Lecture 06 - Ecologic and Cross Sectional Studies • Steps to conduct ecologic or cross-sectional studies • Key design features • Strengths

Info iconThis preview shows pages 1–11. Sign up to view the full content.

View Full Document Right Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

View Full DocumentRight Arrow Icon

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

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

Unformatted text preview: Ecologic and Cross Sectional Studies • Steps to conduct ecologic or cross-sectional studies • Key design features • Strengths and weaknesses • Analysis and interpretation Lecture 6 - Analytical Ecologic and Cross Sectional Studies Roadmap for the Next Components Been there, done that… Scope of epidemiology • Basic concepts • Measures • Introduction to study design • Interpretation (bias & causation) Emphasis on concepts & some interpretation Study designs • Ecological & cross sectional • Case control • Cohort studies • Experiments Emphasis on interpretation & application Where to from here… Accuracy in Epidemiologic Studies Revisited Accuracy has two major components Random error Precision • Variability due to chance • Measurement or sampling error Systematic error Validity • Non-random flaws in design • Increase or decrease estimates Sources of Bias (Systematic error or deviation from the truth) • Selection bias (specific to cross- sectional studies) – Prevalence-incidence bias – Response/Volunteer bias • Information (Misclassification Bias) – Differential (uneven distribution of error) – Non-differential (error evenly distributed) • Confounding – Alternate factors that could explain the effect Controlling bias is a balancing act Descriptive vs Analytic Designs The Nature of a Descriptive Study • Describe patterns of exposure or outcome by person, place, or time • Used for hypothesis development rather than hypothesis testing 5 10 15 20 25 1 9 5 1 9 6 1 9 7 1 9 8 1 9 9 Males Female Suicide Rates Analytic Designs • Test pre-determined hypotheses • Assess or provide preliminary information on an exposure-outcome association • Identify potential confounders and effect modifiers Outcome Exposure Confounders/ Effect Modifiers Definition of a Hypothesis • A hypothesis is…. – A supposition, arrived at from observation or reflection, that leads to refutable predictions. – Any conjecture cast in a form that will allow it to be tested and refuted. H o : No difference between groups H a : Groups are different-Calculate test statistic (i.e. chi-square, t-test, etc.) and determine probability of observing a difference as large or larger in data, given the null hypothesis is true (p-value)-Reject (refute) null hypothesis (Ho) if p-value ≤ pre-selected alpha (significance) level (i.e. 0.05) Definition of a Hypothesis A useful hypothesis…. – Makes more precise predictions – Explains more of the previous observations – Explains observations in more detail – Passes tests that other hypotheses have failed (not refuted) – Suggests new tests (makes new predictions) – Unifies or connects phenomena not previously considered related and links things within explanatory theories Analytic Ecologic & Cross-Sectional Studies Designed to test a pre-determined hypothesis about an exposure-disease relationship Units of Analysis Individual Level Data • Exposure & outcome can be linked to an individual...
View Full Document

This note was uploaded on 02/23/2012 for the course EPID 301 taught by Professor Richardson&aronson during the Spring '09 term at Queens University.

Page1 / 79

Lecture 06 - Ecologic and Cross Sectional Studies • Steps to conduct ecologic or cross-sectional studies • Key design features • Strengths

This preview shows document pages 1 - 11. Sign up to view the full document.

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