Question

Recall again that Rind & Bordia (1996) investigated whether or not drawing a happy face
on customers’ checks increased the amount of tips received by a waitress at an upscale
restaurant on a university campus. During the lunch hour a waitress drew a happy,
smiling face on the checks of a random half of her customers. The remaining half of the
customers received a check with no drawing (18 points).
The tip percentages for the control group (no happy face) are as follows:
45% 39% 36% 34% 34% 33% 31% 31% 30% 30% 28%
28% 28% 27% 27% 25% 23% 22% 21% 21% 20% 18%
8%
The tip percentages for the experimental group (happy face) are as follows:
72% 65% 47% 44% 41% 40% 34% 33% 33% 30% 29%
28% 27% 27% 25% 24% 24% 23% 22% 21% 21% 17%

This time, you are to perform a “hypothesis test” using the tip data, answering each of
the questions below. For short-answer questions, be brief. However, you must give
enough detail to justify your answers. Single-sentence responses will generally not
suffice, but do not exceed a paragraph for any given answer.

e. Staying with convention, you will perform your hypothesis test using an
alpha level of .05 (5%). Suppose you had to explain this significance criterion
to someone who has little experience with statistics. Explain how alpha is
used to make a decision (reject or retain) regarding the null hypothesis.

Answer 1

e) Hypothesis is an assumption which we will make based upon the data we have.

Null Hypothesis H₀ (Always equals something) and Alternative Hypothesis H_1.

To test the significance of hypothesis test, we consider the level of significance which is denoted with alpha (0.05). We calculate the test statistic 't', if the the hypothesis test is two sided ( Alternative Hypothesis is two sided) we compare the critical value with calculated test statistic.

if | tcalculated | is greater that critical value we reject null hypothesis and vice versa. Rejecting null hypothesis means statistically we conclude that the assumption in H₀ is wrong.