Surveys collecting data on consumer attitudes and buying intentions have been performed in Sweden since 1973. This paper examines the usefulness of these data as quick indicators of the development of household expenditures on automobiles. In the evaluation we are considering the explanatory power as well as the prediction accuracy. It turns out that the best single indicator is among the plan indices. However, an indicator based on car registration statistics is found to be at least as good. By combining plan/attitude indices with car registrations our study shows that considerable improvements can be obtained.
KEY WORDS Consumer attitudes Buying plans Forecasting
Car expenditures Household survey data Time-series data
The consumption expenditures of Swedish households on cars constitute a relatively small part of total consumption expenditures (3%). However, this is the largest single component of consumer expenditures on durables, on average 35% in the period 1963-1990, and its great variability (ranging from 25% to 50%) makes it a strategic component to forecast. There are many studies of household demand for cars trying to formulate causal models which then have been used for producing forecasts, the major approach being based on the stock adjustment model. (For a recent survey of some approaches see de Pelsmacker, 1990.) In the case of short-term forecasting some alternative approaches have been presented. One is based on survey data collected from households concerning their buying plans of durables and their attitudes towards the general and private economic conditions. Considering the fact that car expenditures are of a discretionary character, household attitudes and plans can be regarded as a measure of willingness to buy (Katona and Mueller, 1952). The emphasis of this approach is on the predictive ability of models where macroeconomic variables and attitudes/plans are taken together or models where only attitude/plan variables are included (for a brief survey see Agren, 1989). A great advantage of the latter type of models is that they are based on data which are easier to produce than national accounts data and hence also available without long delays.
The first more comprehensive study of the predictive ability of consumer attitudeslplans was