.Understanding individuals responses to relative price changes is central to almost every area of applied economics and policy formation. Yet the reliable estimation of these remains a difficult problem for researchers and policy-makers, with a main difficulty being the choice of an empirical specification of demand relations which is consistent with the theory, the data and common sense. This research will develop and apply practical nonparamethc methods for analysing household-level demand data in terms of both market goods and observable product characteristics, based on revealed preference restrictions. There will be three main elements in the research agenda: i) the derivation of consumers demand responses to price changes without the need to write down and rely upon particular mathematical models for demand, ii) improving the practicality of existing tests designed to tell whether goods can be grouped together with others or whether they should be modelled separately iii) the development of tests and adaptations of the above procedures and theory such that demands can be modelled in terms of the characteristics embodied in goods and well as marketed goods themselves