Price and Income Elasticities Estimated from BLS Consumer Expenditure Surveys and ACCRA Price Data

Price and Income Elasticities Estimated From BLS Consumer Expenditure Surveys and ACCRA Price Data Lester D. Taylor University of Arizona* This paper represents a low-key effort to estimate both price and income elasticities for several broad categories of expenditure from cross-sectional data sets that combine price information collected by ACCRA with the BLS Consumer Expenditure Surveys. Sixteen quarters of data for 1996 through 1999 are analyzed. Statistically strong, and for the most part sensible, price elasticities are obtained for six exhaustive categories of expenditure (food consumed at home, housing, utilities, transportation, health care, and miscellaneous expenditures) from both simple double-logarithmic demand functions and equations based upon an Almost Ideal Demand System. The results are clearly supportive of further research. * I am grateful to Sean McNamara of ACCRA for making EXCEL files of ACCRA surveys available to me and to the Cardon Chair Endowment in the Department of Agricultural and Resource Economics at the University of Arizona for financial support. Construction of data sets and econometric estimation have all been done in SAS. 1 The standard reference for the history of early empirical studies of consumer behavior using data from household budget surveys is Stigler (1954); see also Houthakker (1957). Important 20 century studies with a family budget focus include Allen and Bowley (1935), Shultz (1938), Prais and Houthakker (1955), Deaton and Muelbauer (1980), and Pollak and Wales (1992). 2 The reference here is to price elasticities estimated from conventional household budget surveys. Deaton (1990) provides an exception. In contrast, estimation of price elasticities for goods, such as telephone or utility services, in which the data used in estimation are collected from the records of vendors or from the actual bills of consumers are fairly commonplace. Cf., Price and Income Elasticities Estimated From BLS Consumer Expenditure Surveys and ACCRA Price Data Lester D. Taylor University of Arizona