Search Results

Discusses the permanent income hypothesis and the mechanisms by which consumption smoothing responds to short‐run changes in income. It also reviews the role played by income and expectations in transmitting fluctuations through the economy. The chapter considers detailed econometric evidence on the excess sensitivity of consumption to present and lagged changes in income. Explanations involving non‐stationary income, the timing of consumption, durables, and habit formation are critically evaluated.

Develops the themes of Ch. 3 by exploring how consumption responds to innovations in income. The focus is on the econometric enquiry and presents insights into how measured income differs from permanent income and how to deal with the non‐stationarity of income. The chapter concludes by looking at how to analyse cases where the agents base their consumption plans on private information that is not available to the econometrician.

The ‘time‐series’ approach to econometrics is critically evaluated, and analytical test power response surfaces presented. Non‐stationarity, differencing and ‘error‐correction’ models (though not yet named) are discussed. Residual autocorrelation is reinterpreted using Sargan's common factor approach, and embryonic ideas presented on how to explain competing models’ findings to reduce the proliferation of conflicting results. Finally, the respective roles of criticism and construction are considered.

Presents the important properties of integrated variables and sets out some of the preliminary asymptotic theories essential for the consideration of such processes. It explores the concepts of unit roots, non‐stationarity, orders of integration, and near integration, and demonstrates the use of the theory in understanding the behaviour of least‐squares estimators in spurious regressions and in models involving integrated data. The theoretical analysis is accompanied by evidence from Monte Carlo simulations. Several examples are also provided to illustrate the use of Wiener distribution theory in deriving asymptotic results for such models.

We discuss models for multivariate counts observed at fixed spatial locations of a region of interest. Our approach is based on a continuous mixture of independent Poisson distributions. The mixing component is able to capture correlation among components of the observed vector and across space through the use of a linear model of coregionalization. We introduce here the use of covariates to allow for possible non‐stationarity of the covariance structure of the mixing component. We analyse joint spatial variation of counts of four fish species abundant in Lake Saint Pierre, Quebec, Canada. Models allowing the covariance structure of the spatial random effects to depend on a covariate, geodetic lake depth, showed improved fit relative to stationary models.

This chapter gives a brief overview of the basic concepts and topics used in the book. There exists a large literature on linear stationary models. The purpose of the present book is to look at nonlinear models in both a stationary and nonstationary framework. Linear techniques are contrasted with typical tools used to analyse nonlinearity, such as the conditional mean and the conditional variance, and Markov chain theory. Nonlinear parametric models are mentioned as well as nonparametric ones.

This chapter introduces time series data and outlines how it differs from cross sectional data. It also highlights how the object of interest when modelling time series data is the forecast, which differs from the object of interest in cross-sectional modelling, which is typically some parameter of interest that has an economic interpretation.