Factor analysis as a tool in community diagnosis

For the family physician, community diagnosis can be likenedto individual diagnosis by the application of methods of informationacquisition and analysis. This paper describes the techniqueof factor analysis, applied to data from an urban inner-cityarea, for reducing a multitude of factors to a manageable numberwithout an appreciable loss of information. The variables wereselected from four broad categories which have been shown toinfluence both health states and health care needs: demography,socioeconomics, social disorganization and morbidity/mortality.A correlation matrix based on 40 of the most accessible indicesserved as input for a principal axes factor analysis. Six factors acounted for 74% of the total variance and wereinterpreted as: ‘Poverty and social disorgan ization’,‘Distribution and problems of the elderly’, ‘Ethniccomposition’, ‘Fertility’, ‘Infant mortality’and ‘Foetal mortality’. Representative indices fromeach factor were then mapped to identify and display censustract differences. Finally, the application of the factors toa specific community illustrated important differences withinthe community and identified areas of high risk and need.