, and marital status. Loss is a dummy = 1 when an individual reports a loss of happiness upon losing his job.
  2. Δ Hap measures the initial change in happiness when becoming unemployed. Given that most observations of Diff-hap are negative, the results have to be interpreted as follows: if happier about losing a job, then one spends more time in unemployment.
  3. Column “ReturnWork” is based on the sample of individuals who return to work after their unemployment spell.
Back to article page