T.3.6 - Population Growth Example

Census Data Section

Government Census poster

A simple model for population growth towards an asymptote is the logistic model


where \(y_{i}\) is the population size at time \(x_{i}\), \(\beta_{1}\) is the asymptote towards which the population grows, \(\beta_{2}\) reflects the size of the population at time x = 0 (relative to its asymptotic size), and \(\beta_{3}\) controls the growth rate of the population.

We fit this model to Census population data (US Census data) for the United States (in millions) ranging from 1790 through 1990 (see below).

year population
1790 3.929 
1800 5.308
1810 7.240
1820 9.638
1830 12.866
1840 17.069
1850 23.192
1860 31.443
1870 39.818
1880 50.156
1890 62.948
1900 75.995
1910 91.972
1920 105.711
1930 122.775
1940 131.669
1950 150.697
1960 179.323
1970 203.302
1980 226.542
1990 248.710

The data are graphed (see below) and the line represents the fit of the logistic population growth model.

plot of census data

To fit the logistic model to the U. S. Census data, we need starting values for the parameters. It is often important in nonlinear least squares estimation to choose reasonable starting values, which generally requires some insight into the structure of the model. We know that \(\beta_{1}\) represents asymptotic population. The data in the plot above show that in 1990 the U. S. population stood at about 250 million and did not appear to be close to an asymptote; so as not to extrapolate too far beyond the data, let us set the starting value of \(\beta_{1}\) to 350. It is convenient to scale time so that \(x_{1}=0\) in 1790, and so that the unit of time is 10 years.

Then substituting \(\beta_{1}=350\) and \(x=0\) into the model, using the value \(y_{1}=3.929\) from the data, and assuming that the error is 0, we have


Solving for \(\beta_{2}\) gives us a plausible start value for this parameter:

\beta_{2}&=\log\biggl(\frac{350}{3.929}-1\biggr)\approx 4.5.

Finally, returning to the data, at time x = 1 (i.e., at the second Census performed in 1800), the population was \(y_{2}=5.308\). Using this value, along with the previously determined start values for \(\beta_{1}\) and \(\beta_{2}\), and again setting the error to 0, we have


Solving for \(\beta_{3}\) we get

\beta_{3}&=\log\biggl(\dfrac{350}{5.308}-1\biggr)-4.5\approx -0.3.

So now we have starting values for the nonlinear least squares algorithm that we use. Below is the output from fitting the model in Minitab using Gauss-Netwon:

  • Select Stat > Regression > Nonlinear Regression
  • Select "population" for the Response
  • Type the following into the "Edit directly" box under Expectation Function: beta1/(1+exp(beta2+beta3*(year-1790)/10))
  • Click Parameters and type in the values specified above (350, 4.5, and –0.3)

As you can see, the starting values resulted in convergence with values not too far from our guess.


population = 389.166/(1+exp(3.99035 - 0.22662 * (year - 1790) / 10))

Parameter Estimates

Paraemeter Estimate SE Estimate
beta1 389.166 30.8120
beta2 3.990 0.0703
beta3 -0.227 0.0109

population = beta1/(1 + exp(beta2 + beta3 * (year - 1790) / 10))

Lack of Fit

There are no replicates.

Minitab cannot do the lack of fit test based on pure errror.


Iterations 8

Final SSE

DFE 18
MSE 19.8000
S 4.44972

Here is a plot of the residuals versus the year.

residuals of census data

As you can see, the logistic functional form that we chose did catch the gross characteristics of this data, but some of the nuances appear to not be as well characterized. Since there are indications of some cyclical behavior, a model incorporating correlated errors or, perhaps, trigonometric functions could be investigated.