Eye strain for office workers
Use this page to show that the conditional probabilities are found by rescaling rows (or columns) of joint probabilities so each row (or column) has the same total (1.0). E.g.
Click the formulae for the conditional probabilities to do the stacking.
(The values are actually sample proportions rather than probabilities but the diagram illustrates the concept.)
The diagram is based on a real data set which classifies 295 office workers by their type of work and whether they have symptoms of eye strain.
Type of work | No eye strain | Eye strain |
---|---|---|
VDU data entry | 42 | 11 | General VDU use | 79 | 30 | Full-time typing | 64 | 14 | Standard clerical work | 52 | 3 |
The sample proportions are treated as joint probabilities in the diagram.