Reviews the book "A Study of the Application of Statistical Sampling to External Auditing," by T.W. McRae.

A general equilibrium model of optimal employment contracts is developed where firms have better information about labor's marginal product than workers. It is optimal for the wage to be tied to the level of employment, to prevent the firm from falsely stating that the marginal product is low and cutting the wage. It is shown that an observed aggregate shock that leads to an interindustry shift in labor demand and that would have no effect on total employment under symmetric information leads to a reduction in employment when firms and workers have asymmetric information.

Article plaidant en faveur de l'utilisation d'estimateurs d'equations simultanees pour estimer les modeles d'effets aleatoires dynamiques d'un panel de donnees

This paper considers the null hypothesis that the errors on a regression equation form a random walk. By using the standard Durbin-Watson assumptions, we derive three test statistics that are uniformly most powerful against the alternative hypothesis that the errors are being generated by the stationary first order Markoff process. Unfortunately, the tabulated lower and upper bounds are too wide apart and so we compare the powers of the three tests using simulated as well as economic data. It is then recommended that the Imhof routine should be attached to standard regression programs to calculate the exact limit of the Berenblut-Webb statistic.

J. D. Sargan, Alok Bhargava, Maximum Likelihood Estimation of Regression Models with First Order Moving Average Errors when the Root Lies on the Unit Circle, Econometrica, Vol. 51, No. 3 (May, 1983), pp. 799-820

THE study of merger activity has been of long-standing interest to economists as well as the financial community. References to merger activity in American industry generally acknowledge three major merger movements. The first one occurred during the turn of the century, the second one during the 1920s. Stigler (1950) describes the second merger wave as being for oligopoly in contrast with the earlier for monopoly movement. Increased market power through consolidation and corporate concentration and operating economies of scale were identified as motives for mergers during these two waves. Horizontal mergers (i.e., mergers between direct competitors) were relatively more important during the first merger wave with vertical mergers (i.e., mergers between firms with prior buyer-seller relationships) being significant in the second wave.' Currently the United States is in the midst of its third major merger wave which began after the end of World War II. This has become known as the conglomerate merger wave because of the emphasis on mergers between unrelated firms or firms seeking product extension objectives (i.e., mergers between firms functionally related in terms of distribution and/or production facilities but whose products are not directly competing).2 The direction of the current merger wave can be partially explained by the fact that the Celler-Kefauver amendment to the Clayton Act in 1950 discourages horizontal and vertical mergers. While many authors have engaged in the study of mergers in the United States, the empirical examination of changes in aggregate merger activity has been limited both as to type and time period covered. Nelson (1959) first examined changes in quarterly merger activity during the 1895-1920 period and found a high positive correlation between changes in merger activity and changes in stock prices, and a positive but lower correlation between mergers and industrial activity. Further study by Nelson, however, showed that for the 1919-1954 period the relationship between mergers and stock prices was considerably weaker. In a follow up study, which extended aggregate merger data through 1962, Nelson (1966) concluded that merger activity exhibited a positive and highly consistent response to changes in business activity (as measured by the reference or business cycle). In addition to the efforts by Nelson, Weston (1961) examined annual changes in merger activity during the interwar period (between World War I and World War II). Using a multiple regression model, Weston found merger activity to be significantly related to stock prices but not significantly related to industrial production activity. Previous studies provide only limited insights into the structural (especially lead-lag) relationships between aggregate merger activity and macroeconomic/market factors. The literature is particularly void of empirical studies which investigate such relationships during the current merger period.3 It is this subject which we address in this paper. We employ a data-based multiple time series approach to develop an explanatory model for describing changes in the incidence of Received for publication July 14, 1981. Revision accepted for publication December 17, 1982. * University of Colorado, University of Iowa, and University of Denver, respectively. Computer facility support from the University of Iowa along with multiple time series programs provided by the University of Wisconsin-Madison are gratefully acknowledged. We also wish to thank the referees for their helpful comments. ' These two merger waves or movements were extensively studied, either separately or together, by Eis (1969), Markham (1955), Nelson (1959), Stigler (1950), Thorp (1941), and Weston (1961), as well as others. 2 The current merger movement, either separately or in conjunction with the earlier movements or waves, was analyzed by Lintner (1971), Lynch (1971), Markham (1973), Nelson'(1966), Reid (1968), and Steiner (1975). 3 International investigation of aggregate merger activity during the 1960s and 1970s is reported in Mueller (1980). Visual examination of the movement of mergers, GNP, and stock prices in Belgium suggested generally positive relationships. Aggregate merger activity was compared individually against economic activity (GDP), gross fixed investment, and share prices in West Germany. During the 1960s mergers tended to move in step with changes in economic activity and investment while lagging share prices. However, in the 1970s merger activity tended to lead the other aggregate measures. The best overall relationship was between merger activity and share prices.

This paper investigates the production technology facing computerized credit unions in Canada. A full system of translog cost equations is estimated in order to test for economies of scale, economies of scope, and other production characteristics in a multiproduct context. The regression results indicate that most of the credit unions in our sample experience significant increasing returns to scale as they expand their level of output. There is also evidence of cost complementarity or economies of scope in their mortgage and other lending activities. As a result, legislation which limits the ability of credit unions to grow and diversify will likely raise the operating costs of this important group of financial institutions. Additional structural tests of the most general translog specification suggest that none of the restrictive production conditions commonly imposed by other researchers using Cobb‐Douglas and CES specifications provide a valid representation of credit union technology. The results of many earlier studies are therefore open to question.