* Long-Run Marginal Propencity to Consume
*
* Keywords:
* regression, ols, log, consumption function, distributed lag, F-test, MPC,
* marginal propencity to consume, long-run
*
* Description:
* We illustrate how to estimate a Distributed Lag OLS Model for Comsumption
* Function and test the hypothesis on the long-run Marginal Propencity to
* Consume
*
* Author(s):
* Noel Roy
* Skif Pankov
*
* Source:
* William H. Greene, Econometric Analysis - 7th Edition
* Pearson International Edition, Chapter 5, Example 5.6 (page 172)
*
* Setting the first time period to be equal to year 1950 with periodicity of
* one quarter
time 1950.1 4
sample 1950.1 2000.4
* Reading the datafile and naming the variables, specifying to ignore the
* first line of the file
read (TableF5-2.shd) year qtr realgdp realcons realinvs realgovt realdpi / skiplines=1
* drop beginning observation to obtained lagged consumption.
genr lnc=log(realcons)
genr lny=log(realdpi)
sample 1950.2 2000.4
genr lnclag=lag(lnc)
ols lnc lny lnclag /pcov
* a test command of the null hypothesis that the long-run mpc
* is unity, also gives us the value and standard error of the
* long-run mpc.
test lny/(1-lnclag)=1
* we can also use a linear test.
test lny+lnclag=1
* repeat the exercise for the final 11 years.
sample 1990.1 2000.4
ols lnc lny lnclag
test lny/(1-lnclag)=1
test lny+lnclag=1
stop