In 1944, Marschak and Andrews published a seminal paper on how to obtain consistent estimates of a production technology. The original formulation of the econometric model regarded the joint estimation of the production function together with the first-order nec- essary conditions for profit-maximizing behavior. In the seventies, with the advent of du- ality theory, the preference seemed to have shifted to a dual approach. Recently, how- ever, Mundlak resurrected the primal-versus-dual debate with a provocative paper titled “Production Function Estimation: Reviving the Primal.” In that paper, the author asserts that the dual estimator, unlike the primal approach, is not efficient because it fails to util- ize all the available information. In this paper we argue that efficient estimates of the production technology can be obtained only by jointly estimating all the relevant primal and dual relations. Thus, the primal approach of Mundlak and the dual approach of McElroy become nested special cases of our general specification. The theory of the price-taking cost-minimizing, risk-neutral firm is based upon the expectation of prices and quantities as the relevant information used by the entrepreneur in making her deci- sions. The econometrician intervenes later on and collects information about those quan- tities and prices. In so doing, measurement errors creep into the econometric specifica- tion. A two-phase procedure is suggested to implement the primal-dual approach. A Monte Carlo analysis indicates that our primal-dual approach produces estimates that ex- hibit a smaller variance of the estimates than those obtained from either the traditional primal or the dual specification separately implemented. A bootstrapping approach is used to compute the standard errors of the model’s estimates.

We prove that the symmetric and negative semidefinite modified Slutsky matrix derived by Samuelson and Sato (1984) for the money-goods model of the consumer, is identical to that derived by Pearce (1958) a quarter century before and restated sixteen years later by Berglas and Razin (1974). We also prove that these conditions are only sufficient for the problem at hand and are encompassed by a more general, modified Slutsky matrix that is necessary and sufficient as derived by Paris and Caputo (2001). These results have crucial relevance for testing the implications of consumer behavior.

In a recent paper, Mundlak assumes that the price-taking, risk-neutral and profit- maximizing entrepreneur makes his decisions on the basis of a planning model that maximizes expected profit using expected prices. In the same paper, the author asserts that when there is no sample price variation across competitive firms, it is impossible to estimate the supply and factor demand functions from cross-section data using a dual approach. In a famous paper, titled “To Dual or not to Dual,” Pope asserted a similar opinion. This paper shows that, using Mundlak’s assumption about planning decisions based upon expected profit, it is possible to use a dual estimator to estimate supply and factor demand functions. This objective is achieved by using Mundlak’s assumption about the individuality of the firm’s expectation process. A two-phase procedure is suggested to obtain consistent estimates of the expected quantities and prices which are then used, in phase II, in a nonlinear seemingly unrelated equations problem to obtain efficient estimates of the technological parameters.

For the past twenty-five years, Dusansky and his associated co-authors have published a long series of papers which are based on the same price-dependent utility function. The alleged price dependence, however, is fictitious in the sense that the level of exogenous money income can replace the commodity prices. The consequence is that the demand functions derived from Dusansky’s utility function are identical and observationally equivalent to the demand functions obtained from a prototypical utility function. Since all the market and environmental effects are revealed only through the demand functions, the specification and use of a utility function such as that used by Dusansky is irrelevant and uninformative for the analysis of any economic problem where prices enter the consumer utility function and whose goal is the detection of the effects of price-dependent preferences on the demand for real goods.

In 1944, Marschak and Andrews published a seminal paper on how to obtain consistent estimates of a production technology. The original formulation of the econometric model regarded the joint estimation of the production function together with the first-order necessary conditions for profit-maximizing behavior. In the seventies, with the advent of econometric duality, the preference seemed to have shifted to a dual approach. Recently, however, Mundlak resurrected the primal-versus-dual debate with a provocative paper titled "Production Function Estimation: Reviving the Primal." In that paper, the author asserts that the dual estimator, unlike the primal approach, is not efficient because it fails to utilize all the available information. In this paper we propose that efficient estimates of the production technology can be obtained only by jointly estimating all the relevant primal and dual relations. Thus, the primal approach of Mundlak and the dual approach of McElroy become special cases of the general specification. In the process of putting to rest the primal-versus-dual debate, we tackle also the nonlinear errors-in-variables problem when all the variables are measured with error. A Monte Carlo analysis of this problem indicates that the proposed estimator is robust to misspecifications of the ratio between error variances.

An exhaustive comparative statics analysis of a general price taking cost-minimizing model of the firm operating under the influence of price-induced technical progress is carried out from a dual vista. The resulting refutable implications are observable and thus amenable to empirical verification, and take on the form of a symmetric and negative semidefinite matrix. Using data from individual cotton gins in California's San Joaquin Valley, we empirically test the complete set of implications of the price-induced technical progress theory using both classical and Bayesian statistical procedures. We find that the data are fully consistent with the atemporal, cost-minimizing, price-induced microeconomic theory of technical progress.

In 1944, Marschak and Andrews published a seminal paper on how to obtain consistent estimates of a production technology. The original formulation of the econometric model regarded the joint estimation of the production function together with the first-order necessary conditions for profit-maximizing behavior. In the seventies, with the advent of econometric duality, the preference seemed to have shifted to a dual approach. Recently, however, Mundlak resurrected the primal-versus-dual debate with a provocative paper titled “Production Function Estimation: Reviving the Primal.” In that paper, the author asserts that the dual estimator, unlike the primal approach, is not efficient because it fails to utilize all the available information. In this paper we demonstrate that efficient estimates of the production technology can be obtained only by jointly estimating all the relevant primal and dual relations. Thus, the primal approach of Mundlak and the dual approach of McElroy become nested special cases of the general specification. In the process of putting to rest the primal-versus-dual debate, we solve also the nonlinear errors-in-variables problem when all the variables are measured with error.

The introduction of real-cash balances into the neoclassical model of the consumer wrecks havoc, in general, on the empirically observable refutable comparative statics properties of the model. We provide the most general solution of this problem to date by deriving a symmetric and negative semidefinite generalized Slutsky matrix that is empirically observable and which contains all other such comparative statics results as a special case. In addition, we clarify and correct two aspects of Samuelson and Sato's (1984) treatment of this problem.