Knowledge that Transforms

G REAT WORKS often do not immediately get the attention they deserve. David Hume's Treatise of Human Nature fell, in his own words, dead born from the press.' John Stuart Mill's Subjection of Women was received coolly (it was the only book of Mill on which his publisher lost money).2 Bertrand Russell has recorded his disappointment at the reception that Principia Mathematica got: I used to know of only six people who had read the later parts of the book. Three of these were Poles, subsequently (I believe) liquidated by Hitler.3 remaining three readers apparently got back to their old lazy ways soon enough: The other three were Texans, subsequently successfully assimilated-a result as bad as being liquidated so far as the effect on the deserted Principia Mathematica

Jerry G. Thursby, A Test Strategy for Discriminating between Autocorrelation and Misspecification in Regression Analysis: Reply, The Review of Economics and Statistics, Vol. 67, No. 1 (Feb., 1985), pp. 177-178

This study examines institutional production of higher education. An interesting aspect of this production process is that two of the more important inputs, students and faculty, enter upon considerable self-selection. To address this interdependence, the production relationship is specified by a three-equation simultaneous model in which the quality of college output, faculty, and students are treated endogenously. The significance of simultaneity is demonstrated in an em- pirical model estimated via three-stage least-squares for a sam- ple of 174 private undergraduate institutions. The results offer clear implications regarding the allocation of institutional re- sources across the basic factors in educational production. This paper examines the input-output relationship for private undergraduate education. The study falls generally within the economic literature that has analyzed the educational process via a production function specification (Astin, 1968; Bowles, 1970; Summers and Wolfe, 1977; Hanushek, 1979; McGuckin and Winkler, 1979). However, we extend the argument that research assessments of the educational process are not dealing with a production function in the classic sense. For example, the purchaser of the product-the student-is also one of the more important inputs. Further, the non-profit orientation of most universities reduces incentives for cost minimization.' The implication is that the educa- tional process is far more complicated than a simple, production-functional rendering indicates. To demonstrate this point, we estimate a three-equation simultaneous model in which the quality of students, faculty, and college output are treated endogenously.2 This study's broad objective is to identify more clearly the relative contribution of the many human and nonhu- man resources combining to produce quality under-

Peter K. Clark, Jane T. Haltmaier, The Labor Productivity Slowdown in the United States: Evidence from Physical Output Measures, The Review of Economics and Statistics, Vol. 67, No. 3 (Aug., 1985), pp. 504-508

Garbade, Kenneth, Methods of Examining the Stability of Regression Coefficients, Journal of the American Statistical Association 72 (Mar. 1977), 54-63. Godfrey, L. G., Against General Autoregressive and Moving Average Error Models when the Regressors Include Lagged Dependent Variables, Econometrica 46 (Sept. 1978), 1293-1301. Harvey, Andrew C., and Garry D. A. Phillips, for Stochastic Parameters in Regression S.S.R.C. supported project on Testing for Specification Error in Econometric Models, Working Paper No. 1, University of Kent at Cantebury (1976). _ Maximum Likelihood Estimation of Regression Models with Autoregressive-Moving Average Disturbances, Biometrika 66 (1979), 49-58. Johnson, N. L., and S. Kotz, Distribution in Statistics: Continuous Multivariate Distributions (New York: Wiley, 1972). LaMotte, R., and A. McWhorter, Jr., An Exact Test for the Presence of Random Walk Coefficients in a Linear Regression Model, Journal of the American Statistical Association 73 (Dec. 1978), 816-819. Mizon, Grayham E., and David F. Hendry, An Empirical Application and Monte Carlo Analysis of of Dynamic Specification, Review of Economic Studies 47 (Jan. 1980), 21-46. Pagan, Adrian R., Some Identification and Estimation Results for Regression Models with Stochastically Varying Coefficients, Journal of Econometrics 13 (1980), 341-363. Pagan, Adrian R., and K. Tanaka, A Further Test for Assessing the Stability of Regression Coefficients, Australian National University, unpublished manuscript (1979). Quandt, Richard E., Tests of the Hypothesis that a Linear Regression System Obeys Two Separate Regimes, Journal of the American Statistical Association 55 (Dec. 1960), 873-880. Rosenberg, Barr, The Analysis of a Cross-Section of Time Series by Stochastically Convergent Parameter Regression, Annals of Economic and Social Measurement 2 (1973), 399-428. Watson, Mark W., A Test for Regression Coefficient Stability when a Parameter Is Identified only Under the Alternative, H.I.E.R. Discussion Paper 906 (1982). , Applications of Kalman Filter Models in Econometrics, Ph.D. Dissertation, University of California at San Diego (1980). Watson, Mark W., and Robert F. Engle, Alternative Algorithms for the Estimation of Dynamic Factor, MIMIC, and Varying Coefficient Regression Models, Journal of Econometrics 23 (Dec. 1983), 385-400.

The association between parents' health practices and children's health requirements is explored in this paper. A variance components model, incorporating unobserved family effects in the estimation procedure, is used. Mother's education is positively related to both children's days of recuperation and visits to medical facilities. Although each of the health practices examined here is significantly related to the mother's education, each health practice is also related to children's health needs independently of mother's education: Good maternal health practices are associated with 1.7 additional days of recuperation and 2.3 additional visits to medical facilities for a child per annum.

Alan L. Halvorson, Switching Regression Estimates of a Sequential Production Process: The Case of Underground Coal Mining, The Review of Economics and Statistics, Vol. 67, No. 1 (Feb., 1985), pp. 161-165