This document discusses key concepts in scientific studies and data analysis. It explains study variables, descriptive and inferential statistics, statistical significance, and different types of study designs including observational studies. Specific topics covered include error bars, regression, p-values, strengths and weaknesses of epidemiological data, risk analysis in epidemiology, case-control studies, cohort studies, and an example of the Framingham Heart Study.
16. Statistical Significance
• When observed p-value less than
the significance level defined for the study
• Always possible that an observed effect would
have occurred due to sampling error alone
• If p-value less than the significance level,
reflects characteristics of whole population
• Does not imply research, theoretical, or
practical significance
22. Challenges
• What are the actives and how much is present?
• Dose – not directly administered
• Compliance –how to model a dose-response study
with complex pattern of use
• Relevant timing – disease etiology may require
temporal specificity (cancer)
• Outcome biased by consumer – are healthy people
more likely to use herbs?
24. Epidemiology: Risk Analysis
Condition:
Coronory Heart Disease
Total
Yes No
Exposure:
Periodontal
Disease
Yes 349 1437 1786
(A) (B) (A+B)
No 1706 6898 8604
(C) (D) (C+D)
Total 2055 8335 10390
(A+C) (B+D) (A+B+C+D)
Relative Risk = (A/A+B) / (C/C+D) = 0.98
Ratio of the incidence of disease in the exposed
group relative to unexposed group
DeStefano et al. (1993) Br Med J 306: 688-691