Suggested answer to exercise: Checking student data, 4

Question 4: Try a tabulation of the first observation of the subject's sex against the second. You can do this using Descriptive Statistics, Crosstabs. What do you notice about the data? Why do you think it happened?

Suggested answer

We get the table by Descriptive Statistics, Crosstabs, then choose variable sex 1 for the row variable and sex 2 for the columns variable, OK.

We get the following output:

sex 1 * sex 2 Crosstabulation
sex 2
female male Total
sex 1 female 219 1 220
male 2 87 89
Total 221 88 309

Three students seem to have changed sex during the measurement exercise.

This is very unlikely. There are several possibilities:

  1. The observers were genuinely mistaken about the sex of the subject.
  2. The observers accidently misrecorded their observations.
  3. The observers were being mischevious.
  4. The data were entered wrongly into the computer.

We do not know which is the correct explanation, but I suspect explanation 4 to be correct.

The same thing happened every year that I ran this exercise. It shows that we cannot assume that data on a computer file are correct. Checking is essential.

Back to Exercise: Checking student data.

To Applied Biostatistics index.

To Martin Bland's M.Sc. index.

To Martin Bland's home page.

This page maintained by Martin Bland.
Last updated: 20 October, 2006.

Back to top.