Question 3: What could we do about the problems with head circumference?
If we inspect the cases with dubious low values for head circumference, there is no obvious explanation for any of the clearly incorrect values.
The safest thing to do is to make all the dubious head circumferences missing values. This is easy to do in SPSS. Simply put the cursor over the observation you do not trust and press the Delete key.
You will find this easier if you sort the data by head circumference first, so that all the dubious observations are at the start of the file. Sort is in the Data menu.
Back to Exercise: Checking student data.
To Applied Biostatistics index.
To Martin Bland's M.Sc. index.
This page maintained by Martin Bland.
Last updated: 23 January, 2012.