Robert Newcombe makes some powerful points which I agree with; among other
things he quoted the following passage:
>"In a study comparing those that did and did not agree to take part
>in a survey of infant feeding, 61 mothers declined to take part and
>473 responded. Data collected from the clinical records showed that
>23 of those who declined to take part were smokers compared to 123 of
>those who did respond."
and asks what the source of difficulty might have been for those readers who
were unable to convert it into a 2x2 table.
I wonder how many were, like me, diverted by contemplation of the
methodological problems suggested by the phrase "comparing those that did
and did not agree to take part in a survey", and only later [or never]
reached the task intended?
Julian Wells
OU Business School
The Open University
Walton Hall
Milton Keynes
MK7 6AA
United Kingdom
+44 1908 654658
|