Measures of inequality are used by economists to answer a wide range of questions. For example, sociologists are interested in the distribution of income. In this paper, the term “inequality” is used in a purely described sense. It is not intended to describe any message on the fairness of the differences in health geographically, as implied by the term “inequity”. One of the famous measures is the Gini-style index. The Gini index is often described in terms of Lorenz curve. This measure is mainly used in the social science to evaluate the relationship between two variables. The index also provides appealing criteria without any unnecessary parametric assumptions about the specific form of the inequality index or the social welfare function. In spite of the disadvantage of the Gini index, the Gini index of multivariate variables is not well defined. Therefore, quantile regression (QR) is used in the paper.
QR proposed by Koenker (1978) is used to analyze the distribution and change of health practitioners in Taiwan between 1994 and 2000. The aspects of measuring the extreme and intermediate of a distribution have important meanings in many fields. Many studies have used the least squares estimator to predict interesting variable although the least squares estimator cannot describe the whole distribution sufficiently only depending on a mean equation. Besides, there is an impact on parameters solved by using the least square estimators which have higher sensitivities to extreme values. QR is avoided by the influence of extreme values. The QR of multivariate data is well defined. The distribution of health practitioners can be described completely by the distribution of practitioners at different quantiles. QR provides an alternative way to investigate the distribution of health manpower. It is interested to investigate that if inequalities reduce after applying the National Health Insurance (NHI).

Measures of inequality are used by economists to answer a wide range of questions. For example, sociologists are interested in the distribution of income. In this paper, the term “inequality” is used in a purely described sense. It is not intended to describe any message on the fairness of the differences in health geographically, as implied by the term “inequity”. One of the famous measures is the Gini-style index. The Gini index is often described in terms of Lorenz curve. This measure is mainly used in the social science to evaluate the relationship between two variables. The index also provides appealing criteria without any unnecessary parametric assumptions about the specific form of the inequality index or the social welfare function. In spite of the disadvantage of the Gini index, the Gini index of multivariate variables is not well defined. Therefore, quantile regression (QR) is used in the paper.
QR proposed by Koenker (1978) is used to analyze the distribution and change of health practitioners in Taiwan between 1994 and 2000. The aspects of measuring the extreme and intermediate of a distribution have important meanings in many fields. Many studies have used the least squares estimator to predict interesting variable although the least squares estimator cannot describe the whole distribution sufficiently only depending on a mean equation. Besides, there is an impact on parameters solved by using the least square estimators which have higher sensitivities to extreme values. QR is avoided by the influence of extreme values. The QR of multivariate data is well defined. The distribution of health practitioners can be described completely by the distribution of practitioners at different quantiles. QR provides an alternative way to investigate the distribution of health manpower. It is interested to investigate that if inequalities reduce after applying the National Health Insurance (NHI).

Chapter 1 Introduction…………………………………………………………..1
Chapter 2 Gini Index…………………………………………………………….3
2.1 Gini’s Mean Difference………………………………………………4
2.2 Gini Coefficient………………………………………………………9
2.3 Gini Regression………………………………………………………11
Chapter 3 Quantile Regression………………………………………………….14
3.1 Introduction to QR…………………………………………………...15
3.2 Review of QR’s Application…………………………………………21
3.3 Illustration of the QR and Gini Index………………………………..26
Chapter 4 Empirical Study: Medical Manpower in Taiwan…………………….41
4.1 Data Description……………………………………………………..45
4.2 Number of Physicians………………………………………………..48
4.3 Density of Physicians………………………………………………..53
4.4 the Growth Rate of Physicians………………………………………58
Chapter 5 Conclusions and Comment…………………………………………..83
References……………………………………………………………………………86

Allison, P. D., (1982), “Regression Analysis of Inequality Measures Applied to Interval Scales”, Quality and Quantity, 16, 251-260
Atkinson, A. B., (1970), “On the Measurement of Inequality”, Journal of Economic Theory 2, 244-263
Belsley, D. A., Kuh, E., and Welsch, R. E., (1980), Regression Diagnostics: Identifying Influential Data and Sources of Collinearity, New York: John Wiley and Sons
Buchinsky, M., (1994), “Changes in the U.S. Wage Structure 1963-1987: Application of Quantile Regression”, Econometrica, 62, 405-458
Buchinsky, M., (2001), “Quantile Regression with Sample Selection：Estimating Women’s Return to Education in the U.S.”, Empirical Economics, 26, 87-113
Bollerslev, T. and Chou, R. Y., (1992), “ARCH Modeling in Finance”, Journal of Econometrics, 52, 5-59
Brown, M. C., (1994), “Using Gini-Style Indices to Evaluate the Spatial Patterns of Health Practitioners: Theoretical Considerations and an Application Based on Alberta Data”, Social Science and Medicine ,38, 1243-1256
Chernozhukov, V. and Umantsev, L., (2001), “Conditional Value-at-Risk：Aspects of Modeling and Estimation”, Empirical Economics, 26, 271-292
David, H.A., (1981), Order Statistics, 2nd edition, New York, Wisley
Eide, E. and Showalter, M. H., (1998), “The Effect of School Quality on Student Performance: A Quantile Regression Approach”, Economics Letters, 58, 345-350
Engle, R. F., (1982), “Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation”, Econometrica, 50, 987-1007
Gastwirth, J. L., (1972), “The Estimation of the Lorenz Curve and Gini index”, The Review of Economics and Statistics, 54, 306-316
Huber, P. J., (1973), “Robust Regression, Asymptotics, Conjectures and Monte-Carlo”, Annals of Statistics, 1, 799-821
Lerman, R. I. and Yitzhaki, S., (1985), “Income Ineqyality Effects by Income Source: A New Approach and Applications to the U.S.”, The Review of Economics and Statistics, LXVII, 1, 151-156
Kendall, M. G. and Stuart, A., (1969), The Advanced Theory of Statistics, Vol. 1, New York: Hafner
Koenker, R. and Hallock, K. F., (2000), “Quantile Regression an Introduction”, University of Illinois at Urbana-Champaign
Koenker, R. and Zhao, Q., (1996), “Conditional Quantile Estimation and Inferece for ARCH Model”, Econometric Theory, 12, 793-813
Koenker, R. and Bassett,G., (1978), “Regression Quantiles”, Econometrica, 46, 33-50
Mackenbach, J. P. and Kunst, A. E., (1997), “Measuring the Magnitude of Socio-Economic Inequalities in Health: an Overview of Available Measures Illustrated with two Examples form Europe”, Social Science and Medicine, 44, 757-771
Mata, J. and Machado, J. A. F., (2001), “Earning Function in Portugal 1982 -1994：Evidence from Quantile Regressions”, Empirical Economics, 26, 115-134
Olkin, I. and Yitzhaki, S., (1992), “Gini Regression Analysis”, International Statistical Review, 60, 185-196
Randles, R. H. and Wolfe, D. A., (1979), Introduction to the Theory of Nonparametric Statistics, New York: John Wiley and Sons
Schechtman, E. and Yitzhaki, S., (1987), “A measure of association based on Gini’s Mean Difference”, Communications in Statistics, Theory and Methods, 16(1), 207-231
Schechtman, E. and Yitzhaki, S., (1998), “Gini’s Mean Difference, Gini Correlation and Gini Regression”, Proceedings of the Business and Economic Statistics Section, 108-111
Wagstaff, A., Paci, P. and Doorslaer, E. V., (1991), “On the Measurement of Inequalities in Health”, Social Science and Medicine, 33, 545-557
Yitzhaki, S., (1998), “More than a Dozen Alterative Ways of Spelling Gini”, Research on Economic Inequality, 8, 13-30
Yitzhaki, S. and Lerman, R. I., (1984), “A note on the calculation and interpretation of the Gini Index”, Economics Letters, 15, 363-368
王宗曦, (1999), “台灣地區診所醫師地理分布之變遷1996~1998”, 國立台灣大學公共衛生學院醫療機構管理研究所, 碩士論文
王德仁, (2000), “風險值評估之統計方法與實證研究”, 國立台北大學統計研究所, 碩士論文
江東亮, (1992), “公元二千年台灣地區醫師人力的供給與地理分布的推計”, 台灣衛誌, 91, s109-s116
朱橋麗、薛亞聖、江東亮, (2000), “醫師人力供給的多寡是否會影響被保險人的門診利用？--1994年國民醫療保健調查之發現”, 中華衛誌, 19, 381-388
洪錦墩、李卓倫, (1989), “以GINI係數分析台灣地區的醫師人力分布”, 公共衛誌, 16, 225-232
洪錦墩、藍忠孚、宋文娟, (2001), “台灣醫師人力研究之方法學探討”, 台灣衛誌, 20, 183-191
徐俊強, (2001), “影響醫院門診、住院平均單價、佔床率因素之研究”, 輔仁大學應用統計研究所, 碩士論文
陳依琪, (2001), “全民健康保險醫療資源分配：非醫療需要變數之影響”, 台北醫學大學醫學研究所, 碩士論文
黃偉堯、張睿詒、江東亮, (1999), “台灣地區醫師人力地理分布之變遷，1984-1997’, 醫師人力政策研究會大會手冊, 1999/1/27
藍忠孚、宋文娟、陳琇玲、詹錕鋙, (2000), “台灣地區醫師人力供需預測之情境分析”, 中華衛誌, 19, 86-95