1. Basic Statistics: The Three Things You Need to Know In Order to Complete Your Project

2. Edward P. Sloan, MD, MPH Associate Professor Dept of Emergency Medicine University of Illinois College of Medicine Chicago, IL

3. Attending Physician Emergency Medicine University of Illinois Hospital Our Lady of the Resurrection Medical Center

4. Overview Global Objectives Answer clinical questions Learn minimal statistics Get it done

5. Overview Session Objectives Know what question to ask Review stats needed to answer question Collect data for stat analysis

6. Three Things to Know What measurement? What question? How to report your results

7. Other Things to Know What data is needed? Basic statistical tests Nothing else

8. Two Measurements Proportion Mean

9. Two Questions What is the number? Do two groups differ?

10. Proportion Measurement What % of patients had some outcome? Divides a group into subgroups

11. Mean Measurement Describes a characteristic of a patient group Provides an overview

12. What is the Number? Describes one group Tells a story No comparisons

13. What #? Confidence Interval Can we believe the results? Was the process acceptable? Are the results reproducible?

14. Confidence Interval 95% CI Provides a range The “real” number is in this range

15. Do Two Groups Differ? Compares two groups Attempts to detect differences Relates outcomes to different interventions

16. Groups Differ? Hypothesis Test Null hypothesis, H o Alternate hypothesis, H A Are the groups the same (H o ) or different (H A )?

17. Hypothesis Test We reject H o The groups aren’t the same We then accept that they differ

18. Using Statistics 1)Pick your number type (Proportion or mean) 2)Decide what you will do (Describe or compare) (CI or hypothesis test) 3)Do the stat analysis 4)Report the results

19. Reporting Proportions 95% Confidence Interval In patients with T-wave inversion on their ED EKG, 29 (+ 3)% will develop an AMI during hospitalization (95% CI 26-32%).

20. Reporting Proportions: Hypothesis Test There was a two-fold greater 5 year survival rate in drug A patients vs. drug B patients (30% vs. 15%, p<.001)

21. Reporting Means: 95% Confidence Interval The mean CPK-MB in ED T-wave inversion AMI patients was 12 + 6 (95% CI=9-15).

22. Reporting Means: Hypothesis Test Drug A patients had a 50% greater survival time than that of drug B patients (1.5 + 0.7 years vs. 1.0 + 0.5 years, p<.001).

23. Statistics: Proportions Chi-square Fisher’s Exact test

24. Statistics: Means Students’s t-test ANOVA

25. Key Concepts: Design Know your number Know what question you’ll do Know how you will report results

26. Key Concepts: Data Collection Data to describe groups Data to compare groups Data to provide results Data to study confounding

27. Key Concepts: Data Analysis Simple data elements Ability to do 2x2 analysis Ability to do simple regression

28. Key Concepts: Reporting Consistent statements Straightforward p-value is less important

29. Statistics: Reporting Results Differences in outcome Absolute vs. Relative Mortality 25% to 20% –5% absolute decrease –20% relative decrease

30. Statistics: Reporting Results Odds ratios Relative risk Regression analysis What variables predict outcome?

31. Example: 2x2 Analysis Risk variable Outcome measure OR, 95% CI p-value Conclusion

32. Conclusions Know baseline proportions/means Project your results Know what data is needed Collect the data Analyze via 2x2 tables

33. Recommendations Keep it simple Follow our directions completely