A structural analysis of the correlated random coefficient wage regression model

We estimate a dynamic programming model of schooling decisions in which the log wage regression function is set within a correlated random coefficient model. We show that estimates of the dynamic programming model can be used to obtain a number of treatment effects, including the local average treatment effect (LATE). However, unlike LATE parameters obtained in a standard IV framework, our LATE estimates are obtained without imposing separability between individual specific heterogeneity and schooling choices and are therefore not subject to a “monotonicity” restriction. We find that returns to schooling are characterized by a high degree of dispersion across individuals.     

Bayesian estimation of a random coefficient model

This paper carries out a Bayesian analysis of the Hildreth-Houck (1968) random coefficient model and applies it to some cross-section production function data. Posterior distributions for mean coefficients, actual coefficients, variances and variance ratios are derived. The variance ratio posteriors are largely uninformative but they do lead to relatively informative densities on the variances, and the problem of negative variance estimates, obtained with previous techniques, is overcome. Posterior densities for the mean coefficients are not extremely sensitive to the variance ratios.     

A bayesian analysis of a random coefficient model in a simple keynesian system

The marginal propensity to consume in a simple Keynesian model is treated as a random coefficient. This gives rise to the problem of quotient of random variables, i.e., the Fieller-Creasy problem. The Bayesian and maximum likelihood estimators are compared in sampling experiments. The Bayesian estimators have smaller mean squared errors than the maximum likelihood estimators. Marginal posterior probability density functions for a given sample are also presented.     

A note on the unbiasedness of Swamy's estimator for the random coefficient regression model

In this note the estimator proposed by Swamy (1970) for the random coefficient regression model is proved to be unbiased under fairly general conditions. In addition, the conditions under which the mean of the estimator exists are derived.     

An application and test for a random coefficient model in Bangladesh agriculture

This paper deals with efficiency question by estimating four production functions for four different regions in connection with Bangladesh agriculture. Hildreth and Houck's (1968) random coefficient method was found more suitable than OLS after conducting an appropriate test for this. In contrast to earlier studies, 24 piece-wise regressions have been fitted for each index of efficiency considering all four regions and six different ranges of farm size instead of a single regression so that the relationship could be studied more closely. The study clearly indicates higher efficiency for smaller farms.     

Testing for a unit root in a random coefficient panel data model

This paper proposes new unit root tests in the context of a random autoregressive coefficient panel data model, in which the null of a unit root corresponds to the joint restriction that the autoregressive coefficient has unit mean and zero variance. The asymptotic distributions of the test statistics are derived and simulation results are provided to suggest that they perform very well in small samples.     

A link between random coefficient autoregressive models and some agent based models

An agent based model (ABM), where each agent makes decisions by using the sum of two signals, is proposed. The first is related to the fundamental information while the second comes from trader’s idiosyncratic noise. This model entails the switching between two groups called fundamentalist and noise traders. Additionally, if the price impact function is log-linear, then the dynamic of log asset prices belongs to the class of random coefficient autoregressive RCA(p) models, which are known to share important stylized facts of financial prices.     

International mergers and acquisitions: A jump diffusion model application

This paper empirically investigates international mergers and acquisitions (M&As) of foreign targets and bidders by analyzing the stock price behavior of the firms involved. The jump diffusion model is employed to study the effects of the M&A announcements on stock prices. The results indicate that acquisition announcements are perceived as a surprise by the market, but prices seem to adjust rather rapidly, supporting the semi-strong form of the market efficiency hypothesis. In addition, a comparison of the pure diffusion and jump diffusion models indicates that the jump diffusion model is statistically superior to the traditional event study methodology (pure diffusion model). (JEL G34)     

Spatial aspects of the diffusion of technological innovations among American municipal governments

Examination of the spatial diffusion patterns of a sample of 43 technological innovations organized into four functional areas—fire fighting, traffic control, air pollution control, solid waste collection, and disposal—indicates the absence of systematic patterns of either rank-size or contagious diffusion of these innovations among municipal governments in the United States. Absence of these general patterns reflects an inadequate identification in existing theories of spatial diffusion processes of variables that enter into agency decisions to adopt new technologies and the inadequate identification of possible interactions among variables. In particular, attempts to model diffusion patterns based on neighborhood effect or on hierarchical relationships fail to take into account, it least for the classes of adopters and innovations studied here, polynuclear propagation and the role of intermediaries (e.g. professional associations, governmental agencies, suppliers) in communication patterns or the role of site-specific factors that determine the “suitability” or “worth” or an innovation to different potential adopters.     

Modeling the diffusion of public policy innovations among the U.S. States

This paper describes and validates a general model of state diffusion of public policy innovations. The model can be used to identify whether new policies are likely to become fully adopted into the system of states and the time horizon over which this is likely to occur. Limitations and extensions of the model are also concluded.     

Innovation diffusion: A deterministic model of space-time integration with physical analog

This paper extends a fundamental temporal diffusion model to integrate space and time dimensions of the diffusion of innovation. The analogous developments in physical sciences are compared and it is demonstrated that the proposed model may be the first step in linking the concept of catalysts in physical science diffusion processes to the role of change agents in social science systems.     

Bayesian analysis of random coefficient logit models using aggregate data

We present a Bayesian approach for analyzing aggregate level sales data in a market with differentiated products. We consider the aggregate share model proposed by Berry et al. [Berry, Steven, Levinsohn, James, Pakes, Ariel, 1995. Automobile prices in market equilibrium. Econometrica. 63 (4), 841–890], which introduces a common demand shock into an aggregated random coefficient logit model. A full likelihood approach is possible with a specification of the distribution of the common demand shock. We introduce a reparameterization of the covariance matrix to improve the performance of the random walk Metropolis for covariance parameters. We illustrate the usefulness of our approach with both actual and simulated data. Sampling experiments show that our approach performs well relative to the GMM estimator even in the presence of a mis-specified shock distribution. We view our approach as useful for those who are willing to trade off one additional distributional assumption for increased efficiency in estimation.     

Towards a microscopic analysis of industrial innovations: From diffusion curves to technological integration through participative management

This paper traces the development of ever more microscopic analyses of the industrial innovation process and presents these as progressive stages in a gradual coming to terms with the real-life complexities of this process. Begining with the macroscopic, diffusion perspective inherited from rural sociology, it reveals how more user-centred models have emerged. The changing image of the user is traced from “passive adopter” to “managerial problem solver” and finally, to “innovative designer”. The paper then turns to the difficulties involved in understanding the nature of the firm's infrastructure and the implications it has for innovation management and industrial relations problems. Research in this area is identified as a crucial source of the new management tachniques that are required to solve the growing problems of resistance to technology implementation. A socio-psychological analysis drawing upon the concepts of the ethogenic approach is proposed and seen to recommend a participative management style similar to that used so successfully by the Japanese.     

Performance of empirical Bayes estimators of random coefficients in multilevel analysis: Some results for the random intercept-only model

For a multilevel model with two levels and only a random intercept, the quality of different estimators of the random intercept is examined. Analytical results are given for the marginal model interpretation where negative estimates of the variance components are allowed for. Except for four or five level-2 units, the Empirical Bayes Estimator (EBE) has a lower average Bayes risk than the Ordinary Least Squares Estimator (OLSE). The EBEs based on restricted maximum likelihood (REML) estimators of the variance components have a lower Bayes risk than the EBEs based on maximum likelihood (ML) estimators. For the hierarchical model interpretation, where estimates of the variance components are restricted being positive, Monte Carlo simulations were done. In this case the EBE has a lower average Bayes risk than the OLSE, also for four or five level-2 units. For large numbers of level-1 (30) or level-2 units (100), the performances of REML-based and ML-based EBEs are comparable. For small numbers of level-1 (10) and level-2 units (25), the REML-based EBEs have a lower Bayes risk than ML-based EBEs only for high intraclass correlations (0.5).     

Network legitimacy diffusion: a model for corporate entrepreneurship

International corporate entrepreneurship increasingly requires broader internal and external networks and legitimacy seeking in areas where the corporation and the entrepreneur are not well known. In this article, the important factors that influence the degree of legitimacy granted to corporate entrepreneurs are proposed and discussed. Specifically, we identify three primary levels of legitimacy: pragmatic legitimacy, normative legitimacy, and structural legitimacy. A model is proposed that suggests that organizations move through these levels of legitimacy resulting in differing brokering behaviors for network building. In addition, we integrate this effort into a global perspective by focusing on corporate entrepreneurs who seek to engage in international efforts. Implications for future research are provided.