DIS Experimental data - Follow up through time. Case...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Experiment Hypothesis—needs to be verifiable/testable Variables Appropriate population Quantifiable data Experimental study: investigator active Observational: investigator does not play an active goal Exposure: a characteristic that a population has in common Outcomes: results—health/physical/psychological/birth effects (occurrence of illness) Treatment group vs control group Randomization—equal shot of being in either group. Eliminates bias. Controls frequently receive placebo. Also removes bias. Dose Response—splits treatment group into low, medium high exposure, to see how the intensity of exposure affects the outcome Ethical Issues: Starvation video—participants volunteered: ethical? Institutional Review Board approved. Respect for persons Informed consent Beneficence Equipoise—genuine uncertainty about the benefits or harm Justice—administered Association, Correlation, Causation Association Correlation Causation Observational Study Cohort-some people are exposed, some people are not.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Follow up through time. Case control studiesstarting with outcome (i.e. obesity), then find similar people who are not obese, then go back in time to see some similarities in the past Ecological Studiesecological fallacy. We can take population data, and apply to individual. Japanese people eat fish, low coronary heart disease. We cannot say, individuals should eat fish to reduce coronary heart disease Cross sectional studyexposure and outcome. Frequently surveys. 24 hr dietary recall Interview Not representative Expensive 72 hr food diary Person could lie Inaccurate Less prone to error than the FFQ Better to remember FFQ More prone to error Bias Interviewer bias-interviewee might not tell the truth because of the interviewer Selection bias- Information/misclassification: when someone is put in the wrong group Confounding Ecological Fallocy...
View Full Document

Page1 / 2

DIS Experimental data - Follow up through time. Case...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online