Asian Research Journal of Current Science

The objective of this research investigation is to present a novel scheme of Ensemble Linear Regression Based on Incorporation of the Linear Model Strength Contributed By Each Data Point Co-ordinate. An example of computation of Construction Accidents (Fatal Falls) Forecasts modeled according to the proposed fashion is presented to this end. Firstly, we compute the linear regression model for the given data points of concern and note its R squared value. The method involves calculation of linear regression model forecasts (for a specific independent variable co-ordinate of concern) of each co-ordinate of the parameter of concern by omitting the co-ordinate itself and modeling the rest of the co-ordinates that the parameter takes on, using Linear Regression. We also note their respective R squared values. We then ascribe the Linear Regression Model Strength coefficient to each independent variable co-ordinate as 1 minus the {(change in R squared value of each linear regression model obtained by omission of the considered independent variable co-ordinate with respect to the R squared value of the linear regression model obtained initially by using all the data point co-ordinates) divided by the R squared value of the linear regression model obtained initially by using all the data point co-ordinates}. We now product scale (using the Model Strength coefficient of each independent variable co-ordinate) the dependent variable co-ordinate obtained for each independent variable co-ordinate using the linear regression model generated by using all the data points. This gives us a new set of dependent variable co-ordinates for the given independent variable co-ordinates of concern for which we finally generate the General Linear Regression Model. We can also note that the R squared values of this thusly fashioned Ensemble Regression Model is higher than the rote General Linear Regression Model. In this study, the authors have used Adjusted R² values for this analysis.