Exploration of the Stamps Data

by Asli Ersoz

The data set used in this investigation is based on the first class letter postage for the US Mail from 1933 to 2002. The problem is to plot the data and develop a prediction function. Then using the prediction function, I answer the following questions:

When will the cost of a first class postage stamp reach \$1.00?

When will the cost be 64 cents?

How soon should we expect the next 3 cent increase?

The data is given as below:

Using Excel I can plot the data and have the following graph:

Looking at this graph, I decided to use an exponential model to develop a prediction function. The graph of the exponential function looks like this:

Using the exponential function developed above, stamp prices for the following years are predicted:

Year Price

According to this data,

The cost of stamps will be 64 cents in 2019.

The cost of stamps will be \$1.00 i.e. 100 cents in 2030.

It seems difficult to answer the question of when the next 3 cent increase will be because in our given data stamps are already 37 cents in 2002, however the exponential function shows that stamps will be 37 cents in 2005. Actually, this also leads to questioning how good this model is.

I also tried the power model. The corresponding graph looks like this:

According to the power function, stamp prices are predicted as the following:

Year Price

According to this data,

The cost of stamps will be 64 cents in 2017.

The cost of stamps will be \$1.00 i.e. 100 cents in 2029.

The cost of stamps according to this model is 37 cents in 2003 which is closer to our given data.

We can also develop some other models omitting some of the data or using other types of functions. Choosing the best fit depends on different criteria.