StatLecture.pptVIP

Stat 512 – Lecture 12 Two sample comparisons (Ch. 7) Experiments revisited Announcements No HW this week! PP 10 due Thursday, preview next example Readings (no starred sections) Final Exam schedule Thank you for feedback Midterms returned at end of class Grades updated on blackboard Exam solutions online Probably a sub on Thursday What’s left to do? Practice the concepts p-value, confidence scope of conclusions New techniques for new situations Minitab number crunching Type and number of variables Keep thinking about whether a technique will apply to your project Example 1: Newspaper Credibility Nationwide sample of 1,002 adults interviewed via telephone (under direction of Princeton Survey Research Assoc), 2002 Comparison to 1998 nationwide sample Variable of interest: Would you rate your local daily newspaper as largely believable? Can consider 1998 vs. 2002 as second variable Example 1: Newspaper Credibility Two-way table Segmented bar graph Example 1: Newspaper Credibility Want to compare a categorical variable (believability rating) between two populations Let p1-p2 = difference in population proportion who rate daily paper as largely believable H0: p1-p2 = 0 (no change in proportion) Ha: p1-p2 0 (more believable in 1998 Assume H0 is true, could these sample proportions be coming from the same population proportion? Example 1: Newspaper Credibility Estimate: difference in sample proportions Observed: .670 - .634 = .036 Could a difference this large happen by chance? If we repeatedly took two samples from the same population, how often would we observe a difference in the sample proportions at least this large? Sampling Distribution of Mean: p1-p2 Standard deviation Variances add… When null hypothesis is true: Sampling Distribution of Shape? Normal if sample size is large… At least 5 successes and 5 failures in each group Example 1: Newspaper Credibility Example 1: Newspaper Credibility Summary The difference in the proportions is statistically signif