B.3 testing the hypothesis
Download as PPTX, PDF0 likes254 views
Hypothesis tests are conducted in four steps: 1) state the null and alternative hypotheses, 2) form an analysis plan to test the hypotheses using sample data, 3) analyze the sample data and calculate a test statistic, 4) interpret the results by comparing the p-value to the significance level to determine whether to reject or fail to reject the null hypothesis. The test statistic equation compares the sample statistic to the parameter value specified in the null hypothesis using either a z-score or t-score. The p-value represents the probability of observing results as extreme as the test statistic if the null hypothesis is true.
1 of 2
Download to read offline
More Related Content
What's hot (18)
Ad
Viewers also liked (14)
Ad
Similar to B.3 testing the hypothesis (20)
More from Ulster BOCES (20)
B.3 testing the hypothesis
- 2. Conducting Hypothesis Tests • All hypothesis tests are conducted the same way. (state hypothesis, form analysis plan, analyze sample data according to plan, interpret data and make a claim based on the results of the analysis) 1. State hypothesis: Ho &Ha, where Ho & Ha are mutually exclusive 2. Form analysis plan: describes how to use the sample data and whether to reject or not reject the null hypothesis 3. Analyze: calculate computation using sample data TEST STATISTIC: use following equation when null hypothesis involves mean or proportion TS= (Statistic- Parameter) OR TS= (Statistic – Parameter ) SD of Statistic SD of Statistic ** where parameter is a value specific to the null hypothesis and the statistic is the point estimate of parameter ** when the parameter in the null hypothesis involves qualitative data, use a chi-square statistic as Test Statistic (in future lesson) ** you can find the TS formula under inferential statistics in the formula sheet P-value: probability of observing a sample statistic as extreme as the test statistic, assuming the null hypothesis is true. 4. Interpret Results: compare P-value to significance level, reject the null hypothesis when the P- value is less than the significant level.