Step 1.
Set up hypotheses and determine level of significance
Ho:
Ha: Should the alternative hypothesis be upper-tailed, lower-tailed, or two-tailed?
Step 2.
Select the appropriate test statistic
Insert Specific Formula (Consider sample size to determine Z-score or T-distribution)
Step 3.
Set up decision rule
Do NOT use your level of significance as a part of your decision rule. Be sure to use
only the critical values found in your appendices. Critical values are based upon the type
of test used, your sample size or degrees of freedom, your alternative hypothesis
(upper-tailed, lower-tailed, or two-tailed), and your level of significance.
When using a two-tailed test, be sure to include both positive and negative values of the
critical value.
Be sure to include the equal sign. For example, "Reject Ho if Zā„ 1.960."
Step 4.
Compute the test statistic.
Please show all computations. If you do not show your computations, you will not
receive credit, even if your test statistic is correct.
Step 5.
Conclusion
There should be two parts to your conclusion-1) Your decision to either reject or fail to
reject the null hypothesis; and 2) You conclusion. Please state both portions. If we reject
the null hypothesis for an upper-tailed test, we can simply say "Reject the null hypothesis
because XXX value is greater than YYY value..."
Your conclusion statement should also reflect the null and alternative hypotheses. For
example, "We have statistically significant evidence to indicate a difference in
PROBLEM IV. Approximately 26% of pregnant women deliver their child prior to the expected due
date. A clinical trial is undertaken to investigate the effectiveness of an experimental drug in reducing
pre-term delivery, compared to a drug which is the standard of care as well as a placebo. Pregnant women
are enrolled and randomly assigned to receive the experimental drug, the standard drug, or the placebo.
Women are follow through delivery and classified as delivering pre-term (<37 weeks) or not. The data
are shown below.
PRE-TER
DELIVERY STATUS
YES
NO
EXPERIMENTAL
DRUG
17
83
STANDARD DRUG
23
77
PLACEBO
35
65
Is the distribution of pre-term delivery approximately normal? Run the test at a 5% level of significance.
1. Set Up Hypothesis and Determine Level of Significance
2. Select the Appropriate Test Statistic
3. Set Up the Decision Rule
4. Compute the Test Statistic
5. Decision and Conclusion