An econometric model of the petroleum industry

This paper describes a forty-two nonlinear equation model of the U.S. petroleum industry estimated over the period 1946 to 1973. The model specifies refinery outputs and prices as being simultaneously determined by market forces while the domestic output of crude oil is determined in a block-recursive segment of the model. The simultaneous behavioral equations are estimated with nonlinear two-stage least-squares adjusted to reflect the implications of autocorrelation for those equations where it appears to be a problem. A multi-period sample simulation, together with forecasts for 1974 and 1975 are used to evaluate the model's performance. Finally it is used to forecast to 1985 under two scenarios and compared with the Federal Energy Administration's forecast for the same period.     

Property taxation and the demand for housing: An econometric analysis

There is disagreement among economists regarding the effect of a local increase in property taxation on the housing market. In defining the price of housing services studies of the demand for housing have treated the property tax exclusively as an excise tax on housing consumption. Two recent theoretical developments suggest this is a misrepresentation of the tax. One theory holds that the excise effects of property taxation may be shifted backward to the factors employed in the production of housing. The other theory concludes that the property tax is not an excise, but rather serves as an efficient price for local public services. To investigate these hypotheses, data from the Annual Housing Survey were employed to estimate a housing demand model which included the net effective property tax rate among the set of independent variables. In addition to revealing the property tax-housing demand relationship, the model provides more reliable estimates of income and price elasticities by eliminating specification errors found in previous studies. Results indicate that the property tax reduces the housing consumption of central city homeowners, but does not distort the suburban housing market.     

An econometric model of housing price, permanent income, tenure choice, and housing demand

This paper addresses the determination of housing price, permanent income, tenure choice, and housing demand. Full housing demand elasticities incorporate the interactive effects among the four stages of the model. Price and income have major effects in the tenure choice equation. Sociodemographic variables, such as age, have complex effects that may be lost in simpler forms of estimation.     

The demand for retailer-financed instalment credit: An econometric analysis

During the mid- to late 1980s the UK's Chancellor of the Exchequer has attempted to reduce the volume of consumer credit extended by increasing interest rates rather than by re-introducing terms controls. This paper presents estimates of demand functions for new credit extended by retailers which was financed by them and repaid by instalments. Following earlier papers, a stock-adjustment model is presented that is extended to allow for credit rationing. The results suggest that the demand for such new credit extended is related negatively to terms control and positively to personal disposable income and expectations. Demand was not found to be related to (a proxy for) the nominal interest rate charged by retailers (although it was found to be positively related to the real rate). The former finding is consistent with questionnaire evidence that consumers are unaware of the interest rate that they pay for credit. Elasticities of demand are presented.     

An econometric model of a retail firm

Existing models of retail resource allocation generally specify response functions in a somewhat ad hoc manner. These are not usually derived from an explicit model of consumer maximization, and they generally do not explicitly consider the supply side of the market. This paper shows how the model of Ehrlich and Fisher (1982) can be used to provide insights into the proper specification of these functions. We illustrate the application of this model on data from a retail chain; our application extends work in Ratchford and Stoops (1988) to the demand side of the market. Potential areas of application of the model are to understanding the demand for labor and advertising services by consumers, and to the measurement of retail productivity.     

Keeping off the grass? An econometric model of cannabis consumption in Britain

This paper presents estimates of a dynamic individual‐level model of cannabis consumption, using data from a 1998 survey of young people in Britain. The econometric model is a split‐population generalization of the non‐stationary Poisson process, allowing for separate dynamic process for initiation into cannabis use and subsequent consumption. The model allows for heterogeneity in consumption levels and behavioural shifts induced by leaving education and the parental home. Copyright © 2004 John Wiley & Sons, Ltd.     

Residential energy demand in the United States: A regional econometric analysis

A static equilibrium and a dynamic partial adjustment model of residential demand for electricity and natural gas are presented and estimated for the United States over a recent period characterized by sharply increasing energy prices. The static model is estimated using Ordinary Least Squares while the instrumental variables method is used for the dynamic partial adjustment model. The estimates of long-run elasticities suggest the residential demand for electricity and natural gas are price and income elastic. Intercept and slope dummies used in the models identify significant regional differences in demand functions.     

An econometric model of nonlinear dynamics in the joint distribution of stock and bond returns

This paper considers a variety of econometric models for the joint distribution of US stock and bond returns in the presence of regime switching dynamics. While simple two‐ or three‐state models capture the univariate dynamics in bond and stock returns, a more complicated four‐state model with regimes characterized as crash, slow growth, bull and recovery states is required to capture their joint distribution. The transition probability matrix of this model has a very particular form. Exits from the crash state are almost always to the recovery state and occur with close to 50% chance, suggesting a bounce‐back effect from the crash to the recovery state. Copyright © 2006 John Wiley & Sons, Ltd.     

An econometric model of internal migration and development: extensions and tests

The author extends a previous work on migration in Italy "from 1958-1976 to 1958-1981, tests for the stability of the model and its coefficients, and uses the model for policy simulations and forecasting. The model performs as well over the extended sample period as over the original period and, even more important..., the model is found to be quite stable. This is remarkable in view of the economic turmoil that characterized the years by which the original sample period was extended."     

The econometric forecasting model of Czechoslovakia

Conclusion The result of the construction, estimation, testing and forecasting uses of the VVS-2 model testify to the expediency of using comprehensive econometric models in socialist economy. The VVS-2 model expresses at a satisfying rate of accuracy the quantitative relations between the fundamental indicators of Czechoslovak economy and has produced satisfactory results also in calculating short-term forecasts. Some new methods and computer programs that have been developed and employed for model estimation may be considered a contribution towards the development of applied econometrics in socialist countries.At the Computing Research Centre, United Nations D.P. in Bratislava, research work has continued on the development and improvement of further comprehensive econometric models. Within this framework the VVS-2 model will be permanently reestimated and possibly also extended and re-specificated according to the practical needs of macroeconomic analysis and planning.Authors are indebted to Professor Anton Klas, director of the Computing Research Centre, United Nations D.P., for creating very favourable conditions for the research work.     

Bootstrapping the process of model selection: AN econometric example

If a researcher has mined the data (i.e. selected an empirical model based on a series of trial estimates), inferences based on the final set of results are in general incorrect. This note treats the entire data mining process as an estimator and shows how a bootstrapping technique may improve the quality of inference. The method is applied to an empirical example on the deterrent effects of capital punishment.     

Determining the final form of a linear dynamic econometric model

This paper outlines a method for determining the final form and associated quantities of a linear or linearized dynamic econometric model. The method is based on the Cauchy integral formula which is approximated by a Riemann sum and evaluated with the fast Fourier transform algorithm. The approach is seen to fit naturally into both the time and frequency domain methods of analyzing dynamic econometric models. An empirical application illustrates the use of the technique.     

An econometric procedure for estimation of a generalized systemic gravity model under incomplete information about the system

Gravity spatial interaction models have a long history and a wide scope of empirical applications, Alonso (1973) proposed a generalized model whose structure subsumes major versions of the gravity model in the literature as special cases. Little attention has been given to how the general model might be estimated, or if it is estimable at all. This paper develops an econometric procedure for situations where all places in a geographic system are not included in the observations. The general model and various constrained versions are empirically estimated on a sample of intermetropolitan migration data and compared.     

A labor-oriented quarterly econometric forecasting model of the youngstown-Warren SMSA

Our model contains forty-two stochastic equations and thirty-two identities designed to explain variation in manhours of work, employment, weekly wages and the wage bill by sector of activity for the Youngstown-Warren SMSA. Methodology in the development of these equations is discussed and the regression results shown. The paper evaluates the simulation results of the model by showing the root mean squares error and percent root mean squares error for the major aggregates using both dynamic and historic system simulations.     

A dynamic econometric model of agricultural wage determination in Bangladesh

Economists applied data from 1949-1950 and 1980-1981 to a new dynamic model to examine the dynamics of determinants of agricultural wages in Bangladesh, particularly the effect of changes in relative prices of rice (the staple food) and productivity. Just a 20% rise in the price or rice was passed on in the agricultural wage rate within the current year. About 50% was passed on in the long run, however. Therefore an increase in the price of rice reduced the rice purchasing power of agricultural wages in the short and long term. In fact, the importance given to rice in the long run real wage rate was almost the same as the mean proportion of expenditure that an agricultural laborer in Bangladesh committed to rice and closely related food staples. Thus arise in the price of rice in comparison to other goods had limited effects on the long run real wage in terms of the bundle of goods typically consumed, but very adverse effects in the short run placing a high burden on the rural poor. On the other hand, the long run real wage rate fell considerably between the mid 1960s-early 1980s when overall agricultural productivity increased. The economists pointed out that this increased productivity may not have lowered long run real wage rates, but instead mitigating factors may have contributed to this fall. For example, population growth, rising landlessness, and insufficient economic growth in nonagricultural sectors resulted in a consistent growth in the labor supply. In conclusion, this new dynamic model showed that Bangladesh cannot depend only on agricultural growth to reduce the poverty of farmers.