REGRESSION MODELS FOR MOTION SIMULATORS
Regression Model Analysis
The initial scatterplot for the number of motion simulators and the number of corresponding helicopters showed that linear, cubic and quadratic equations would describe the regression model with greater precision than the rest.
The SPSS “curve estimation” analysis for the linear equation gave the results shown on tables 2, 3, and 4.
The SPSS “curve estimation” analysis for the quadratic equation gave the results shown on tables 5, 6, and 7.
The SPSS “curve estimation” analysis for the quadratic equation gave the results shown on tables 8, 9, and 10.
All three models indicated that there is a strong correlation between the number of helicopters and the corresponding simulators (.863<R2<.898). Figure D2 presents the curve fit of the three equations. Although the cubic equation had the best fit (R2=.898), it was rejected because it suggested that, after a number of helicopters, the number of simulators used should be growing at a growing rate.Figure 9
This can not be true, since higher number of simulators give more flexibility and thus better utilization of the available resources.
Between the other two models the quadratic had a higher R square value. It also presented a better fit for very high number of helicopters and thus it was chosen as the regression model to predict the number of simulators. The equation of the model is Y=0+(.024*X)-(4.9*10-006*X2).