5 Written questions
5 Matching questions
- Pretest Probability
- Dependent Variables
- Regression to the Mean
- Types of Prevention:
- Ecology of Medicine
- a "Patients selected because they represent an extreme value in a distribution can be expected, on average, to have less extreme values on subsequent measurements..This occurs for purely statistical reasons, not because the patients have necessarily improved." This is the reasoning behind repeating lab tests: "Subsequent values are likely to be more accurate estimates of the true value." p. 32
- b The prevalence of disease in a specified group of subjects.
- c variables describing a possible effect p. 5
- d Def: Early detection of existing disease to reduce severity and complications
Ex. Screening for cancer
- e (Dr. Wheat) author? journal?....i think...Kerr White New England Journal of Medicine, Nov. 2, 1961 "Ecology of Medical Care"
5 Multiple choice questions
- According to answers.com, a case control study is a usually retrospective study in which individuals with and without a condition are examined and past medical history etc. is statistically analyzed for correlation.
- The number of people needed to be treated to prevent one bad outcome
NNT = 1/ARR
- a process at any stage of inference tending to produce results that depart systematically from true values.
- Normal distribution curve. based in statistical theory, describes the frequency distribution of repeated measurements of the same physical object by the same measurement.
- Patient characteristics that may affect the results a study it is trying to measure. They can decrease the validity of a study.
5 True/False questions
Reliability → "the extent to which repeated measurements of a stable phenomenon by different people and instruments at different times and places get similar results" Other words for this are reproducability and precision. p. 20
Approximately how many people does smoking kill in the US every year? → 7,000
Case Fatality Rate → A general term for measures of association calculated from data in a 2x2 table. = Risk of disease in exposed (a/(a+b)) / Risk of disease in unexposed (c/(c+d))
Relative Risk → The probability of an event in a population under study. #new cases over a given period of time / # people in the group
Approximately how many people does smoking kill in AL every year? → 7,000