Finite-Sample Inference Methods for Simultaneous Equations and Models with Unobserved and Generated Regressors

We propose finite sample tests and confidence sets for models with unobserved and generated regressors as well as various models estimated by instrumental variables methods. The validity of the procedures is unaffected by the presence of identification problems or \"weak instruments\", so no detection of such problems is required. We study two distinct approaches for various models considered by Pagan (1984). The first one is an instrument substitution method which generalizes an approach proposed by Anderson and Rubin (1949) and Fuller (1987) for different (although related) problems, while the second one is based on splitting the sample. The instrument substitution method uses the instruments directly, instead of generated regressors, in order to test hypotheses about the \"structural parameters\" of interest and build confidence sets. The second approach relies on \"generated regressors\", which allows a gain in degrees of freedom, and a sample split technique. For inference about general possibly nonlinear transformations of model parameters, projection techniques are proposed. A distributional theory is obtained under the assumptions of Gaussian errors and strictly exogenous regressors. We show that the various tests and confidence sets proposed are (locally) \"asymptotically valid\" under much weaker assumptions. The properties of the tests proposed are examined in simulation experiments. In general, they outperform the usual asymptotic inference methods in terms of both reliability and power. Finally, the techniques suggested are applied to a model of Tobin’s q and to a model of academic performance.

Addressing endogeneity in the relationship between health and employment through a simultaneous equations model

Este documento analiza la relación de doble causalidad entre salud y empleo y su comportamiento dinámico usando datos de Estados Unidos tomados del PSID (Pane Study of Income Dynamics). Este estudio usa dos variables dependientes (Estado de salud auto-reportado y Empleo), las cuales son estimadas usando un modelo probit bivariado para abordar el problema de endegeneidad presente en dicha relación. Los resultados muestran evidencia significativa de la existencia de dicha endogeneidad y del impacto positivo que tiene sobre la probabilidad de ser empleado tener un buen estado de salud y vicesersa, sin embargo, el impacto de la situación de empleo sobre el estado de salud se encuentra que no es significativa.

Development and validation of spectroscopic methods for simultaneous estimation and dissolution of ofloxacin and ornidazole in tablet dosage forms

The aim of this work was to develop and validate simple, accurate and precise spectroscopic methods (multicomponent, dual wavelength and simultaneous equations) for the simultaneous estimation and dissolution testing of ofloxacin and ornidazole tablet dosage forms. The medium of dissolution used was 900 ml of 0.01N HCl, using a paddle apparatus at a stirring rate of 50 rpm. The drug release was evaluated by developed and validated spectroscopic methods. Ofloxacin and ornidazole showed 293.4 and 319.6nm as λmax in 0.01N HCl. The methods were validated to meet requirements for a global regulatory filing. The validation included linearity, precision and accuracy. In addition, recovery studies and dissolution studies of three different tablets were compared and the results obtained show no significant difference among products.

Analysing the impact of public capital stock using the NEG wage equation: a panel data approach

This paper examines the relationship between the level of public infrastructure and the level of productivity using panel data for the Spanish provinces over the period 1984-2004, a period which is particularly relevant due to the substantial changes occurring in the Spanish economy at that time. The underlying model used for the data analysis is based on the wage equation, which is one of a handful of simultaneous equations which when satisfied correspond to the short-run equilibrium of New Economic Geography theory. This is estimated using a spatial panel model with fixed time and province effects, so that unmodelled space and time constant sources of heterogeneity are eliminated. The model assumes that productivity depends on the level of educational attainment and the public capital stock endowment of each province. The results show that although changes in productivity are positively associated with changes in public investment within the same province, there is a negative relationship between productivity changes and changes in public investment in other regions.

Bayesian Model Averaging in the Instrumental Variable Regression Model

This paper considers the instrumental variable regression model when there is uncertainty about the set of instruments, exogeneity restrictions, the validity of identifying restrictions and the set of exogenous regressors. This uncertainty can result in a huge number of models. To avoid statistical problems associated with standard model selection procedures, we develop a reversible jump Markov chain Monte Carlo algorithm that allows us to do Bayesian model averaging. The algorithm is very exible and can be easily adapted to analyze any of the di¤erent priors that have been proposed in the Bayesian instrumental variables literature. We show how to calculate the probability of any relevant restriction (e.g. the posterior probability that over-identifying restrictions hold) and discuss diagnostic checking using the posterior distribution of discrepancy vectors. We illustrate our methods in a returns-to-schooling application.

On making causal claims: A review and recommendations

Social scientists often estimate models from correlational data, where the independent variable has not been exogenously manipulated; they also make implicit or explicit causal claims based on these models. When can these claims be made? We answer this question by first discussing design and estimation conditions under which model estimates can be interpreted, using the randomized experiment as the gold standard. We show how endogeneity--which includes omitted variables, omitted selection, simultaneity, common methods bias, and measurement error--renders estimates causally uninterpretable. Second, we present methods that allow researchers to test causal claims in situations where randomization is not possible or when causal interpretation is confounded, including fixed-effects panel, sample selection, instrumental variable, regression discontinuity, and difference-in-differences models. Third, we take stock of the methodological rigor with which causal claims are being made in a social sciences discipline by reviewing a representative sample of 110 articles on leadership published in the previous 10 years in top-tier journals. Our key finding is that researchers fail to address at least 66 % and up to 90 % of design and estimation conditions that make causal claims invalid. We conclude by offering 10 suggestions on how to improve non-experimental research.

How does ownership structure invfluence bank risk? Analyzing the role of managerial incentives

This paper analyzes how ownership concentration and managerial incentives influences bank risk for a large sample of US banks over the period 1997-2007. Using 2SLS simultaneous equations models, we show that ownership concentration has a positive total effect on bank risk. This is the result of a positive direct effect, which reflects monitoring and opportunistic behavior, and a negative indirect effect, which works through the design of managerial incentive contracts and reflects shareholder preferences toward risk. Large shareholders reduce bank risk by reducing the sensitivity of CEO wealth to stock volatility (Vega) and by increasing the CEO pay-performance sensitivity (Delta). In addition, we show that the direct and indirect effect of ownership concentration on bank risk depends on the type of the largest shareholder (a family, a bank, a corporation or an institutional investor), as well as, on the total shareholding held by each type as a group. Our results suggest that the positive relation between ownership concentration and risk is not the result of preferences towards more risk. Rather, they point at opportunistic behavior of large shareholders.

Who benefits from parental leave in Spain? : a life course analysis

This paper analyses the extent to which individual and workplacecharacteristics and regional policies influence the use and duration ofparental leave in Spain. The research is based on a sample of 125,165people, and 6,959 parental leaves stemming from the ‘Sample ofWorking Life Histories’ (SWLH), 2006. The SWLH consists of administrative register data which include information from threedifferent sources: Social Security, Municipality and Income TaxRegisters. We adopt a simultaneous equations approach to analyse theuse (logistic regression) and duration (event history analysis) ofparental leave, which allows us to control for endogeneity and censoredobservations. We argue that the Spanish parental leave scheme increases gender and social inequalities insofar as reinforces genderrole specialization, and only encourages the reconciling of work andfamily life among workers with a good position in the labour market(educated employees with high and stable working status).

On making causal claims: A review and recommendations

Social scientists often estimate models from correlational data, where the independent variable has not been exogenously manipulated; they also make implicit or explicit causal claims based on these models. When can these claims be made? We answer this question by first discussing design and estimation conditions under which model estimates can be interpreted, using the randomized experiment as the gold standard. We show how endogeneity--which includes omitted variables, omitted selection, simultaneity, common methods bias, and measurement error--renders estimates causally uninterpretable. Second, we present methods that allow researchers to test causal claims in situations where randomization is not possible or when causal interpretation is confounded, including fixed-effects panel, sample selection, instrumental variable, regression discontinuity, and difference-in-differences models. Third, we take stock of the methodological rigor with which causal claims are being made in a social sciences discipline by reviewing a representative sample of 110 articles on leadership published in the previous 10 years in top-tier journals. Our key finding is that researchers fail to address at least 66 % and up to 90 % of design and estimation conditions that make causal claims invalid. We conclude by offering 10 suggestions on how to improve non-experimental research.

Corporate Social Responsibility, Corporate Governance, And Managerial Risk-Taking

This dissertation investigates the association between corporate social responsibility (CSR) and managerial risk-taking, as well as the differences in governance structure that affect this association. Using a sample of US public firms from 1995 to 2009, we find that firms with strong CSR records engage in higher risk-taking. Furthermore, we find that this relationship is robust when accounting for differences in governance structure and correcting for endogeneity via simultaneous equations modeling. Additional testing indicates that performance in the employee relations dimension of CSR in particular increases with risk-taking, while high firm visibility dampens the association between CSR and the accounting-based measures of risk-taking. Prior literature establishes that high managerial risk-tolerance is necessary for the undertaking of risky yet value-enhancing investment decisions. Thus, the main findings suggest that CSR, rather than being a waste of scarce corporate resources, is instead an important aspect of shareholder value creation. They contribute to the debate on CSR by documenting that corporate risk-taking is one mechanism among others through which CSR maps into higher firm value.

Projection-Based Statistical Inference in Linear Structural Models with Possibly Weak Instruments

It is well known that standard asymptotic theory is not valid or is extremely unreliable in models with identification problems or weak instruments [Dufour (1997, Econometrica), Staiger and Stock (1997, Econometrica), Wang and Zivot (1998, Econometrica), Stock and Wright (2000, Econometrica), Dufour and Jasiak (2001, International Economic Review)]. One possible way out consists here in using a variant of the Anderson-Rubin (1949, Ann. Math. Stat.) procedure. The latter, however, allows one to build exact tests and confidence sets only for the full vector of the coefficients of the endogenous explanatory variables in a structural equation, which in general does not allow for individual coefficients. This problem may in principle be overcome by using projection techniques [Dufour (1997, Econometrica), Dufour and Jasiak (2001, International Economic Review)]. AR-types are emphasized because they are robust to both weak instruments and instrument exclusion. However, these techniques can be implemented only by using costly numerical techniques. In this paper, we provide a complete analytic solution to the problem of building projection-based confidence sets from Anderson-Rubin-type confidence sets. The latter involves the geometric properties of “quadrics” and can be viewed as an extension of usual confidence intervals and ellipsoids. Only least squares techniques are required for building the confidence intervals. We also study by simulation how “conservative” projection-based confidence sets are. Finally, we illustrate the methods proposed by applying them to three different examples: the relationship between trade and growth in a cross-section of countries, returns to education, and a study of production functions in the U.S. economy.

Identification, Weak Instruments and Statistical Inference in Econometrics

We discuss statistical inference problems associated with identification and testability in econometrics, and we emphasize the common nature of the two issues. After reviewing the relevant statistical notions, we consider in turn inference in nonparametric models and recent developments on weakly identified models (or weak instruments). We point out that many hypotheses, for which test procedures are commonly proposed, are not testable at all, while some frequently used econometric methods are fundamentally inappropriate for the models considered. Such situations lead to ill-defined statistical problems and are often associated with a misguided use of asymptotic distributional results. Concerning nonparametric hypotheses, we discuss three basic problems for which such difficulties occur: (1) testing a mean (or a moment) under (too) weak distributional assumptions; (2) inference under heteroskedasticity of unknown form; (3) inference in dynamic models with an unlimited number of parameters. Concerning weakly identified models, we stress that valid inference should be based on proper pivotal functions —a condition not satisfied by standard Wald-type methods based on standard errors — and we discuss recent developments in this field, mainly from the viewpoint of building valid tests and confidence sets. The techniques discussed include alternative proposed statistics, bounds, projection, split-sampling, conditioning, Monte Carlo tests. The possibility of deriving a finite-sample distributional theory, robustness to the presence of weak instruments, and robustness to the specification of a model for endogenous explanatory variables are stressed as important criteria assessing alternative procedures.

Exam 1997

Exam and solutions in LaTex