Composite circular steel tubes- with and without epoxy infill for three different grades of concrete are tested for ultimate load capacity and axial shortening , under axial monotonic loading for compression. Steel tubes are compared for different lengths, cross sections and thickness. Specimens were tested separately after adopting Taguchi’s L9 (Latin Squares) Orthogonal array in order to save the initial experimental cost on number of specimens and experimental duration. DOE (Design of Experiment) approach was adopted. Results were generated using Taguchi’s method-a new technique to get mean effects plot. Analysis was carried out using ANOVA (Analysis of Variance) technique with the assistance of Mini Tab v15- a statistical soft tool. Results were verified after conducting preliminary nine combination experiments as per L9 orthogonal array and linear regression models were developed. Comparison for predicted and experimental output is obtained from linear regression plots. To know the implications of different factors on circular composite columns with and without epoxy, surface contours were also generated. From this research study it is concluded that ,Regression models which were developed with minimum number of experiments based on Taguchi’s method predicted the axial load carrying capacity very well and reasonably well for at ultimate point. Cross sectional area of steel tube has most significant effect on ultimate load carrying capacity. Also it is observed that, as length of steel tube increased- load carrying capacity decreased.