Consider the following two AM peak work trip generation models, estimated by hou

Question

Consider the following two AM peak work trip generation models, estimated by household linear regression: Where y are household trips to work in the morning peak, x_1, is the number of workers in the household, x_2, is the number of cars in the household, z_1, is a dummy variable which takes the value of 1 if the household has one car and z_2 is a dummy variable which takes the value of 1 if the household has two or more cars. (a) Choose one of the models explaining clearly the reason behind your decision. (b) Graphically depict both models using appropriate axis. (c) If a zone has 1000 households (with an average of two workers per household), of which 50% has no cars, 35% has only one car and the rest exactly two cars, estimate the total number of trips generated by the zone using both models. Discuss your results.

Explanation / Answer

Both the models, 1 and 2 have almost the same value for the R2 .

So, in this case, we choose the model with parsimonious variables or lesser number of variables as the model is able to explain the same amount of data with lesser number of variables.

Thus, I choose model 1.

Now,

for comparing the models we work out as follows:

y (for model 1)

y ( no car) = 0.50 + 2(0.50 * 2) = 2.50

y( 1 car) = 0.50 + 2(0.35*2) + 1.5(1) = 3.40

y(2 cars) = 0.50 + 2(0.15 * 2) + 1.5(2) = 4.10

y(model 2)

y( 0 cars) = 0.01 + 2.3 ( 0.5 * 2) = 2.31

y ( 1 car) = 0.01 + 2.3(0.35*2) + 1.1 = 2.72

y (2 cars) = 0.01 + 2.3 (0.15 *2) + 4.1 = 4.8

Hope this helps.

Note: I am unable to copy-paste the diagram for the model over here because of some unknown reason. However, you will definitely find some online graphing software to plot the models.

Related Questions

Navigate

• Browse (All)
• Browse C
• Subjects

---