• The Korean Journal of Applied Statistics
• /
• v.16 no.2
• /
• pp.283-291
• /
• 2003

The Gini index is one of the most commonly used measures of inequality of income distributions. In this paper, the Lorenz curve is estimated by arcs of two optimal circles, and a new simple method to estimate the Gini index is proposed using the law of cosines. We compare the proposed estimator with the estimator proposed by Ogwang and Rao(1996) in terms of the mean squared error(MSE) though Monte Carlo simulation in a Pareto distribution.

• Journal of the Korean Data and Information Science Society
• /
• v.6 no.1
• /
• pp.97-103
• /
• 1995

In this paper, we propose estimators of Gini index of the exponential distribution. We also obtain the distribution and the moments of the proposed estimators. The moments of the proposed estimators are derived by special function. We compare the maximum likelihood estimator (MLE) of Gini index with the proposed estimator of Gini index in the sense of MSE through Monte Carlo Method.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.05a
• /
• pp.121-126
• /
• 2003

소득분배의 가장 대표적인 불평등척도는 Gini index이며, 이것은 통계학자인 Gini가 제안한 지표로서 소득분배에 관한 분석에서 가장 널리 이용되고 있다. 본 논문에서는 두 원의 호에 의해 Lorenz 곡선을 추정하고 코사인법칙을 이용하여 Gini index를 추정하기 위한 새로운 간편한 방법을 제시하여, 소득분포를 따르는 파레토분포에서 모의실험을 통해 Ogwang and Rao (1996)의 추정방법과 평균제곱오차 면에서 비교 분석한다.

• Communications for Statistical Applications and Methods
• /
• v.8 no.1
• /
• pp.249-256
• /
• 2001

We shall derive the MLE and UMVUE of Lorenz Curve and Gini Index in a Pareto distribution with the pdf(1.1) and their variances. And compare mean square errors(MSE) of the MLE and UMVUE of the Lorenz Curve and Gini Index in a Pareto distribution with pdf(1.1).

• Korea Journal of Hospital Management
• /
• v.16 no.3
• /
• pp.1-18
• /
• 2011

In this study, population census(2005 & 2008) from Statistics Korea and the statistical data of the number of hospital beds by healthcare facilities classification from Ministry of Health and Welfare were used. For analyzing distribution of hospital beds, hospital beds were classified as acute care beds, long-term care beds and all hospital beds, which is including acute and long-term care beds. Regional areas, which are city(si), county(goon) for the study and district(gu) were reclassified as metropolitan city, city(si) and county(goon). Because there were 165 regional areas in 2005 and 2008, 84 and 81 areas were classified as metropolitan city and/or city and county, respectively. Gini index were calculated for hospital beds from each year, and Lorenz curves were drawn. The following summary presents the findings of this study. Compared to the year 2005 and 2008, the Gini index was 0.24472, and hospital bed numbers increased slightly by 0.80% than in 2005. In case of acute care beds, the Gini index was 0.23797(0.13%), and there was no big difference; however, the Gini index for long-term care beds was 0.41091, and there was a 30.25% decrease, which shows improvement to reduce disparities. It might result from an increase in long-term care beds up to 476.2%. For geographical equality of hospital beds, the Gini index and Lorenz curve, which can be compared the degree of inequality in the distribution of hospital beds reasonably and possibly show statistical data, should be used. Through this study, the distribution policy of hospital beds should be established.

• Journal of applied mathematics & informatics
• /
• v.5 no.1
• /
• pp.213-222
• /
• 1998

In this paper we propose several estimators of Gini index of the two-parameter exponential distribution and obtain dis-tributions and moments of the proposed estimators. The proposed estimators are shown to cosistency and will be compares in terms of the proposed estimators. The proposed estimators are shown to cosistency and will be compared in terms of the mean squared error (MSE) through Monte Carlo method.

• Journal of Korean Society of Forest Science
• /
• v.95 no.4
• /
• pp.476-483
• /
• 2006

This study tried to estimate the concentration indices of 15 forested national parks using Gini coefficient and Lorenz curve which can be measure the degree of inequality. The concentration indices were estimated by two parts which are yearly index for the periods of 1997-2005 and travel origin area(city or province) distribution index each national park. The empirical results were as follows: first, yearly Gini coefficients showed severe inequality. Particularly, 2004 and 2005 Gini coefficients were .453 and .446. which are intensive inequality compared with other years. Second, in travel origin area distribution each national park, Gini coefficients of Bukhansan and Kyeryungsan national park were .916 and .855 which are the great inequality compared with other national parks. The other hand, Gini coefficients of Dukyusan and Byunsanbando national parks were .508 and .628 which are the lowest inequality. The national park policy manager should find out the factors of concentration and deconcentration each year and national park and decided the visitor distribution policy which visitor size and scope for balancing the natural resources use.

• Korean Journal of Social Welfare Studies
• /
• v.41 no.1
• /
• pp.65-84
• /
• 2010

The purpose of Inequality Index Decomposition is to know the cause of overall inequality through decomposing aggregate inequality index into relevant components. Previous studies have mostly focused on the absolute contribution meaning that how much each component possesses out of overall inequality. However it could be more important to know the marginal contribution and inequality effect of each component in order to implement policies reducing overall inequality effectively. For this, we decomposed Gini Coefficient as representative inequality index into income sources or social welfare programs and calculated each Gini Income Elasticity(GIE). Analysis result says that regular employee income and employer(or the self-employed) income, of which GIE are 1.205 and 1.867, are classified as inequality-increasing income source. GIE can be one of good methods to analyse the inequality effect of various income sources and social welfare programs.

• Communications for Statistical Applications and Methods
• /
• v.24 no.4
• /
• pp.339-351
• /
• 2017

Resampling approaches were the first techniques employed to compute a variance for the Gini coefficient; however, many authors have shown that an analysis of the Gini coefficient and its corresponding variance can be obtained from a regression model. Despite the simplicity of the regression approach method to compute a standard error for the Gini coefficient, the use of the proposed regression model has been challenging in economics. Therefore in this paper, we focus on a comparative study among the regression approach and resampling techniques. The regression method is shown to overestimate the standard error of the Gini index. The simulations show that the Gini estimator based on the modified regression model is also consistent and asymptotically normal with less divergence from normal distribution than other resampling techniques.

• Asia-Pacific Journal of Business
• /
• v.8 no.2
• /
• pp.15-30
• /
• 2017

This study analyzes the relationship between income inequality and economic growth. Gini coefficient (market income), the deciles income inequality index and per capita real GDP were analyzed. Furthermore, various cointegration tests were tried to improve the reliability of the test results. From the weak exogeniety test of between per capita real GDP and the Gini coefficient (market income), per capita real GDP has a weak exogeneity while the Gini coefficient is endogenous. From the various cointegration tests, we found out that there is a cointegration between Gini coefficient and per capita real GDP. Moreover, it is estimated that per capita real GDP has a positive effect on the Gini coefficient (market income). In the VAR Granger causal analysis, per capita real GDP affects the Gini coefficient (market income), but it is difficult to say that the Gini coefficient (market income) always has an effect on per capita real GDP. Also, the impulse-response function of the VAR model shows that per capita real GDP temporarily reduces the Gini coefficient (market income), and then increases it over time. Accordingly, it is necessary for the policies to improve not only the distribution structure but also income distribution through economic growth.