Computer lab for March 13
Topic: Multiple regression model
In today’s class, you will learn about the multiple regression model and how to
interpret the coefficients. You need to know how to get variance and covariance
matrix for the estimated coefficients, You also need to know how to test hypotheses
about single coefficients in a multiple regression model.
5.8
The regression model:
etrendqualquantprice ***
4321
a) What signs would you expect on the coefficients
2
,
3
and
4
b) Estimate the equation and interpret the coefficients. Did the sign turn out as
you expected?
regress price quant qual trend
c) What proportion of variation in cocaine price is explained jointly by variation
in quantity, quality and time?
It is just R2, you can get it after you run the regression
d) Test the null hypothesis that the greater the number of sales, the lower the
price.
0:1
0:0
2
2
H
H
scalar t2=(_b[quant]-0)/_se[quant]
scalar tc=invttail(52,0.05)
scalar list t2 tc
If you do not like defining a scalar
You can use the following command
Display (_b[quant]-0)/_se[quant]
display invttail(52,0.05)
e) Test the following hypothesis:
0:1
0:0
3
3
H
H
scalar t3=(_b[qual]-0)/_se[qual]
scalar tc=invttail(52,0.05)
scalar list t3 tc
If you do not like defining a scalar
You can use the following command
Display (_b[qual]-0)/_se[qual]
display invttail(52,0.05)
f) What is the average annual change in the cocaine price? Can you suggest why
price might be changing in this direction?
5.9
The model:
