Multivariate analysis provides statistical methods for study of the joint relationships of variables in data that contain inter-correlations. At present even with the developed techniques, one of the main limiting factors for multivariate analysis operation is the lack of availability of data. The study aimed to develop Principal Component Analysis (PCA) using multivariate method for analysing inventory field data and their applications for sustainable forest management. The research was carried out in the two stands of Gmelina arborea and Tectona grandis plantation. Total enumeration was carried out and a total of 108 Gmelina arborea and 205 Tectona grandis species were measured. Parameters measured were diameter at breast height and Total height. DBH was measured at 1.3m above the ground level, using spiegelrelascope andmeasuring tape. The result revealed that Tectona grandis had a standard error for height parameter of 0.354 and diameter at breast height of 0.198 while Gmelina arborea had a standard error value for height of 0.248 and diameter at breast height of 0.045, the higher the standard error of the stands, the higher the susceptibility to error but the lower the standard error, the closer to perfection. This implies that diameter at breast height of Gmelina arborea had a low standard error of 0.045 which means there is lesser susceptibility to error. Height parameter of Tectona grandis and Gmelina arborea had a positive low correlation value of 0.027 and diameter at breast height parameter of Tectona grandis and Gmelina arborea had a low negative correlation value of -0.190, this indicates that there is a weak relationship between the two tree species. Conclusively Tectona grandis and Gmelina arborea are independent on each other for growth and survival.