Search

Machine learning (ML) is a novel method that has applications in asset pricing and that fits well within the problem of measurement in economics. Unlike econometrics, ML models are not designed for parameter estimation and inference, but similar to econometrics, they address, and may be better suited for, problems of prediction. While some ML methods have been applied in econometrics for decades, their success in prediction has been limited, and examples of this abound in the asset pricing literature. In recent years, the ML literature has advanced new, more efficient, computation methods for regularization, modeling nonlinearity, and improved out-of-sample prediction. This article conducted a comprehensive, objective, and quantitative bibliometric analysis of this growing literature using Web of Science (WoS) data. We identified trends in the literature over the past decade, the geographical distribution of articles, authorship, and institutional contributions worldwide. The paper also identifies the dominant literature using citations in WoS and discusses computational algorithms that are expanding the econometric frontiers in asset pricing. The top cited papers were reviewed, highlighting their contribution. The limitations of ML learning methods and recent advances in ML were used to provide a conic view to future ML econometric practice.

This paper examines two interrelated issues in commodity markets, namely, the cyclical relationship between stocks and commodities and the function of commodity and agribusiness indexes in portfolios. A high negative correlation has existed between stock and commodity prices over the past 140 years. Moreover, the two markets have alternated in price leadership with 29-32-year cycles. The recent price dominance in agricultural commodities started in 2000, a result supported by the empirical results of the portfolio allocation analysis. For a risk-averse investor, irrespective of the period analyzed, placing funds in agribusiness and/or agricultural commodity indexes was sound investing.

The export-led growth (ELG) hypothesis for the Philippines is examined by adopting a semiparametric approach under two levels of temporal aggregation. To assess the impact of model specification on the ELG hypothesis, parametric and semiparametric error-correction models (ECMs) are estimated using Philippine annual and quarterly data on gross domestic product (GDP), exports, exchange rates, and gross fixed-capital formation, focusing on the role of exchange rates. The causal relationship between exports and economic growth is examined using the Granger-causality procedure. It can be concluded that for the Philippines, the ELG hypothesis is (a) sensitive to model specification and (b) affected by different levels of temporal aggregation and by the inclusion or exclusion of exchange rates. The general results on bidirectional causality between exports and economic growth suggest that the Philippines could enjoy economic prosperity by strengthening its trade and investment policy and gearing it toward opening up the economy.

This paper examines the relationship between New York coffee futures and cash export prices in Guatemala and Honduras . Cointegration tests suggest that the futures market is serving its price discovery function, and provides a vehicle by which to manage the domestic price risk in export countries. However, further analysis finds that as the percent of speculative open interest increases in the coffee futures market, price volatility increases. This suggests that cash market price risk in exporting countries may actually increase as a result of futures trading activity in developed country futures exchanges.

ables suggested by the theory. Stepwise procedures, A credit scoring function incorporating statistical for instance, have been used for variable selection selection criteria was proposed to evaluate the credit in bankruptcy prediction. These procedures, howworthiness of agricultural cooperative loans in the ever, examine variables in a sequence usually deterFifth Farm Credit District. In-sample (1981-1986) mined by the data. The purpose of this study is to and out-of-sample (1988) prediction performance introduce a procedure that supplements previous of the selected models were evaluated using rank studies by giving further consideration to the specitransformation discriminant analysis, logit, and fication of a statistical model within a management probit. Results indicate superior out-of-sample per- oriented framework and the evaluation of predictive formance for the management oriented approach performance of that model. Four specific objectives relative to classification of unacceptable loans, and were associated with the classification and predicpoor performance of the rank transformation in out- tion of agricultural cooperatives into two groups of-sample prediction. (acceptable and unacceptable) according to the performance criteria provided by the Bank for Coopera

Per capita seafood consumption, which has been increasing was 15.5 lbs. in 1987 compared to 10.3 lbs. in 1980. This increase occurred during a period of increasing aquaculture production, especially catfish. Per capita catfish consumption increased from .24 lb. in 1983 to .58 lb. in 1988. A nationwide household survey indicates catfish is the fifth most popular seafood item in the United States. A logit analysis was used to identify socioeconomic factors significantly influencing catfish consumption both at home and away from home. Race, religious preference, and household size are significant factors along with perceived regional availability.

A review of literature on applications of Granger causality to problems in international agricultural economics research is summarized. The review relates to cointegration theory, and it identifies the areas where recent econometric developments may be of value. Testing procedures are outlined, and a discussion is provided on questions such as non-stationarity and asymptotic distribution of non-causality tests, the relationship between cointegration and causation, the relative merits of various testing procedures, and concerns about testing bivariate causality in higher dimensional models. Finally, a recent econometric development is discussed and its future use in applied research is discussed. © 1999 Elsevier Science B.V. All rights reserved.

The objective of this study is to provide an empirical evaluation of the expected relationship between cash and futures prices for fluid milk. This is done using historic cash prices from 1988 to 1995, and making inferences about how futures prices would have behaved if they had traded during this sample period. Futures prices are simulated over the sample period based on two assumptions about futures market behavior for fluid milk. The first is that the futures market will essentially price the Basic Formula Price (BFP). The BFP is an estimate of the previous month's pay price for Grade B manufacturing milk in Minnesota and Wisconsin adjusted for contemporaneous changes in the prices of manufactured milk products. It establishes the federal milk marketing order minimum Grade A pay price for Class III milk used to make cheese, and is the mover of both the minimum Class II price for milk used in soft manufacturing products and the minimum Class I price for beverage milk (Jesse).

The small sample performance of Granger causality tests under different model dimensions, degree of cointegration, direction of causality, and system stability are presented. Two tests based on maximum likelihood estimation of error-correction models (LR and WALD) are compared to a Wald test based on multivariate least squares estimation of a modified VAR (MWALD). In large samples all test statistics perform well in terms of size and power. For smaller samples, the LR and WALD tests perform better than the MWALD test. Overall, the LR test outperforms the other two in terms of size and power in small samples.

The temporal relationship between Chicago corn and soybean cash prices, nearby futures prices, and interest rates is examined using daily 1980-1989 data. Johansen cointegration tests suggest joint movement of the three series over the data period considered. In addition, analyses of individual crop years, which is consistent with previous work, shows co-movement between cash, futures, and interest rates in years when bivariate cointegration between cash and futures prices was not found. The results provide initial empirical evidence that a potential limitation of previous research in the study of cash- futures simple efficiency has been the exclusion of the interest rate as a common stochastic factor explaining equilibrium in models of cash and futures prices. (This abstract was borrowed from another version of this item.)