Inmaculada Villanúa

Household Size and Residential Water Demand: An Empirical Approach

The effectiveness of pricing policies depends on the price elasticity of consumption. It is well documented that residential demand for water is influenced by heterogeneity associated with differences in the size of the household and socioeconomic characteristics. In this paper, we focus on household size. Our initial hypothesis is that users’ sensitivity to changes in price is different depending on the number of household members. To this end, we carry out an empirical estimation of urban water demand in Zaragoza (Spain) distinguishing between households with different sizes using data at the individual level. As far as we are aware, this approach to urban residential water demand is new in the literature. The analysis suggests that all households are sensitive to prices regardless of size. A more relevant finding is that small households are more sensitive to price changes.

Potential for Pricing Policies in Water Resource Management: Estimation of Urban Residential Water Demand in Zaragoza, Spain:

This paper presents an empirical study to estimate the urban residential water demand in Zaragoza, Spain; this allows the testing of the short-run sensitivity of water demand to changes in a set of socioeconomic variables and especially in prices. A residential water demand model is estimated using a dynamic panel data technique. Furthermore, three water demand equations have been proposed and two alternative process specifications are applied. The empirical application suggests that the linear demand specification is the most adequate. Finally, the results indicate that domestic demands are inelastic with respect to price.

Multivariate Linear Regression Model

A Multivariate linear regression model (MLRM) is a generalization of the univariate linear regression model which has been dealt with in Chapter 2. In this chapter we consider an endogenous or response variable denoted by y, which depends on a set of k variables x j (j = 1,…, k), called “regressors”, “independent variables” or “explanatory variables”, and an unobservable random term called “disturbance” or “error” term. The latter includes other factors (some of them non-observable, or even unknown) associated with the endogenous variable, together with possible measurement errors.

Which factors determine water saving behaviour? evidence from spanish households

In this paper we propose to answer the following questions: What does the adoption of water saving measures by Spanish households depend on? Which factors have the most influence on water saving behaviour? To this end we have conducted an empirical study in which a binary model (probit/logit) with interaction effects between city size, educational level and climatic area, along with other quantitative and qualitative variables, is estimated using household level data. The results of this estimation, together with the evaluation of probability changes that occur when any of the qualitative factors change, suggest that the level of income, the size of the city where the dwelling is, the educational level of the reference person and the climatic location of the city are factors that influence the attitude towards saving water.

The asymptotically efficient version of the information matrix test in binary choice models. A study of size and power

As Newey (1985) and Orme (1988) argue in the context of discrete binary choice models, the test of the information matrix (IM) is sensitive to heteroscedasticity and the incorrect distribution of the error term, with both these problems leading to inconsistency of the estimators obtained. This paper uses simulation experiments to analyse the size and power of the asymptotically efficient version of this test, with the aim of obtaining evidence on its capacity to detect such specification errors, considering different alternatives.

Measures of probability changes in binary choice models: a comparative study

A measure of probability changes in probit and logit dichotomous models is proposed based of the efficient use of sampling information, specifically using the average of the derivatives, as opposed to the traditional practice of calculating the derivative at the mean value. The two strategies are compared using a simulation exercise which reveals their respective robustness.