Knowledge that Transforms

Recent studies by Durbin and Watson [5], L'Esperance and Taylor [10], Koerts and Abrahamse [8], Tillman [15], Vinod [16], Savin and White [14] and others have shown increasing interest in the test of autocorrelation based on the d statistic proposed by Durbin and Watson [3 and 4]. The focus of these papers has been the computation of the exact distribution of d and the power of the test based on d. The exact distribution of d has been developed by Imhof [7] and Pan Jie-Jian [12]. However, few of the generally available computer programs for regression analysis incorporate these methods,2 possibly because of computational costs, particularly for large samples. With the Durbin and Watson [4] tables the bounds test is restricted to time series regressions with 15 to 100 observations and a maximum of 5 regressors in addition to unity. Often regression studies do not meet these restrictions since samples with less than 15 observations commonly occur with annual time series and regressions with more than 5 regressors are often found in the context of simultaneous equations and of distributed lags.3 In this paper we present extended tables for the bounds test. Our tables can be used for samples with 6 to 200 observations and for as many as 20 regressors.

[This paper considers the least squares estimator of @? extasciicircum2 in the linear model with disturbances generated by a first-order autoregressive process. It is well known that the estimator is biased. In this paper an attempt is made to establish bounds for the bias. These bounds depend on n, k, and @r, where n is the number of observations, k is the number of parameters, and @r is the (positive) coefficient of the autoregressive process.]

[It has already been proven that when production is described by differentiable supply functions, the equilibrium correspondence is continuous for "most" economies [7 and 8]. The present paper generalizes this result to situations where production activities are described through a certain class of correspondences: namely, those which have a smooth graph and are such that the profit function is differentiable.]

[The Rawlsian maximin is defined for situations involving risk and applied to growth with an uncertain technology. Existence and uniqueness are discussed and it is shown to unambiguously lead to at least the same savings as under certainty.]

A household time-allocative model which explicitly takes into account the economic contribution of children in agricultural areas of less-developed countries is applied to direct-level data pertaining to the rural population of India. Joint family decisions concerning fertility and the allocation of male and female child time to schooling and work activities are examined empirically in a simultaneous equations system. The properties of the formal model are used to derive inferences from the parameter estimates with respect to the shadow price configuration influencing these joint decisions.

[This paper demonstrates how a two or three component error structure can be used with seemingly unrelated regressions. Its application may be particularly useful with large panel data sets when the researcher wishes to estimate several equations simultaneously and believes that errors both between and within equations are correlated over time and across units. Relatively simple algorithms are presented for estimation of the error covariance matrix and generalized least squares coefficients.]

The exact stochastic character of observed data from a Markov process is derived for the case where only aggregate stocks, as opposed to individual transitions, are observed. Particular attention is devoted to the distinction between data generated by a panel study, where a single group of individuals is followed over time, and that generated by random sampling, where the observed groups are not identical over time. Several alternative estimators are developed which take into account the particular stochastic structure of the data.