ESTIMATION OF PROBABILITY MODELS FROM INCOME CLASS DATA

Abstract. Many household surveys report income by a limited number of classes only. In Engel curve analyses of such data, income is usually equated to the class midpoint. We argue that it is better to specify a continuous income distribution over the entire range, and to estimate its parameters jointly with the Engel curve coefficients; the position of the dependent variable within income classes is sufficiently informative about the income distribution parameters. The method is illustrated for a simple logit model of automobile ownership. The effect on estimation is perceptible, but not impressive; further analysis suggests that the standard method is acceptable provided some care is taken over the income class limits at the lower end of the range.     

INTRAHOUSEHOLD INEQUALITY AT DIFFERENT WELFARE LEVELS: ENERGY INTAKE AND ENERGY EXPENDITURE DATA FROM THE PHILIPPINES*

ABSTRACTS This paper investigates the relationship between intrahousehold inequality and levels of household welfare. Under certain conditions it is demonstrated — with both the unitary model of the household and with some collective models — that the relationship between household welfare and inequality within the household can have an inverted u-shape. Using two sets of calorie adequacy data from a sample of 455 households in the Philippines, a spline analysis is used to test the hypothesis that inequality within the household first increases and then decreases as per capita household total expenditure increases. The two sets of calorie adequacy data are based on repeated 24- hour recalls of dietary intake, and on calorie requirements that are unadjusted and then adjusted for individual activity patterns. Results indicate that once activity patterns are accounted for, calorie intake shortfalls are borne fairly equally within the household at all per capita household total expenditure levels.     

WHAT FACTORS AFFECT A STATE'S MANUFACTURING EMPLOYMENT? EVIDENCE FROM 1974–1994 STATE PANEL DATA

This paper provides new evidence that US state policies can affect the location of manufacturing activity. The paper extends the literature by analyzing industry-level panel data from 1974–1994. Results from the two-stage empirical model support ex ante intuition that divergence in state policy and/or characteristics affects specific manufacturing industries differently. Econometric techniques employed herein address many of the criticisms of previous work in this area.     

PATENTS,R&D,AND TECHNOLOGICAL SPILLOVERS AT THE FIRM LEVEL: SOME EVIDENCE FROM ECONOMETRIC COUNT MODELS FOR PANEL DATA

This paper analyses the relationship between the main determinants of technological activity and patent applications. To this end, an original panel of 181 international manufacturing firms investing substantial amounts in R&D during the late 1980s has been constructed. The number of patent applications by firms is explained by current and lagged levels of R&D expenditures and technological spillovers. Technological and geographical opportunities are also taken into account as additional determinants. In order to examine this relationship, several econometric models for count panel data are estimated. These models deal with the discrete nature of patents and firm specific unobservables arising from the panel data context. The main findings of the paper are first, a high sensitivity of results to the specification of patent distribution. Second, the estimates of the preferred GMM panel data method suggest decreasing returns to scale in technological activity and finally a positive impact of technological spillovers on firm's own innovation. © 1997 John Wiley & Sons, Ltd.