* Logistic Regression for US Population Growth
*
* Keywords:
* regression, nonlinear, logistic, linear, graph, us, population, growth
*
* Description:
* We illustrate how to estimate Logistic and Linear Models for US
* Population Growth and produce a Graph
*
* Author(s):
* Skif Pankov
*
* Source:
* Damodar N. Gujarati and Dawn C. Porter, Basic Econometrics - 5th Edition
* McGraw-Hill International Edition, Chapter 14, Example 14.3 (page 532)
*
sample 1 38
* Reading the datafile and naming variables
read (data_14.3.shd) t y
* Initiating nonlinear regression procedure, stating that 1 equation with
* 3 coefficients
nl 1 / ncoef = 3
* Writing up an equation we would like to estimate - coefficients are named
* A, B and C
eq y = A / (1+exp(B + C*t))
* Stating the initial values of coefficients - these shall be used as the starting
* points in the process of iterative estimation
coef A 1 B 1 C 1
end
* Generating a log of population size y
genr lny = log(y)
* Plotting lny against time
graph lny t
* Running an OLS regression of lny on t, as suggested by the graph
ols lny t / rstat
stop