Regression model development
A regression model for all types of vehicle was developed as shown in Figures 3-7 and Table 4. Three types of model were developed: 1) model for all vehicles, 2) model for classified vehicles, and 3) model for all types of condominiums. These models were
evaluated using R-squared, t-statistic, and F-statistic. The predictive equation from the regression model is
Y = 0 + 1Xi + ei
where
Y = Trips produced by the condominium
construction project (veh./day)
0 = Constant
1 = Coefficient of Xi
Xi = Dwelling units (100 units)
ei = Random error
The R-squared of the regression is the fraction of the variation in the dependent variable that is accounted for (or predicted) by the independent variables. The
coefficient of determination R-squared ranges in value from 0 to 1. A value of R-squared equal to 1 shows a perfect correlation in the sample — there is no difference between the estimated y value and the actual y value. At the other extreme, if the coefficient of determination is 0, the regression equation is not helpful in predicting a y value. The t values indicate that each slope coefficient is useful in estimating the dependent variable. The F statistic is used to determine whether the observed relationship between the dependent and independent variables occurs by chance. The t values of most of the developed equations suggest that the coefficient is useful in estimating the trip rates for condominium construction projects. Except for the model of 4-wheeled trucks and passenger cars and low rise condominiums for Saturday and Sunday, the coefficient is not significant. Moreover, F statistics confirm the validity of the regression output. The model obtained very small significance for F. This means that there was only a very small chance that the regression output was merely
a random occurrence. The F statistics confirms that the model is not valid for 4-wheeled trucks and passenger cars for the Sunday model and low rise condominiums for the Saturday and Sunday models. For the significant model, the R-squared of the
model is more than 0.60 except for high rise condominiums on Sunday, for which it equals 0.54. The
R-squared suggests that the model has a moderate level
for prediction. However, for some models such as 6-and 10-wheeled trucks on Saturday, all vehicle types on
weekdays, and high rise condominiums, obtained high
R-squared (more than 0.75). This means that 75% of the
trips produced are influenced by dwelling units while
25% are explained by other factors.
Regression model developmentA regression model for all types of vehicle was developed as shown in Figures 3-7 and Table 4. Three types of model were developed: 1) model for all vehicles, 2) model for classified vehicles, and 3) model for all types of condominiums. These models wereevaluated using R-squared, t-statistic, and F-statistic. The predictive equation from the regression model isY = 0 + 1Xi + eiwhereY = Trips produced by the condominiumconstruction project (veh./day)0 = Constant1 = Coefficient of XiXi = Dwelling units (100 units)ei = Random errorThe R-squared of the regression is the fraction of the variation in the dependent variable that is accounted for (or predicted) by the independent variables. Thecoefficient of determination R-squared ranges in value from 0 to 1. A value of R-squared equal to 1 shows a perfect correlation in the sample — there is no difference between the estimated y value and the actual y value. At the other extreme, if the coefficient of determination is 0, the regression equation is not helpful in predicting a y value. The t values indicate that each slope coefficient is useful in estimating the dependent variable. The F statistic is used to determine whether the observed relationship between the dependent and independent variables occurs by chance. The t values of most of the developed equations suggest that the coefficient is useful in estimating the trip rates for condominium construction projects. Except for the model of 4-wheeled trucks and passenger cars and low rise condominiums for Saturday and Sunday, the coefficient is not significant. Moreover, F statistics confirm the validity of the regression output. The model obtained very small significance for F. This means that there was only a very small chance that the regression output was merelya random occurrence. The F statistics confirms that the model is not valid for 4-wheeled trucks and passenger cars for the Sunday model and low rise condominiums for the Saturday and Sunday models. For the significant model, the R-squared of themodel is more than 0.60 except for high rise condominiums on Sunday, for which it equals 0.54. TheR squared แสดงให้เห็นว่า แบบจำลองที่มีในระดับปานกลางสำหรับการคาดเดา อย่างไรก็ตาม สำหรับบางรุ่นเช่นล้อ 6 และ 10 รถบรรทุกเสาร์ ชนิดของยานพาหนะทั้งหมดในวันธรรมดา และคอนโดมิเนียมที่เพิ่มสูงขึ้น สูงได้R squared (มากกว่า 0.75) ซึ่งหมายความ ว่า 75% ของการเดินผลิตได้รับอิทธิพลจากหน่วยที่อยู่อาศัยในขณะ25% ได้รับการอธิบายจากปัจจัยอื่น
การแปล กรุณารอสักครู่..