Thesis (MS)--Montana State University--Bozeman, 2008. / Typescript. Chairperson, Graduate Committee: Douglas J. Young. Includes bibliographical references (leaves 57-64).

The dynamics of demand for energy goods such as gasoline are complicated by investment decisions and behavioral habits. Both types of complication can be captured by a habits model, in which past consumption enters into an agent's current utility function. If the agent is forward-looking, or 'rational', then habits imply his consumption of the habit-forming good will be sensitive to his expectation of future market conditions, in particular future prices. This sensitivity implies, in turn, that demand and price elasticity will depend upon price volatility, and that the agent will respond differently to different types of price changes. Price elasticity measured over the mixture of price changes that occur in a given market will therefore underestimate the power of policy instruments that act through permanent or long-run price changes. This thesis examines the implications of rational habits on demand behavior in a multi-good setting, drawing motivation from and considering applications to gasoline demand. Chapter 1 introduces the theory of rational habits, examines a simple perfect-foresight model, and uses microeconometric techniques to look at an application to U.S. gasoline demand. Chapter 2 builds a theory model in which agents have rational habits and future prices are uncertain. The implications of this model are then utilized in Chapter 3, which uses macro-type econometric techniques to test for rational habits in international gasoline demand. The empirical evidence suggests that rational habits may indeed shape demand for gasoline and that traditionally-measured price elasticity should not be used to project consumers' responses to policy interventions.

This thesis consists of four self-contained papers related to energydemand and household cooking energy.Paper [I] examine the impact of price, income and non-economicfactors on gasoline demand using a structural time series model. Theresults indicated that non-economic factors did have an impact ongasoline demand and also one of the largest contributors to changes ingasoline demand in both countries, especially after the 1990s. Theresults from the time varying parameter model (TVP) indicated thatboth price and income elasticities were varying over time, but thevariations were insignificant for both Sweden and the UK. Theestimated gasoline trend also showed a similar pattern for the twocountries, increasing continuously up to 1990 and taking a downturnthereafter.Paper [II] studies whether the commonly used linear parametricmodel for estimating aggregate energy demand is the correctfunctional specification for the data generating process. Parametricand nonparametric econometric approaches to analyzing aggregateenergy demand data for 17 OECD countries are used. The resultsfrom the nonparametric correct model specification test for theparametric model rejects the linear, log-linear and translogspecifications. The nonparametric results indicate that the effect of theincome variable is nonlinear, while that of the price variable is linearbut not constant. The nonparametric estimates for the price variable isrelatively low, approximately −0.2.Paper [III] relaxed the weak separability assumption betweengasoline demand and labor supply by examining the effect of laborsupply, measured by male and female working hours on gasolinedemand. I used a flexible semiparametric model that allowed fordifferences in response to income, age and labor supply, respectively.Using Swedish household survey data, the results indicated that therelationship between gasoline demand and income, age and laborsupply were non-linear. The formal separability test rejects the null ofseparability between gasoline demand and labor supply. Furthermore,there was evidence indicating small bias in the estimates when oneignored labor supply in the model.Paper [IV] investigated the key factors influencing the choice ofcooking fuels in Ghana. Results from the study indicated thateducation, income, urban location and access to infrastructure werethe key factors influencing household’s choice of the main cookingfuels (fuelwood, charcoal and liquefied petroleum gas). The study alsofound that, in addition to household demographics and urbanization,the supply (availability) of the fuels influenced household choice forthe various fuels. Increase in household income was likely to increasethe probability of choosing modern fuel (liquefied petroleum gas andelectricity) relative to solid (crop residue and fuelwood) and transitionfuel (kerosene and charcoal).

The rapid growth of gasoline consumption in the USA for the last decades brings much concern to scientists and politicians. Therefore many researchers investigated the influence of the main factors that have an impact on gasoline demand. In our study we tried to estimate gasoline demand in the USA, using national time series data for the period 1984-2010. Gasoline demand function considered in this paper includes price, income, fuel efficiency and gasoline consumption in previous year, as the main explanatory variables. The model is estimated using simultaneous equations and cointegration and error correction model (ECM). The results of both methods show a significant price and income effect on gasoline demand. The price is found inelastic and its impact on gasoline demand is very small, however when we correct for endogeneity of price variable, we obtain higher price elasticity. The results on income elasticities obtained from two methods are dubious, since the two methods gave us the different results. In whole, an income raise will lead to an increase of consumption, gasoline demand is inelastic with respect to income in the short-run, while in the long-run it is found to be elastic according to 2SLS method, while the results of cointegration method indicate that gasoline response to income changes is higher in the short-run than in the long-run. Lag of error term suggests that around 57% of adjustment between short-run and long-run occurs during the first year.

Using theoretical relations as a source of econometric specifications might lead a researcher to models that do not adequately capture the statistical regularities in the data and do not faithfully represent the phenomenon of interest. In addition, the researcher is unable to disentangle the statistical and substantive sources of error and thus incapable of using the statistical evidence to assess whether the theory, and not the statistical model, is wrong. The Probabilistic Reduction Approach puts forward a modeling strategy in which theory can confront data without compromising the credibility of either one of them. This approach explicitly derives testable assumptions that, along with the standardized residuals, help the researcher assess the precision and reliability of statistical models via misspecification testing. It is argued that only when the statistical source of error is ruled out can the researcher reconcile the theory and the data and establish the theoretical and/or external validity of econometric models. Through the approach, we are able to derive the properties of Beta regression-like models, appropriate when the researcher deals with rates and proportions or any other random variable with finite support; and of Lognormal models, appropriate when the researcher deals with nonnegative data, and specially important of the estimation of demand elasticities. / Ph. D.

This dissertation thesis consists of six papers on macroeconomics, international economics, and energy economics. All the papers are tied together by the use of meta-regression analysis, which is essential for the derivation of robust policy-relevant conclusions from often conflicting results presented in the empirical literature. I use meta-analysis to quantitatively synthesize the reported research results on a given topic, correct the literature for publication selection bias, and filter out the effect of various misspecifications present in some primary studies. My results can be summarized as follows: 1) The elasticity of intertemporal substitution in consumption, a key input to all dynamic models in finance and macroeconomics, varies significantly across countries. The differences can be explained by the level of stock market participation, when countries with higher participation exhibit larger values of the elasticity; the mean reported elasticity is 0.5. 2) The effect of borders on international trade, which most authors find to be surprisingly large, can be explained away by innovations in methodology introduced in the last decade. When these innovations are taken into account jointly, the border effect disappears for developed countries, and is relatively small for developing countries. 3) When...