# Exercises 3.1 - 3.2

## Exercise 3.1

To be able to do a T-test analysis, you need to have software (SPSS) installed on your computer, and you should download and use the dataset Family, Gender and Work.

Test the following hypotheses for Germany and Spain:

1. Women in the labour force (working women) are more educated on average than women who are not in the labour force.
2. The education gap between working and non-working women is larger in the family-dependence regime than in the state-dependence regime.

### Procedure:

• Create a subset including Germany and Spain
• Select women only (gender = 0).
• For each country, calculate the mean years of schooling (eduyrs) by women's work status (work_sta). Perform an ‘Independent-Samples T-test’ from the ‘Compare Means’ alternative on the ‘Analysis menu’. Use ‘work_sta’ as the grouping variable.

### Questions:

1. When you compare the mean number of years of schooling for working and non-working women in each country, do the results support the first hypothesis? Explain.
2. When you examine the education gap between working and non-working women for each of the two countries, do the results support your second hypothesis? Explain.
SPSS syntax
*You need to have a copy of SPSS installed on your computer, and you should download and use the dataset Family, Gender and Work.
*Open SPSS by clicking on the appropriate link.
*Open the ESS data by clicking ‘File’, ‘Open’, and ‘Data’ on the SPSS menu bar before you select the folder and the data set.
*Open a new syntax window by clicking ‘File’, ‘New’, and ‘Syntax’ on the SPSS menu bar.
*You can copy the syntax below and paste it into the syntax window in SPSS.
*Execute the syntax using the 'Run' option on the menu bar.

*Commands must always end with a dot.

* The following command causes the cases to be weighted by the design weight variable 'dweight'.

WEIGHT BY dweight.

*Create filter variable - only include women from Germany and Spain.

USE ALL.
COMPUTE filter_\$=(cntry ='DE' | cntry ='ES') & gender = 0.
VARIABLE LABEL filter_\$ 'cntry = DE or ES & gender = 0 (FILTER)'.
VALUE LABELS filter_\$ 0 'Not Selected' 1 'Selected'.
FORMAT filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

SORT CASES BY cntry.
SPLIT FILE, SEPARATE BY cntry.

T-TEST
GROUPS=work_sta(1 0)
/MISSING=ANALYSIS
/VARIABLES=eduyrs
/CRITERIA=CIN(.95).

*Turn off the split file and weight, and select all cases.

SPLIT FILE OFF.
WEIGHT OFF.
USE ALL.
Sample solution

1. The results support the first hypothesis, both in Germany and in Spain. In Germany, the mean number of years of schooling for women in the labour market is 13.7, and it is a year lower for women not in the labour market. This difference is statistically significant. The figures for Spain are 13.6 years of schooling among women in the labour force and 10.2 years for women not in the labour force. This difference is also statistically significant.
2. The results support the second hypothesis, as the education gap in Spain is more than three years and only one year in Germany.

## Exercise 3.2

1. How does the presence of young children affect the likelihood that a woman will participate in the labour market, and how might this differ by regime type (examine women in the relevant age group which we define as 25-45)?
2. Suggest hypotheses and test them using data from Germany Spain and Denmark.

### Procedure:

• Subset the data set to include Germany, Spain and Denmark.
• Select only women (gender = 0) aged 25-45 (25<=age=<45).
• For each country, create a cross-tabulation with 'Children under 12 living with you' as the column variable and women’s work status (Working status, paid work as main activity last 7 days (mnactic=1)) as the row variable.
• Calculate percentages within columns.

### Questions:

1. Are women with children more or less likely to be working? Are the results consistent with your hypothesis?
2. Are there differences in the relationship between the presence of children and women’s work status between the countries? Discuss the results in light of the second hypothesis.
Nesstar
• Open the dataset Family, Gender and Work
• Click the ‘Tabulation’ tab
• Click the icon for weighting, and select ‘dweight’
• Click the variable ‘Gender’ and select ‘Use as filter’, select women from the tab above the table
• Click the icon for subset, use the variable ‘yrbrn’ and the two conditions ‘age >= 25 & age <= 45’
• Click the variable ‘country’ and select ‘Use as filter’
• Click the variable ‘work_sta’ and select ‘Add to row’
• Click the variable children and select ‘Add to column’
SPSS syntax
*You need to have a copy of SPSS installed on your computer, and you should download and use the dataset Family, Gender and Work.
*Open SPSS by clicking on the appropriate link.
*Open the ESS data by clicking ‘File’, ‘Open’, and ‘Data’ on the SPSS menu bar before you select the folder and the data set.
*Open a new syntax window by clicking ‘File’, ‘New’, and ‘Syntax’ on the SPSS menu bar.
*You can copy the syntax below and paste it into the syntax window in SPSS.
*Execute the syntax using the 'Run' option on the menu bar.

*Commands must always end with a dot.

* The following command causes the cases to be weighted by the design weight variable 'dweight'.

WEIGHT BY dweight.

*Create filter variable - only include women from Germany, Denmark and Spain in the age group 25-45.

USE ALL.
COMPUTE filter_\$=(cntry = 'DE' | cntry = 'DK' | cntry = 'ES') & (age>=25 & age <= 45) & gender=0.
VARIABLE LABEL filter_\$ '(cntry = DE OR DK OR ES) & (age>=25 & age <= 45) & gender=0 (FILTER)'.
VALUE LABELS filter_\$ 0 'Not Selected' 1 'Selected'.
FORMAT filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

SORT CASES BY cntry.
SPLIT FILE SEPARATE BY cntry.

CROSSTABS
/TABLES= work_sta BY children
/FORMAT= AVALUE TABLES
/STATISTIC=CHISQ PHI
/CELLS= COUNT COLUMN.

*Turn off the split file and weight, and select all cases.

SPLIT FILE OFF.
WEIGHT OFF.
USE ALL.
Sample solution

### Problem

First Hypothesis: The presence of children is likely to reduce the tendency for women to participate in the labour market in all countries.

Second Hypothesis: In the individual-independence regime (represented by Denmark), mothers are almost as likely to participate in the labour market as women without children, as this is encouraged by their ideology and institutional arrangements. The lowest participation of mothers in the labour market is likely in Germany, as the state-dependence regime encourages mothers to withdraw from the labour market and provides economic support. The likelihood of Spanish mothers participating in the labour market should be intermediate.