Telephone surveys often have high rates of nonresponse. When the call is handled by an answering machine, perhaps leaving a message on the machine will encourage people to respond when they are called again. Here are data from a study in which(at random) a message was or was not left when an answering machine picked up the first call from a survey:

------------|Total households|Eventual contact| completed survey
No Message |------100------|--------58-------|--------33
Message----|------291------|-------200------|--------134

a.) Is there good evidence that leaving a message increases the proportion of households that are eventually contacted? Justify your answer.

b.) Is there good evidence that leaving a message increases the proportion who complete the survey? Justify your answer.

c.) If you find significant effects, look at their size. Do you think these effects are large enough to be important to survey takers?


Sorry for the terrible graph, I couldn't upload pictures for some reason. Anyways, I know the answer can't be that simple because we just finished significance and I was wondering how one would go about wording this. Thanks for the help.