The analysis by income strata showed that the variable "education" had a much smaller influence on the nutritional status than that showed on non-stratified models. Besides, education only was significant in intermediate strata. Also, one is led to believe that a multiple regression model is more appropriate to indicate the relations between socio-economic variables and nutritional status by considering the simultaneous effect of several variables. But caution should be taken in the analysis of the results in order to clearly spell out the limitations of a regression treatment.
Socioeconomic factors; Nutrition; Research