Editors:
Goodall, G.
Type:
Category:
Volume:
26(1)
Pages:
22-23
Year:
2004
Publisher:
Teaching Statistics
Abstract:
The ?<sup>2</sup> goodness-of-fit test is often one of the first tests of hypotheses encountered by students. When some of the expected frequencies are small, classes need to be combined. A real-life example is given that illustrates a surprising sensitivity of the results of the test to the way in which such combinations are chosen.
The CAUSE Research Group is supported in part by a member initiative grant from the American Statistical Association’s Section on Statistics and Data Science Education