Regression modeling analyses the relationship between two or more variables and can be used to predict the response variable from one or more independent variables. The present study uses linear regression analysis to evaluate the growth in the two fish species of genus Oreochromis, Nile tilapia and Jipe tilapia, under aquaculture conditions. The models were fitted using a collection of functions in the R-software library. The final models were selected using the goodness of fit criteria based on the coefficient of differentiation, the model p- values and Akaike information criteria. The significance of the linear relationship between predictor variables and the mean response was tested by comparing the computed standardized parameter estimates, whereas the confidence intervals were constructed to assess the uncertainty of predicting the response variable and determine outliers in the model. Generally, both species exhibited good condition during growth and all the measured water quality variables significantly afffected growth (p<0.05). However, only temperature and dissolved oxygen produced the most important linear relationship with fish weight. The study recommends that data from a controlled experiment should be used the determine the interactions between the two growth variables.