Non-parametric decomposition and the choice of reference group

2015 ◽  
Vol 36 (8) ◽  
pp. 1266-1280 ◽  
Author(s):  
Sten Anspal
Keyword(s):  
Gender Wage Gap ◽  
Wage Gap ◽  
Reference Group ◽  
Wage Structure ◽  
Index Number ◽  
Content Type ◽  
Reference Category ◽  
Male Advantage ◽  
Parametric Decomposition ◽  
Non Parametric

Purpose – The Ñopo (2008) method of non-parametric decomposition, a matching-based alternative to Oaxaca (1973) and Blinder’s (1973) method of wage gap decomposition, is subject to the so-called “index number problem” common to the Oaxaca-Blinder and many related methods: its results are sensitive to the (arbitrary) choice of either male or female sex as the reference category in decomposition. The purpose of this paper is to address this issue by proposing an extension to the method that is invariant to the choice of reference category. Design/methodology/approach – The Ñopo method is modified such that the wage structure of the average worker instead of either male or female worker’s is used as the reference, enabling one to distinguish the “male advantage” and “female advantage” portions of the gender wage gap. As an illustration, a decomposition of the gender wage gap is performed with the modified method, using data from 15 OECD countries. Findings – The empirical results using the Ñopo decomposition indicate substantial differences in estimates of the unexplained gap depending on which sex is used as the reference category. Moreover, this disparity varies significantly with the choice of covariates used in the decomposition. This confirms there is significant cross-country variation in the asymmetry between male advantage and female disadvantage and that a decomposition method making this explicit would be relevant in real world settings. Originality/value – The extension of the Ñopo method proposed in this paper offers a way of decomposing the wage gaps in a way that is not sensitive to the choice of the reference category.

scholarly journals Mixing of Apples and Oranges in Milk Research: A Cohort Analysis of Non-Fermented Milk Intake and All-Cause Mortality

Nutrients ◽  
2020 ◽  
Vol 12 (5) ◽  
pp. 1393 ◽  
Author(s):  
Karl Michaëlsson ◽  
Liisa Byberg
Keyword(s):  
Milk Fat ◽  
Reference Group ◽  
Cohort Analysis ◽  
Fermented Milk ◽  
Fat Content ◽  
Milk Intake ◽  
P Value ◽  
Milk Consumption ◽  
Content Type ◽  
Reference Category

Mortality in relation to type of milk intake is unclear. We present mortality rates by intake of non-fermented milk fat content type and examine the degree of bias when other fat content types of non-fermented milk are kept in the reference category. For this purpose, we used a longitudinal cohort consisting of 61,433 women who had been administered food frequency questionnaires in 1987–1990 and in 1997, and analyzed time to death. Non-fermented milk consumption was divided into low ≤0.5%, medium 1.5%, or high fat 3%. For each specific type of milk, the first analysis (A) is restricted to those who consumed less than one serving per day of the other milk subtypes. In the second analysis (B), everyone is retained, i.e., leading to a reference category “contaminated” with other milk consumers. During follow-up, 22,391 women died. Highest (≥3 glasses/day) vs. lowest consumption category of milk (<1 glass/day) with 0.5% fat content was associated with a multivariable hazard ratio (HR) of 1.71 (95%CI 1.57–1.86) in analysis A, whereas the same comparison with a “contaminated” reference category in analysis B provided a HR of 1.34 (95%CI 1.24–1.45), p-value for homogeneity <0.0001. The corresponding HRs for 1.5% fat milk were: 1.82 (95%CI 1.63–2.04) and 1.38 (95%CI 1.25–1.51), and for 3% fat milk 1.95 (95%CI 1.77–2.15) and 1.40 (95%CI 1.29–1.52). HR for ≥3 glasses/day of total milk was 1.95 (95%CI 1.84–2.06). We observe a higher mortality in women with high milk consumption, irrespective of milk fat content. A “contaminated” reference group substantially attenuates the actual estimates.

scholarly journals Occupational segregation and wage differences: the case of Poland

2018 ◽  
Vol 39 (3) ◽  
pp. 378-397 ◽  
Author(s):  
Pawel Strawinski ◽  
Aleksandra Majchrowska ◽  
Paulina Broniatowska
Keyword(s):  
Gender Wage Gap ◽  
Wage Gap ◽  
Occupational Segregation ◽  
Wage Discrimination ◽  
Similar Proportion ◽  
Wage Gaps ◽  
Wage Differences ◽  
Occupational Groups ◽  
Men And Women ◽  
Content Type

Purpose The purpose of this paper is to analyse the relation between occupational segregation and the gender wage differences using data on three-digit occupational level of classification. The authors examine whether a statistically significant relation between the share of men in employment and the size of the unexplained part of the gender wage gap exists. Design/methodology/approach Traditional Oaxaca (1973) – Blinder (1973) decomposition is performed to examine the differences in the gender wage gaps among minor occupational groups. Two types of reweighted decomposition – based on the parametric estimate of the propensity score and non-parametric proposition presented by Barsky et al. (2002) – are used as the robustness check. The analysis is based on individual data available from Poland. Findings The results indicate no strong relation between occupational segregation and the size of unexplained differences in wages. The unexplained wage differences are the smallest in strongly female-dominated and mixed occupations; the highest are observed in male-dominated occupations. However, they are probably to a large extent the result of other, difficult to include in the econometric model, factors rather than the effects of wage discrimination: differences in the psychophysical conditions of men and women, cultural background, tradition or habits. The failure to take them into account may result in over-interpreting the unexplained parts as gender discrimination. Research limitations/implications The highest accuracy of the estimated gender wage gap is obtained for the occupational groups with a similar proportion of men and women in employment. In other male- or female-dominated groups, the size of the estimated gender wage gaps depends on the estimation method used. Practical implications The results suggest that decreasing the degree of segregation of men and women in different occupations could reduce the wage differences between them, as the wage discrimination in gender balanced occupations is the smallest. Originality/value To the best of the authors’ knowledge, this study is one of the few conducted at such a disaggregated level of occupations, and one of few studies focused on Central and Eastern European countries and the first one for Poland.

scholarly journals Gender wage gap and education: a stochastic frontier approach

2017 ◽  
Vol 38 (3) ◽  
pp. 504-516 ◽  
Author(s):  
Carmen Garcia-Prieto ◽  
Patricia Gómez-Costilla
Keyword(s):  
Gender Discrimination ◽  
Imperfect Information ◽  
Gender Wage Gap ◽  
Wage Gap ◽  
Stochastic Frontier ◽  
The European Union ◽  
Wage Differences ◽  
Stochastic Frontier Approach ◽  
Content Type ◽  
And Gender

Purpose The purpose of this paper is to get deeper insight into the measurement of gender wage gap. A proper method to identify which part of gender wage differences is due to discrimination against women is provided, and the relationship between wage differences and education is studied. Design/methodology/approach The stochastic frontier approach is employed to measure wage discrimination against women by using Spanish data from the European Union Statistics on Income and Living Conditions. Mentioned technique allows the authors to split the gender wage gap of workers displaying the same characteristics into two components: the first measures inefficiency in the job search process caused by imperfect information or gender differences concerning preferences regarding working conditions, where as the second takes account of discrimination. Findings A significant level of discrimination is found in the Spanish labour market at all educational levels, but this problem is quantitatively more important when low-educated workers are studied, and gender discrimination is lower for highly educated women. Originality/value In this paper, workers’ potential wage is estimated, and gender discrimination is measured by the gender potential wage gap, since it is not dependent on other wage determinants such as diverse preferences, unmeasured working abilities or imperfect information.

Education-based occupational segregation and the gender wage gap: evidence from France

2014 ◽  
Vol 35 (3) ◽  
pp. 368-391 ◽  
Author(s):  
Thomas Couppié ◽  
Arnaud Dupray ◽  
Stéphanie Moullet
Keyword(s):  
Wage Differential ◽  
Gender Wage Gap ◽  
Wage Gap ◽  
Occupational Segregation ◽  
Gender Composition ◽  
Public Authorities ◽  
Content Type ◽  
Occupational Gender ◽  
Occupation Level ◽  
Male Occupations

Purpose – The purpose of this paper is to test whether the gender wage gap at the beginning of the working life in France varies with the gender composition of occupations (male-dominated, female-dominated or mixed) and its main determinant (educational pre-sorting or labour market sorting). Design/methodology/approach – The first stage of the methodology is to decompose segregation indexes at occupation level into the two components of determination noted above. The occupations are then divided into five groups on the basis of their gender composition and the weight of the educational segregation. Oaxaca-Blinder decompositions are then applied to each group. Findings – Among 54 strongly gendered occupations, the segregation in 26 stems mainly from educational pre-sorting. This context is favourable to reduction of the gender wage gap. However, a modest wage differential is not proof of convergence towards equity, as it may conceal the existence of a significant discrimination component, as in male occupations. Research limitations/implications – The results relate to a cohort of French youth. The earnings-equalizing impact of education-based occupational segregation should be tested in other national contexts. Social implications – Public authorities should put in place incentives to encourage women's participation in a greater range of education and training courses and to improve the matching between education and the skill content of jobs. Originality/value – The originality lies in the suggestion that a strong connection between education and skill requirements helps to narrow the occupational gender wage gap.

It pays to be happy (if you are a man)

2014 ◽  
Vol 35 (3) ◽  
pp. 392-414 ◽  
Author(s):  
Vinod Mishra ◽  
Russell Smyth
Keyword(s):  
Subjective Wellbeing ◽  
Gender Wage Gap ◽  
Wage Gap ◽  
Ordinary Least Squares ◽  
Cross Sectional ◽  
Content Type ◽  
And Gender ◽  
The Relationship ◽  
Identification Strategy

Purpose – The purpose of this paper is to use cross-sectional data collected from six cities in China to examine the relationship between subjective wellbeing and male and female earnings and also to consider the contribution of differences in subjective wellbeing to explaining the gender wage gap. Design/methodology/approach – The paper uses survey data for 3,390 respondents working in a variety of blue collar and white collar jobs across a range of sectors including government, heavy and light manufacturing, mining and services in six Chinese cities: Chengdu, Dalian, Fushun, Fuxin, Fuzhou and Wuhan. The authors employ the ordinary least squares, Lewbel instrumental variable and Blinder-Oaxaca decomposition to econometrically analyze the relationship between subjective wellbeing and gender wage gap. Findings – The paper finds that the relationship between subjective wellbeing and wages is stronger for males than females. The authors note that 0.2 percent of the observed gender wage gap can be attributed to differences in mean subjective wellbeing in favor of females, while 53.5 percent can be ascribed to gender differences in returns to subjective wellbeing in favor of males. The paper also finds evidence that the relationship between subjective wellbeing and income is non-linear and that income peaks at higher levels of subjective wellbeing for men than women. Originality/value – The paper extends the existing literature in three important ways. First, the authors use a novel identification strategy, proposed by Lewbel (2012); second it uses a better measure for subjective wellbeing and third, it examine the role of differences in subjective wellbeing in explaining the gender wage gap.

Influences on the gender wage gap of Trinidad and Tobago

2015 ◽  
Vol 11 (2) ◽  
pp. 140-151 ◽  
Author(s):  
Reshma Mahabir ◽  
Dindial Ramrattan
Keyword(s):  
Trinidad And Tobago ◽  
Design Methodology ◽  
Gender Wage Gap ◽  
Wage Gap ◽  
Age Groups ◽  
Decomposition Analysis ◽  
Caribbean Region ◽  
Content Type ◽  
Significant Difference ◽  
Female Wages

Purpose – The purpose of this paper is to examine the presence of a gender wage gap in Trinidad and Tobago and its possible influences. Design/methodology/approach – Investigation of the issue utilised data from the 2008/2009 Household Budget Survey. A combination of linear regression and Oaxaca-Blinder decomposition analysis permits segregation of wage differences into explained and unexplained. Findings – At the aggregate level, there is a significant difference between male and female wages. Investigation showed that the demographics with the highest levels of discrimination were in the age groups 35-44, income levels $3,000-$5,999 and private sector employment vs public sector. Originality/value – The results of this research can serve as a useful tool for more gender-sensitive employment policies in Trinidad and Tobago, and possibly the wider Caribbean region.

scholarly journals Gender wage gap and its effect on test scores of immigrant students

2019 ◽  
Vol 46 (4) ◽  
pp. 872-887
Author(s):  
Eiji Yamamura
Keyword(s):  
Test Scores ◽  
Cognitive Skills ◽  
Immigrant Students ◽  
Gender Wage Gap ◽  
Wage Gap ◽  
School Attendance ◽  
Wage Level ◽  
Reverse Causality ◽  
Content Type ◽  
Female Wage

Purpose The purpose of this paper is to examine how gender equality influences difference in cognitive skills between genders. For the closer examination of Guiso et al. (2008), restricting the sample to immigrants allows us to reduce the possibility of reverse causality. Design/methodology/approach Using PISA 2012 matched with the gender wage gap sourced from World Economic Forum’s Global Gender Index 2011, the author compares the effect of the wage gap among the areas of mathematics, science and reading. Findings Decreased gender wage gap leads to girls exhibiting a reduced incidence of lateness and skipping school compared with boys, which in turn improves girls’ test scores in mathematics, science and reading. The direct effect of the decreased wage gap on test scores exceeds its indirect effect on performance owing to influencing school attendance. Originality/value The findings of this paper provide evidence that higher female wage level relative to male wage level incentivizes female students to attend school, resulting in their achieving higher test scores not only for mathematics, but also for science and reading.

The gender wage gap among Spanish managers

2014 ◽  
Vol 35 (3) ◽  
pp. 327-344 ◽  
Author(s):  
Sergio Scicchitano
Keyword(s):  
Glass Ceiling ◽  
Gender Wage Gap ◽  
Wage Gap ◽  
Decomposition Analysis ◽  
Wage Distribution ◽  
Pay Gap ◽  
Content Type ◽  
Ceiling Effects ◽  
Sticky Floor ◽  
Shaped Pattern

Purpose – The purpose of this paper is to investigate the existence of sticky floor and glass ceiling effects in the gender wage gap (GWG) among Spanish managers. In addition, the paper determines if the pay gap at every quantile is a result of the gender characteristic differences, or the differences in returns to those characteristics. Design/methodology/approach – The paper exploits a counterfactual decomposition analysis, using quantile regression, to decompose the GWG into one component that is based on differences in characteristics and one component that is based on differences in coefficients across the wage distribution. Findings – A significant GWG over all the wage distribution is found. Such a gap exhibits a clear U-shaped pattern, thus pointing out both significant sticky floor and glass ceiling effects. Furthermore, the paper shows that such pattern is mainly determined by the coefficient effect, whose relative incidence is almost continuously increasing along the wage distribution. Research limitations/implications – While it is difficult to give a definitive explanation for the significant U-shaped pattern in the GWG and for the bigger incidence of the glass ceiling, the authors suggest two possible explanations that are consistent with these findings. The paper leaves the identification of these explanations to future research. Practical implications – The pattern of rising coefficient effects at higher quantiles suggests that the glass ceiling is a more relevant question than the sticky floor. Indeed, at the highest wage quantiles, differences in characteristics make essentially no contribution to the overall wage gap. This suggests that upper-echelon female managers have the same characteristics as their male counterparts, which emphasizes the role of discrimination for these top-level jobs. Originality/value – Despite the general GWG has been largely investigated, the analysis of a wage differential among managerial workers has certainly drawn much less attention. In particular just a few papers have investigated the existence of sticky floors and glass ceiling among managers. In addition, as to Spain, there is no empirical survey investigating and decomposing the gender pay gap among managers.

Sign in / Sign up

Export Citation Format

Share Document