Microeconometric Analysis of Residential Water Demand

Abstract

I present a microeconometric model to analyse residential water demand using panel data. Pricing has an increasing-block structure. Database contains individual consumptions from water meters and lacks further information. Permanent income is treated as an unobservable individual e¤ect determining optimal consumption. I also consider a time-varying shock to connect latent and observed demands. The economic setup gives rise to a random e¤ects model with a nonlinear individual e¤ect. I use likelihood-based indirect inference for estimation. I compute price-elasticities and predict the e¤ects of a tari¤ change. The methodology can be applied to analyse demands of other goods with increasing tari¤s.

Generalized indirect inference for discrete choice models

“…The GII approach was first suggested in an unpublished manuscript by Keane and Smith (2003), but they did not derive the asymptotic properties of the estimator. Despite this, GII has proven to be popular in practice, and has already been applied in a number of papers, such as Gan and Gong (2007), Cassidy (2012), Altonji, Smith, and Vidangos (2013), Morten (2013), Ypma (2013), Lopez-Mayan (2014 and Lopez Garcia (2015). Given the growing popularity of the method, a careful analysis of its asymptotic properties is obviously needed.…”

Economic development and residential water consumption in Chile

“…Water demand studies using household level data are available for the United States and Europe, most focusing on the estimation of price and income elasticities, often under block pricing (e.g., Lopez-Mayan, 2014; Romano et al , 2016; Marzano et al , 2018). In developing countries, the literature is scarcer and typically uses cross-section data (e.g., Jiménez et al , 2017; Ojeda de la Cruz et al , 2017) – understandably, given typical data limitations, and the questions addressed are more to do with delivery and sanitation.…”