Papers by milorad kovacevic
Savezni zavod za statistiku eBooks, 1987
Measuring Human Capital, 2021
Abstract Human development is based on the expansion of the ability of people to be and do what t... more Abstract Human development is based on the expansion of the ability of people to be and do what they value and have reason to value—capabilities. It goes beyond income alone and distinguishes between “means” and “ends” of development (Streeten, 1994). Health and education have intrinsic value—beyond enhancing productivity. With income, they comprise the Human Development Index (see the text by Amartya Sen, paying tribute to Mahbub Ul Haq, in the 2020 Human Development Report: http://www.hdr.undp.org/en/2020-report ), which when introduced in 1990 initiated a broad and permissive framework for social evaluation (Allowing for “many different things as being simultaneously valuable,” as noted in Sen (2000). See also Stewart et al. (2018)). This chapter traces the evolution of human development metrics, describes current indices, and discusses perspectives that inform their evolution.
The cover reflects human development progress over 1990-2017 in terms of Human Development Index ... more The cover reflects human development progress over 1990-2017 in terms of Human Development Index (HDI) values and the number of people in the four human development categories. In the figure each slice's innermost band represents the population in that human development category, and the height of the slice reflects its HDI value. The cover reflects that even though the global population increased from 5 billion to 7.5 billion between 1990 and 2017, the number of people in low human development fell from 3 billion to 926 million-or from 60 percent of the global population to 12 percent-and that the number of people in high and very high human development more than tripled, from 1.2 billion to 3.8 billion-or from 24 percent of the global population to 51 percent.
Communications in Statistics - Theory and Methods, 2002
... The maximum likelihood (ML) method and the application of the Wald statistic (Bishop, Fienber... more ... The maximum likelihood (ML) method and the application of the Wald statistic (Bishop, Fienberg and Holland, 1975[3]3. Bishop, YMM, Fienberg, SE and Holland, PW 1975. ... We use the basic theory of log-linear modelling of the estimated proportions as outlined by Bishop et al. ...
It is widely accepted that country-averages of income, literacy, life expectancy and other indica... more It is widely accepted that country-averages of income, literacy, life expectancy and other indicators conceal widespread human deprivation and inequality. The measures of human development based on these indicators are also averages, and therefore mask disparities in the overall population. While the Human Development Index (HDI) itself is well accepted as a summary measure of HD capabilities and achievements, there is no a consensus about how to measure inequality in the HD distribution within a country. The conceptual difficulties, as well as the lack of appropriate disaggregated data, are customarily given as major obstacles for not adjusting the HDI for inequality. The objective of this paper is to first review some recent developments in measuring inequality in the distribution of multidimensional indices such as the HDI, and second- to present a practical implementation of the Alkire and Foster (2010) adaptation of the Foster, Lopez-Calva, Szekely (2005) method. The paper will...
All surveys, either cross-sectional or longitudinal, contain nonresponse. Under these circumstanc... more All surveys, either cross-sectional or longitudinal, contain nonresponse. Under these circumstances one must make assumptions about the response mechanism. There is extensive literature about nonresponse for cross-sectional surveys. For longitudinal surveys, the missing data problem, the properties of different response mechanisms, and their impacts on variances are much less known. Assuming missing at random (MAR), we apply the weighted generalized estimating equations (WGEE) modeling, following the lines of earlier research for longitudinal studies under non-survey settings (Robins et. al., 1995), to get estimators of regression coefficients and their joint randomization variance under the situation of either dropouts or intermittent nonresponse. We use the NLSCY for our analyses; our variable of interest is the physical aggression score for kids 2 to 11 years old.
Fitting the Linear Mixed Models from Survey Data Milorad Kovacevic and Rong Huang Statistics Cana... more Fitting the Linear Mixed Models from Survey Data Milorad Kovacevic and Rong Huang Statistics Canada Several methods for fitting the linear mixed models from survey data suggested in literature are examined and compared. We concentrate on recent proposals of noniterative methods for estimation of both regression coefficients and the variance components. These methods include the pseudo-empirical best linear unbiased estimation of You and Rao (2002), pseudo maximum likelihood of Kovacevic and Rai (2003), method of moments of Korn and Graubard (2003) and the modified Henderson08's method III of Huang and Hidiroglou (2003). The finite population properties of the methods are studied in a small simulation study designed according to the Canadian Work Place and Employee Survey.
Gender inequality remains a major barrier to human development. Girls and women have made major s... more Gender inequality remains a major barrier to human development. Girls and women have made major strides since 1990, but they have not yet gained gender equity. In this paper, we review ways to measure and monitor gender inequality, providing a critique of existing measures including the first global gender indices that were launched in the 1995 Human Development Report – the Gender-related Development Index and the Gender Empowerment Measure- and introduce a new index that is presented in the 2010 Human Development Report. The Gender Inequality Index, which addresses the key criticisms of previous measures, is unique in including critical issues of educational attainment, economic and political participation, and reproductive health issues and in accounting for overlapping inequalities at the national level. As such, it represents an important advance on existing global measures of gender equity. Measures of the
Acknowledgment: The paper has benefitted from discussions and input from other members of the Sta... more Acknowledgment: The paper has benefitted from discussions and input from other members of the Statistical and Research Team, most notably, Alison Kennedy and Ricardo Fuentes. The careful reading and subsequent comments by Jeni Klugman and Clara Garcia Aguna have tremendously improved the content and readability. This paper reviews critiques of the Human Development Report over the last twenty years. The critiques are mostly related to the choice of indicators, to high correlation of HDI components, functional form of the HDI including normalization of component indicators, aggregation vs. multiplication, and issues related to weighting. A thorough analysis of the critiques leads us to a proposal for modification of the HDI.
This paper discusses the methodological judgments made during the development of the Human Develo... more This paper discusses the methodological judgments made during the development of the Human Development Index (HDI), and analyzes the quantitative and qualitative impact of different methodological choices on the HDI scores, as well as on the associated changes in ranking. This analysis is particularly pertinent this year, in light of the methodological refinements that have been implemented with the occasion of the HDI 20 th anniversary.
So as not to publish misleading results, subject matter analysts at Statistics Canada are urged t... more So as not to publish misleading results, subject matter analysts at Statistics Canada are urged to take account of the complexities of the survey design when doing analysis using data from Statistics Canada’s surveys. While commercial software packages that incorporate methods for controlling for features of the sample design are becoming more readily available and more efficient to use, analysts without some background in survey theory still have difficulty in knowing how to proceed. Statistics Canada has a small unit called the Data Analysis Resource Centre (DARC) whose purpose is to provide specialized services in analysis of statistical data. One of the major activities of DARC is the support of subject matter analysts who are using data from surveys with complex designs. This paper will present some of our experiences in DARC with assisting analysts in doing their research and some “tips and traps ” that we have identified. Because of the practice in many publications, due to s...
This paper focuses on cross-sectional inference based on data from a longitudinal survey which ca... more This paper focuses on cross-sectional inference based on data from a longitudinal survey which carries some additional components to achieve cross-sectional representativity. When inferring about the differences in the cross-sectional populations at two different points in time, problems arise with variance estimation for the difference of the respective estimates, when the estimates are derived from such a survey. There are several factors contributing to these problems. Of these, the most important is the sample overlap at the two time points due to the underlying longitudinal survey design; this introduces a strong covariance component which must be included in the estimate of the variance of the difference. Also associated with the underlying longitudinal sample is the complexity introduced by longitudinally sampled individuals moving from one geographical part of the country to another, and thus being used to represent a different part of the cross-sectional population than tha...
This paper reviews some of the issues related to statistical quality of the Human Development Ind... more This paper reviews some of the issues related to statistical quality of the Human Development Index (HDI) and other indices and indicators regularly published in the Human Development Report (HDR) of UNDP. We examine the HDI and its component indices within a typical statistical quality framework, addressing issues related to its relevance, consistency, accuracy and robustness, timelines, comparability and methodological soundness. A special attention is paid to data availability.
For estimation of parameters of a multi-level model fitted to hierarchical survey data, the stand... more For estimation of parameters of a multi-level model fitted to hierarchical survey data, the standard assumptions are that the survey weights are available at all sampling levels and that the hierarchy of sampling levels coincides with the hierarchy used in modeling. Under these two assumptions, we propose two bootstrap methods for the variance estimation of the estimated parameters in the multi-level model. These methods are essentially modifications of the well-known survey bootstrap methods of Rao and Wu (1988). In a simulation study designed according to the Canadian Workplace and Employee Survey (CWES), we study and compare the properties of these methods, and in turn we compare them to the more prevalent Taylor linearization method.
Measuring Human Capital, 2021
Human development is based on the expansion of the ability of people to be and do what they value... more Human development is based on the expansion of the ability of people to be and do what they value and have reason to value—capabilities. It goes beyond income alone and distinguishes between “means” and “ends” of development (Streeten, 1994). Health and education have intrinsic value—beyond enhancing productivity. With income, they comprise the Human Development Index (see the text by Amartya Sen, paying tribute to Mahbub Ul Haq, in the 2020 Human Development Report: http://www.hdr.undp.org/en/2020-report ), which when introduced in 1990 initiated a broad and permissive framework for social evaluation (Allowing for “many different things as being simultaneously valuable,” as noted in Sen (2000). See also Stewart et al. (2018)). This chapter traces the evolution of human development metrics, describes current indices, and discusses perspectives that inform their evolution.
1. INTRODUCTION The modelling problem addressed in this paper has been called correlated failure-... more 1. INTRODUCTION The modelling problem addressed in this paper has been called correlated failure-time modelling, multivariate survival modelling, multiple spells modelling, or a recurrent events problem, and is studied in biomedical Generally this type of modelling is required for data that arise in time-to-event studies when two or more events happen to the same subject. In such a case, the failure times are correlated within subject, and thus the assumption of independence of failure times conditional on given measured covariates, required by standard survival models, is violated. The research interest is usually to assess the effect of various covariates considered as potential risk factors. In studies of duration of spells (poverty, jobless-ness, etc.), the 'failure' is equivalent to 'exit' out of the state of interest. The dependence among the observed spells from the same individual comes from the fact that these spells share certain unobserved characteristics ...
This paper reviews critiques of the Human Development Report over the last twenty years. The crit... more This paper reviews critiques of the Human Development Report over the last twenty years. The critiques are mostly related to the choice of indicators, to high correlation of HDI components, functional form of the HDI including normalization of component indicators, aggregation vs. multiplication, and issues related to weighting. A thorough analysis of the critiques leads us to a proposal for modification of the HDI.
This paper discusses the methodological judgments made during the development of the Human Develo... more This paper discusses the methodological judgments made during the development of the Human Development Index (HDI), and analyzes the quantitative and qualitative impact of different methodological choices on the HDI scores, as well as on the associated changes in ranking. This analysis is particularly pertinent this year, in light of the methodological refinements that have been implemented with the occasion of the HDI 20th anniversary.
Gender inequality remains a major barrier to human development. Girls and women have made major s... more Gender inequality remains a major barrier to human development. Girls and women have made major strides since 1990, but they have not yet gained gender equity. In this paper, we review ways to measure and monitor gender inequality, providing a critique of existing measures including the first global gender indices that were launched in the 1995 Human Development Report – the Gender-related Development Index and the Gender Empowerment Measure - and introduce a new index that is presented in the 2010 Human Development Report. The Gender Inequality Index, which addresses the key criticisms of previous measures, is unique in including critical issues of educational attainment, economic and political participation, and reproductive health issues and in accounting for overlapping inequalities at the national level. As such, it represents an important advance on existing global measures of gender equity. Measures of the disadvantages for women raise awareness of problems, permit monitoring...
Uploads
Papers by milorad kovacevic