Robin Sickles - Academia.edu (original) (raw)

Papers by Robin Sickles

In the Kalman …lter setting, one can model the disturbance term and the ine¢ ciency term of the s... more In the Kalman …lter setting, one can model the disturbance term and the ine¢ ciency term of the standard stochastic frontier composed error as unobserved states. This gives signi…cant ‡exibility to the econometrician when modeling ine¢ ciency. In this study a panel data version of the local level model is used for estimating time-varying e¢ ciencies of …rms. Monet Carlo simulation results indicate that whenever the e¢ ciency levels of the …rms ‡uctuate, some of the widely used estimators perform poorly in capturing the e¢ ciencies of the …rms. On the other hand, the Kalman …lter performs quite well. We apply the Kalman …lter to estimate average e¢ ciencies of U.S. airlines during the period 1999-2009 and …nd that the technical e¢ ciency of these carriers do not show a tendency to increase. For the …rst few years of the study period, it seems that the e¢ ciencies of the airlines decreased.

Econometrica, Nov 1, 1986

variable model with which we study both the health and retirement status of the elderly. Standard... more variable model with which we study both the health and retirement status of the elderly. Standard linear estimators, which assume that these variables are continuous, are not appropriate and categorical estimation techniques are preferred. Our model differs from previous work in that we have longitudinal data and random effects that are correlated over time for different individuals. The problem is made more complicated because there is sample truncation, which could potentially bias coefficient estimates, since approximately twenty percent of the individuals in our sample die. We outline the full information maximum likelihood estimator for such a model and implement it in our empirical analysis. With our structural estimates we analyze, among other things, the degree to which endogeneously determined health status affects the probability of retirement and how changes in social security benefits and eligibility for transfer payments modify both healthiness and the demand for leisure.

Methods and perspectives to model and measure productivity and efficiency have made a number of i... more Methods and perspectives to model and measure productivity and efficiency have made a number of important advances in the last decade. Using the standard and innovative formulations of the theory and practice of efficiency and productivity measurement, Robin C. Sickles and Valentin Zelenyuk provide a comprehensive approach to productivity and efficiency analysis, covering its theoretical underpinnings and its empirical implementation, paying particular attention to the implications of neoclassical economic theory. A distinct feature of the book is that it presents a wide array of theoretical and empirical methods utilized by researchers and practitioners who study productivity issues. An accompanying website includes methods, programming codes that can be used with widely available software like MATLAB® and R, and test data for many of the productivity and efficiency estimators discussed in the book. It will be valuable to upper-level undergraduates, graduate students, and professionals.

Springer Proceedings in Business and Economics, 2016

This paper aims to investigate spillover effects of public capital stock in a production function... more This paper aims to investigate spillover effects of public capital stock in a production function model that accounts for spatial dependencies. Although there are a number of studies that estimate the output elasticity of public capital stock, they suffer from a failure to refine the output elasticity of public capital stock as well as to account for spillover effects of the public capital stock on the production efficiency when such spatial dependencies exist. For this purpose we employ a spatial autoregressive stochastic frontier model and analyze estimates with a time-varying spatial weights matrix. Using data for 21 OECD countries from 1960 to 2001, we found that spillover effects can be an important factor explaining variations in technical inefficiency across countries as well as discrepancies among various levels of output elasticity of public capital stock in traditional production function approaches.

Causes, Correlates and Consequences of Death Among Older Adults, 1998

In this chapter we use micro economic models of individual behavior in a dynamic context to descr... more In this chapter we use micro economic models of individual behavior in a dynamic context to describe how an individual chooses the optimal level of investment in healthiness and implicitly length of life. This establishes a foundation for the estimation of structural parameters related to health demands for older adult men in Section 2.4 and for the hazard mortality estimates that we present in Chapters 4 and 5. While choice regarding health may be considered commonplace for economists, characterizing the length of life as a choice may seem crude and unreasonable to some. There are, however, numerous examples of people making this choice directly, e.g., suicides, living wills that mandate against extraordinary medical care, the refusal by Christian Scientists of potentially life-preserving medical care, and the shortfall of deaths before personally significant dates with a subsequent spike in death rates afterwards.4 Moreover, people have cut back on cigarette smoking since the Surgeon General’s 1964 report on the morbidity and mortality implications of smoking. They also have to be paid more to work at jobs at which more deaths occur (see Thaler and Rosen, 1975). More to the point, by constantly making choices that affect their health and thus the probability that their health falls irreversibly below some threshold leading to death, individuals constantly are affecting their expected duration of survival — whether or not they characterize these choices as proximate causes of survival.

Springer Proceedings in Business and Economics, 2016

Our paper provides new methods to robustify productivity growth measurement by utilizing various ... more Our paper provides new methods to robustify productivity growth measurement by utilizing various economic theories explaining economic growth and productivity and the econometric model generated by that particular theory. We utilize the World Productivity Database from the UNIDO to analyze productivity during the period 1960-2010 for OECD countries. We focus on three competing models from the stochastic frontier literature, Cornwell, Schmidt, and Sickles (1990), Kumbhakar (1990) and Battese and Coelli (1992) to estimate productivity growth and its decomposition into technical change and efficiency change and utilize methods due to Hansen (2010) to construct optimal weights in order to model average the results from these three approaches.

In 1974 the federal government instituted Supplemental Social Insurance (SSI). The eligible group... more In 1974 the federal government instituted Supplemental Social Insurance (SSI). The eligible group was the elderly on welfare and disabled individuals. The program distributed extra income and made people eligible for Medicaid in all states except Arizona which did not have Medicaid. We used subjective and objective health information in the Retirement History Survey (RHS) to examine the impact of the program. The RHS is a sample that began in 1969 and included heads of households who were 58 to 63 years old. The respondents or widows were resurveyed every second year through 1977. Before 1974 those who subsequently received SSI were in much worse health than those who did not. After 1974 the differences in health were small and not statistically significant.

RePEc: Research Papers in Economics, Jun 1, 2015

Semi-nonparametric Spline Modifications to the Cornwell-Schmidt-Sickles Estimator: An Analysis of... more Semi-nonparametric Spline Modifications to the Cornwell-Schmidt-Sickles Estimator: An Analysis of U. S. Banking Productivity This paper modifies the Cornwell, Schmidt and Sickles (CSS) (1990) time-varying specification of technical efficiency to allow for switching patterns in temporal changes, which may occur more than once during the sample period. For this purpose, we move from the (second-order) polynomial specification of the standard CSS to a spline function set up, while keeping CSS's flexibility regarding the cross section dimension. The spline function specification of the temporal pattern of technical efficiency can accommodate more than one turning point and thus can be non-monotonic. This allows the modeler to account for firm or individual efficiency gains that can occur relatively quickly, for example, changes related to regulation or policy changes, as well as those related to ownership/organization changes (e.g., merger or acquisitions).

RePEc: Research Papers in Economics, Apr 1, 2015

By integrating Battese and Coelli's (1995) model and the spatial autoregressive model, a spatial ... more By integrating Battese and Coelli's (1995) model and the spatial autoregressive model, a spatial autoregressive stochastic frontier model for panel data is developed. The main feature of this frontier model is a spatial lag term of explained variables and joint structure of a production possibility frontier with a model of technical inefficiency. This model addresses both spatial dependence and heteroskedastic technical inefficiency. This study applies maximum likelihood methods considering the endogenous spatial lag term. The proposed model nests many existing models. Further, an empirical analysis using data of Japanese manufacturing industry is conducted, and these existing models are tested against the proposed model, which is found to be statistically supported. The findings suggest that the estimates in the existing spatial and non-spatial models may exhibit bias because of the lack of determinants of technical inefficiency, as well as a spatial lag. This bias also affects the technical efficiency score and its ranking.

Journal of Chinese Economic and Business Studies, Jul 3, 2014

On the basis of the previous success of productivity workshops in 2007 at Tsinghua University and... more On the basis of the previous success of productivity workshops in 2007 at Tsinghua University and in 2008 at Zhejiang University, and in cooperation with the Chinese Economic Association (Europe), the 2012 International Workshop on Chinese Productivity was sponsored by the School for Public Policy and Management at Tsinghua University. The Workshop provided another opportunity for academic researchers to communicate their research results and to discuss important issues in the field of applied productivity analysis in general and specific issues concerning China in particular. This special issue is one of the outcomes from the workshop. The first paper by Sickles, Hao, and Shang provides a brief survey and addresses generic methodological issues in regard to identifying and estimating the two major components of aggregate productivity growth: technical change and efficiency change (catch-up). The paper compares the productivity performance of Asian economies. Färe et al. present a model on environmental efficiency using Swedish data and discuss the potential for applications in the Chinese situation. In the third paper, Han and coauthors study the performance of Chinese commercial banks from aspects of social productive efficiency, service efficiency, profit efficiency and growth efficiency. The last paper by Jensen and Schøtt put innovation performance by a firm in social contexts, studying the difference between China and the rest of the world in terms of networking and innovation and the relationship between the two. The collection of the papers in the special issue reflect the growing interests in recent years in the comparison of productivity performance across economies with different institutional set-ups, increasing concerns of environmental issues in the fast growing Chinese economy and a gradual awareness of innovation and productivity performance in relation to social and historical factors. Therefore, current productivity studies require far more sophisticated frameworks and involve a wide range of cutting edge methodologies such as techniques of frontier analysis, dynamic models of innovation determinants and institutional analysis of national innovation systems. We believe as more resources are attracted into the area of Chinese productivity studies more fruitful results can be expected in the near future. As our work has benefited from many individuals and institutions, we would like to take this opportunity to mention just a few. Since 2007, Professor Angang Hu of Tsinghua University has been a main driving force behind the three workshops on Chinese productivity. It would not have been possible for us to achieve what has been

Seoul Journal of Economics, Mar 1, 2009

Young (1994) and Kim and Lau (1994), among others, argue that the "Asian Miracle" of relatively h... more Young (1994) and Kim and Lau (1994), among others, argue that the "Asian Miracle" of relatively high growth was largely due to increases in factor inputs. Productivity growth would eventually slow because of diminishing returns to factors. Thus total factor productivity growth was not the reason for the Asian Miracle. Krugman (1994) summarized this research, comparing the growth experience of Singapore, among the other Asian Tigers, to that of the Soviet Union and argued that there was reason to expect a similar outcome, namely a collapse of the political institutions due to economic stagnation. Interestingly, Krugman consistently refers to efficiency growth and technical progress as equivalent terms. In this paper and survey we discuss alternative explanations for economic growth in Asia as well as elsewhere in the world in the post WWII years. The alternative explanation is explicit in Krugman's treatise. It is economic growth due to a world with less constraints.

Pacific Economic Review, Oct 1, 2017

Policy makers and the economic researchers who provide them estimates of economic activity need t... more Policy makers and the economic researchers who provide them estimates of economic activity need to have an informative and scientifically-based method to develop a consensus estimate for the most basic of the productivity measures, total factor productivity (TFP) growth. We discuss methods to combine the various estimates based on different empirical specifications that model and estimate productivity growth. We also discuss the various econometric approaches used in the profession to estimate productivity growth. Our focus is on world TFP growth.

Review of Income and Wealth

The Oxford Handbook of Productivity Analysis

This chapter provides a wide-ranging interdisciplinary overview of productivity analysis, which a... more This chapter provides a wide-ranging interdisciplinary overview of productivity analysis, which also serves to introduce the chapters in the Handbook. It begins with an exploration into the significance of productivity growth, for business, for the economy, and for social economic progress. The chapter continues with a treatment of how productivity is defined, measured, and implemented. It then addresses two important empirical issues. The first involves productivity dispersion, and the productivity dynamics that would either lead to a reallocation of resources that would reduce dispersion and increase aggregate productivity, or allow dispersion to persist behind barriers to productivity-enhancing reallocation. The second involves a search for the drivers of (or impediments to) productivity growth, some of which are organizational in nature and under management control, and others of which are institutional in nature and beyond management control but subject to public policy interve...

In the Kalman …lter setting, one can model the disturbance term and the ine¢ ciency term of the s... more In the Kalman …lter setting, one can model the disturbance term and the ine¢ ciency term of the standard stochastic frontier composed error as unobserved states. This gives signi…cant ‡exibility to the econometrician when modeling ine¢ ciency. In this study a panel data version of the local level model is used for estimating time-varying e¢ ciencies of …rms. Monet Carlo simulation results indicate that whenever the e¢ ciency levels of the …rms ‡uctuate, some of the widely used estimators perform poorly in capturing the e¢ ciencies of the …rms. On the other hand, the Kalman …lter performs quite well. We apply the Kalman …lter to estimate average e¢ ciencies of U.S. airlines during the period 1999-2009 and …nd that the technical e¢ ciency of these carriers do not show a tendency to increase. For the …rst few years of the study period, it seems that the e¢ ciencies of the airlines decreased.

Econometrica, Nov 1, 1986

variable model with which we study both the health and retirement status of the elderly. Standard... more variable model with which we study both the health and retirement status of the elderly. Standard linear estimators, which assume that these variables are continuous, are not appropriate and categorical estimation techniques are preferred. Our model differs from previous work in that we have longitudinal data and random effects that are correlated over time for different individuals. The problem is made more complicated because there is sample truncation, which could potentially bias coefficient estimates, since approximately twenty percent of the individuals in our sample die. We outline the full information maximum likelihood estimator for such a model and implement it in our empirical analysis. With our structural estimates we analyze, among other things, the degree to which endogeneously determined health status affects the probability of retirement and how changes in social security benefits and eligibility for transfer payments modify both healthiness and the demand for leisure.

Methods and perspectives to model and measure productivity and efficiency have made a number of i... more Methods and perspectives to model and measure productivity and efficiency have made a number of important advances in the last decade. Using the standard and innovative formulations of the theory and practice of efficiency and productivity measurement, Robin C. Sickles and Valentin Zelenyuk provide a comprehensive approach to productivity and efficiency analysis, covering its theoretical underpinnings and its empirical implementation, paying particular attention to the implications of neoclassical economic theory. A distinct feature of the book is that it presents a wide array of theoretical and empirical methods utilized by researchers and practitioners who study productivity issues. An accompanying website includes methods, programming codes that can be used with widely available software like MATLAB® and R, and test data for many of the productivity and efficiency estimators discussed in the book. It will be valuable to upper-level undergraduates, graduate students, and professionals.

Springer Proceedings in Business and Economics, 2016

This paper aims to investigate spillover effects of public capital stock in a production function... more This paper aims to investigate spillover effects of public capital stock in a production function model that accounts for spatial dependencies. Although there are a number of studies that estimate the output elasticity of public capital stock, they suffer from a failure to refine the output elasticity of public capital stock as well as to account for spillover effects of the public capital stock on the production efficiency when such spatial dependencies exist. For this purpose we employ a spatial autoregressive stochastic frontier model and analyze estimates with a time-varying spatial weights matrix. Using data for 21 OECD countries from 1960 to 2001, we found that spillover effects can be an important factor explaining variations in technical inefficiency across countries as well as discrepancies among various levels of output elasticity of public capital stock in traditional production function approaches.

Causes, Correlates and Consequences of Death Among Older Adults, 1998

In this chapter we use micro economic models of individual behavior in a dynamic context to descr... more In this chapter we use micro economic models of individual behavior in a dynamic context to describe how an individual chooses the optimal level of investment in healthiness and implicitly length of life. This establishes a foundation for the estimation of structural parameters related to health demands for older adult men in Section 2.4 and for the hazard mortality estimates that we present in Chapters 4 and 5. While choice regarding health may be considered commonplace for economists, characterizing the length of life as a choice may seem crude and unreasonable to some. There are, however, numerous examples of people making this choice directly, e.g., suicides, living wills that mandate against extraordinary medical care, the refusal by Christian Scientists of potentially life-preserving medical care, and the shortfall of deaths before personally significant dates with a subsequent spike in death rates afterwards.4 Moreover, people have cut back on cigarette smoking since the Surgeon General’s 1964 report on the morbidity and mortality implications of smoking. They also have to be paid more to work at jobs at which more deaths occur (see Thaler and Rosen, 1975). More to the point, by constantly making choices that affect their health and thus the probability that their health falls irreversibly below some threshold leading to death, individuals constantly are affecting their expected duration of survival — whether or not they characterize these choices as proximate causes of survival.

Springer Proceedings in Business and Economics, 2016

Our paper provides new methods to robustify productivity growth measurement by utilizing various ... more Our paper provides new methods to robustify productivity growth measurement by utilizing various economic theories explaining economic growth and productivity and the econometric model generated by that particular theory. We utilize the World Productivity Database from the UNIDO to analyze productivity during the period 1960-2010 for OECD countries. We focus on three competing models from the stochastic frontier literature, Cornwell, Schmidt, and Sickles (1990), Kumbhakar (1990) and Battese and Coelli (1992) to estimate productivity growth and its decomposition into technical change and efficiency change and utilize methods due to Hansen (2010) to construct optimal weights in order to model average the results from these three approaches.

In 1974 the federal government instituted Supplemental Social Insurance (SSI). The eligible group... more In 1974 the federal government instituted Supplemental Social Insurance (SSI). The eligible group was the elderly on welfare and disabled individuals. The program distributed extra income and made people eligible for Medicaid in all states except Arizona which did not have Medicaid. We used subjective and objective health information in the Retirement History Survey (RHS) to examine the impact of the program. The RHS is a sample that began in 1969 and included heads of households who were 58 to 63 years old. The respondents or widows were resurveyed every second year through 1977. Before 1974 those who subsequently received SSI were in much worse health than those who did not. After 1974 the differences in health were small and not statistically significant.

RePEc: Research Papers in Economics, Jun 1, 2015

Semi-nonparametric Spline Modifications to the Cornwell-Schmidt-Sickles Estimator: An Analysis of... more Semi-nonparametric Spline Modifications to the Cornwell-Schmidt-Sickles Estimator: An Analysis of U. S. Banking Productivity This paper modifies the Cornwell, Schmidt and Sickles (CSS) (1990) time-varying specification of technical efficiency to allow for switching patterns in temporal changes, which may occur more than once during the sample period. For this purpose, we move from the (second-order) polynomial specification of the standard CSS to a spline function set up, while keeping CSS's flexibility regarding the cross section dimension. The spline function specification of the temporal pattern of technical efficiency can accommodate more than one turning point and thus can be non-monotonic. This allows the modeler to account for firm or individual efficiency gains that can occur relatively quickly, for example, changes related to regulation or policy changes, as well as those related to ownership/organization changes (e.g., merger or acquisitions).

RePEc: Research Papers in Economics, Apr 1, 2015

By integrating Battese and Coelli's (1995) model and the spatial autoregressive model, a spatial ... more By integrating Battese and Coelli's (1995) model and the spatial autoregressive model, a spatial autoregressive stochastic frontier model for panel data is developed. The main feature of this frontier model is a spatial lag term of explained variables and joint structure of a production possibility frontier with a model of technical inefficiency. This model addresses both spatial dependence and heteroskedastic technical inefficiency. This study applies maximum likelihood methods considering the endogenous spatial lag term. The proposed model nests many existing models. Further, an empirical analysis using data of Japanese manufacturing industry is conducted, and these existing models are tested against the proposed model, which is found to be statistically supported. The findings suggest that the estimates in the existing spatial and non-spatial models may exhibit bias because of the lack of determinants of technical inefficiency, as well as a spatial lag. This bias also affects the technical efficiency score and its ranking.

Journal of Chinese Economic and Business Studies, Jul 3, 2014

On the basis of the previous success of productivity workshops in 2007 at Tsinghua University and... more On the basis of the previous success of productivity workshops in 2007 at Tsinghua University and in 2008 at Zhejiang University, and in cooperation with the Chinese Economic Association (Europe), the 2012 International Workshop on Chinese Productivity was sponsored by the School for Public Policy and Management at Tsinghua University. The Workshop provided another opportunity for academic researchers to communicate their research results and to discuss important issues in the field of applied productivity analysis in general and specific issues concerning China in particular. This special issue is one of the outcomes from the workshop. The first paper by Sickles, Hao, and Shang provides a brief survey and addresses generic methodological issues in regard to identifying and estimating the two major components of aggregate productivity growth: technical change and efficiency change (catch-up). The paper compares the productivity performance of Asian economies. Färe et al. present a model on environmental efficiency using Swedish data and discuss the potential for applications in the Chinese situation. In the third paper, Han and coauthors study the performance of Chinese commercial banks from aspects of social productive efficiency, service efficiency, profit efficiency and growth efficiency. The last paper by Jensen and Schøtt put innovation performance by a firm in social contexts, studying the difference between China and the rest of the world in terms of networking and innovation and the relationship between the two. The collection of the papers in the special issue reflect the growing interests in recent years in the comparison of productivity performance across economies with different institutional set-ups, increasing concerns of environmental issues in the fast growing Chinese economy and a gradual awareness of innovation and productivity performance in relation to social and historical factors. Therefore, current productivity studies require far more sophisticated frameworks and involve a wide range of cutting edge methodologies such as techniques of frontier analysis, dynamic models of innovation determinants and institutional analysis of national innovation systems. We believe as more resources are attracted into the area of Chinese productivity studies more fruitful results can be expected in the near future. As our work has benefited from many individuals and institutions, we would like to take this opportunity to mention just a few. Since 2007, Professor Angang Hu of Tsinghua University has been a main driving force behind the three workshops on Chinese productivity. It would not have been possible for us to achieve what has been

Seoul Journal of Economics, Mar 1, 2009

Young (1994) and Kim and Lau (1994), among others, argue that the "Asian Miracle" of relatively h... more Young (1994) and Kim and Lau (1994), among others, argue that the "Asian Miracle" of relatively high growth was largely due to increases in factor inputs. Productivity growth would eventually slow because of diminishing returns to factors. Thus total factor productivity growth was not the reason for the Asian Miracle. Krugman (1994) summarized this research, comparing the growth experience of Singapore, among the other Asian Tigers, to that of the Soviet Union and argued that there was reason to expect a similar outcome, namely a collapse of the political institutions due to economic stagnation. Interestingly, Krugman consistently refers to efficiency growth and technical progress as equivalent terms. In this paper and survey we discuss alternative explanations for economic growth in Asia as well as elsewhere in the world in the post WWII years. The alternative explanation is explicit in Krugman's treatise. It is economic growth due to a world with less constraints.

Pacific Economic Review, Oct 1, 2017

Policy makers and the economic researchers who provide them estimates of economic activity need t... more Policy makers and the economic researchers who provide them estimates of economic activity need to have an informative and scientifically-based method to develop a consensus estimate for the most basic of the productivity measures, total factor productivity (TFP) growth. We discuss methods to combine the various estimates based on different empirical specifications that model and estimate productivity growth. We also discuss the various econometric approaches used in the profession to estimate productivity growth. Our focus is on world TFP growth.

Review of Income and Wealth

The Oxford Handbook of Productivity Analysis

This chapter provides a wide-ranging interdisciplinary overview of productivity analysis, which a... more This chapter provides a wide-ranging interdisciplinary overview of productivity analysis, which also serves to introduce the chapters in the Handbook. It begins with an exploration into the significance of productivity growth, for business, for the economy, and for social economic progress. The chapter continues with a treatment of how productivity is defined, measured, and implemented. It then addresses two important empirical issues. The first involves productivity dispersion, and the productivity dynamics that would either lead to a reallocation of resources that would reduce dispersion and increase aggregate productivity, or allow dispersion to persist behind barriers to productivity-enhancing reallocation. The second involves a search for the drivers of (or impediments to) productivity growth, some of which are organizational in nature and under management control, and others of which are institutional in nature and beyond management control but subject to public policy interve...