Question 1
True or False.
In situations where two competing models have essentially the same predictive power (as determined by an
F-test), it is standard procedure to use the model with the greater number of parameters.
◦ True
◦ False
Question 2
Operations managers often use work sampling to estimate how much time workers spend on each operation. Work sampling—which involves observing workers at random points in time—was applied to the staff of the catalog sales department of a clothing manufacturer. The department applied regression to the following data collected for 40 consecutive working days:
TIME:
y = Time spent (in hours) taking telephone orders during the day
ORDERS:
x1 = Number of telephone orders received during the day
WEEK:
x2 = 1 weekday, 0 if Saturday or Sunday
Consider the following 2 models:
Model 1:
E(y) =
β0 +
β1x1 +
β2(x
1)
2 +
β3x2 +
β4x1x2 +
β5(
x1)
2x2Model 2:
E(y) =
β0 +
β1x1 +
β3x2
What strategy should you employ to decide which of the two models, the higher-order model or the simple linear model, is better?
◦ Compare the two models with a nested model F-test, i.e., test the null hypothesis,
H0:
β2 =
β4 =
β5 = 0.
◦ Compare
R2 values; the model with the larger
R2 will always be the better model.
◦ Always choose the more parsimonious of the two models, i.e., the model with the fewest number of
β-coefficients.
◦ Compare the two models with a t-test, i.e., test the null hypothesis,
H0:
β1 = 0.
Median Annual Earnings of Full-Time Workers, by Gender, 1960–2010
Success, You Rock, Achievement, The way we work
The microchip is transforming our lives—the way we shop, spend our leisure, relate to one another, ...
Magnitude of Geologic Time
Time spent on, paid work and housework, by living arrangements of Canadian
home work question