John J. Beggs

Biases in dynamic models with fixed effects

Abstract This paper examines bias in dynamic models with fixed effects where both the number of time series observations and the number of cross-sectional replications are small. The formula bias estimate is in line with that in published Monte Carlo studies.

A simple model for heterogeneity in binary logit models

Abstract This paper introduces unobserved heterogeneity in the binary logit model by adding a uniformly distributed disturbance term which enters the model additively with the observed regressor variables. The model is analytically simple and is observationally very similar to the more complicated model which assumes a normally distributed heterogeneity term.

A Simple Exposition of The Arbitrage Pricing Theory Approximation

This paper presents the Arbitrage Pricing Theory (APT) in a finite economy for the familiar case of quadratic utility functions. The standard APT result of a linear relationship between expected returns and the covariances of returns is shown to be approximately true, and an expression for the error of the approximation is given. Some suggestive calculations indicate that the error in the approximation is likely to be small.

Time Series Analysis in Pooled Cross-Sections

This article proposes the use of spectral methods to pool cross-sectional replications ( N ) of time series data ( T ) for time series analysis. Spectral representations readily suggest a weighting scheme to pool the data. The asymptotically desirable properties of the resulting estimators seem to translate satisfactorily into samples as small as T = 25 with N = 5. Simulation results, Monte Carlo results, and an empirical example help confirm this finding. The article concludes that there are many empirical situations where spectral methods canbe used where they were previously eschewed.

Australian Strike Activity in An International Context, 1964-85: Rejoinder

* Department of Statistics, The Faculties and Centre for Economic Policy Research, Research School of Social Sciences, Australian National University, GPO Box 4, Canberra, ACT 2601. Professor Blandy’s spirited critique of our paper allows us the welcome opportunity to emphasize the measurement problems inherent in international comparisons of strike data, to highlight the overall meaning of the results, and to update the econometric estimations. All three endeavours serve to reinforce our so-called ’strong’ and ’unwarranted’ conclusion that ’At the minimum, [the result] renders dubious strong statements concerning the influence of Australia’s idiosyncratic labour market arrangements on industrial disputation’ (Beggs & Chapman 1987a, 149). The first cannon ball fired at us is that ’These data show ... that if these