Streszczenie
This article presents structural parameters of linear causal-descriptive models
estimated for 45 assortment groups. The computation was carried out separately for
subsequent years from 2006 to 2015 and was based on data from the Central Statistical
Office of Poland. The models were verified by assessing the fitting theoretical values to
empirical data and checking the significance of structural parameter associated with the
independent variable. As a result, food categories were determined for which linear
function is a good approximation describing the stochastic relationship between the
consumption per capita and the size of household as well as such food items for which
the relationship is nonlinear. The first group consists of 39 out of 45 assortment items,
and the second one includes only six items, namely: bread, flour, milk, potatoes,
beetroots and sugar.