It sometimes happens that the unobservable state vector of a linear dynamic model expressed in the state space is subject to known restrictions. Incorporation of this information into the Kalman filter procedure will increase the efficiency of estimation. It is shown that a simple augmentation of the measurement equation constrains the estimated state vector to obey the restrictions. The method applies whether the restrictions are time-invariant, time-varying, linear, or nonlinear.

Two hypotheses are tested in this paper. The first is whether the appropriate geographic market for certain banking services is national, instead of local. The second is whether the definition of banking "product" as all banking services is too broad.

Brent, Richard P., Algorithm 488: A Gaussian Pseudo-Random Number Generator, Communications of the ACM 17 (Dec. 1974), 1704-1706. Durbin, James, and Geoffrey S. Watson, Testing for Serial Correlation in Least Squares Regression I, II, III, Biometrika 37 (1950), 409-428; 38 (1951), 159-178; 58 (1971), 1-42. Godfrey, Lester G., Misspecification Tests in Econometrics (Cambridge: Cambridge University Press, 1988). Imhof, J. P., Computing the Distribution of Quadratic Forms in Normal Variables, Biometrika 48 (1961), 419-426. Judge, George G., R. Carter Hill, William Griffiths, Helmut Lutkepohl, and Tsoung-Chao Lee, Introduction to the Theory and Practice of Econometrics (New York: Wiley, first edition, 1982; second edition, 1988). White, Kenneth J., S. Donna Wong, Diana Whistler, and Shirley Haun, SHAZAM User's Reference Manual, Version 6.2 (New York: McGraw-Hill, 1990).

This paper investigates the relation between substitution possibilities in manufacturing production between capital and two labor inputs, blue collar and white collar workers. Griliches found in 1969 that unskilled.labor was more easily substituted for by capital than skilled labor. Griliches called this capital-skill complementarity. The capital-skill complementarity hypothesis has implications for the aggregation of labor inputs as well as for employment of labor categories and income distribution between factors. This paper investigates the robustness of the capital-skill complementarity hypothesis on Swedish data by varying model assumptions concerning economies of scale and technological growth.

This paper compares the industry characteristics that determine U.S. export competitiveness with those that affect the export competitiveness of U.S. multinationals. Higher R&D and human capital intensities are associated with high U.S. shares in exports and, more strongly with high U.S. multinationals' shares, and higher labor content with low shares. Within the multinationals, high R&D intensity leads to a larger share of the firms' exports being supplied from the U.S. parent. The higher the labor intensity and the level of advertising expenditures in an industry, the larger the proportion of the firms' exports supplied by the foreign affiliates.

The ability of planners in Poland and the U.S.S.R. to recognize and act to eliminate market disequilibrium in the markets for grain and meat is tested by means of an econometric model of grain and meat production, consumption, and trade. Planners' perceptions of excess demand for grain, meat, and foreign exchange are shown to influence production and trade decisions in a way that tends to reduce excess demand or supply. Nevertheless, the markets for grain, meat, and foreign exchange are shown to be characterized by excess demand or supply for much of the sample period.