Multivariate statistical techniques such as factor analysis (FA), cluster analysis (CA) and discriminant analysis (DA), were applied for the evaluation of spatial variations and the interpretation of a large complex water quality data set of three cities (Lahore, Gujranwala and Sialkot) in Punjab, Pakistan. 16 parameters of water samples collected from nine different sampling stations of each city were determined. Factor analysis indicates five factors, which explained 74% of the total variance in water quality data set. Five factors are salinization, alkalinity, temperature, domestic waste and chloride, which explained 31.1%, 14.3%, 10.6%, 10.0% and 8.0% of the total variance respectively. Hierarchical cluster analysis grouped nine sampling stations of each city into three clusters, i.e., relatively less polluted (LP), and moderately polluted (MP) and highly polluted (HP) sites, based on the similarity of water quality characteristics. Discriminant analysis (DA) identified ten significant parameters (Calcium (Ca), Ammonia, Sulphate, Sodium (Na), electrical conductivity (EC), chloride, temperature (Temp), total hardness(TH), Turbidity), which discriminate the groundwater quality of three cities, with close to 100.0% correct assignment for spatial variations. This study illustrates the benefit of multivariate statistical techniques for interpreting complex data sets in the analysis of spatial variations in water quality, and to plan for future studies.