Lecture 14: Research study design and eval 2

• Define descriptive epidemiology:


  -used when little is known about the disease-rely on preexisting data-who, where, when-illustrates potential associations
• Define analytic epidemiology:


  -used when insight about various aspects of disease is available-rely on development of new data-why-evaluated the causality of associations
• What is a hypothesis


  -an educated guess-an unproven idea-based on observation or reasoning, that can be proven or disproven through investigation
• Usually expressed as the 'null hypothesis"


  you usually being by assuming there is no association between exposure and outcome (even if you feel there is)
• Examples of null hypotheses:

  1. there is no association between living in the phoenix area and the incidence of coccidioidomycosis in dogs 2. there is no difference in prevalence of internal parasites in pet dogs compared with those in shelters/pounds
• What is the purpose of an analytic study

  to test the null hypothesis and either reject or find it acceptable
• What are the major types of analytic studies

  -observational-interventional
• Observational (no intentional control of exposure)


  -ecological studies-cohort studies-case-control studies
• Interventional (exposure are controlled/known)


  -clinical studies (random assignment to exposure groups)-community studies (non-random exposures)
• Define ecological studies:


  a study in which the units of analysis are populations or groups of people rather than individuals
• What are the advantages of ecologic studies?


  -may provide information about the contributor to health-can be performed when individual-level measurements are not available-can be conducted rapidly and with minimal resources-relatively low cost
• What are the disadvantages of ecological studies?


  -imprecise measurement of exposure-usually hypothesis generating-temporal ambiguity-confounding-ecological fallacy
• Define ecological fallacy


  associations observed at the group level do not necessarily hold true at the individual level
• Define cohort studies


  a cohort is defined as a population/group that shares a particular exposure and is followed over time to observe changes in outcome
• What are the two types of cohort studies


  -prospective cohort study-retrospective cohort study
• Define prospective cohort study


  subjects are followed into the future to document the occurrence of new cases
• Define retrospective cohort study

  makes use of historical data to determine exposure level after some baseline in the past
• Define framingham Heart Study


  a large epidemiologic study begun in the 1940s designed to assess the relationship between lifestyle factors and risk for heart disease
• What are the advantages of prospective

  -many exposures can be assessed-useful if hypothesis is vague-exposures are well defined
• What are the disadvantages to prospective


  -not useful for rare outcomes-may take a very long time-subjects may bet lost to the study
• What are the advantages of retrospective


  -takes less time than prospective-much less expensive-addresses rarer outcomes
• What are the disadvantages of retrospective


  -bias can be significant-requires extensive histories-temporality may be unclear
• Define case control studies


  subjects are defined on the basis of the presence or absence of an outcome of interest
• What are the advantages to case control studies


  -can be used to study rare conditions-relatively quick and easy to complete-usually inexpensive-involve smaller number of subjects
• What are the disadvantages to case control studies


  -measure of exposure maybe inaccurate-representativeness of cases and controls may be unknown-provide indirect estimates of risk-the temporal relationship between exposure factor and outcome cannot always ne ascertained-prone to bias
• Define intervention studies


  -the investigator intentionally changes some for of exposure between several groups to determine differences in outcome
• Types of intervention studies


  -clinical study/trial-randomized-community study/trial- non-randomized
• Define randomized clinical trial


  subjects are recruited from a population and randomly allocated into groups, usually called study and control groups
• The differences in outcome between the groups determines what?

  the effectiveness of the intervention
• Define variations of clinical trials


  -sometimes after the study progresses the groups are switched (this is termed cross-over clinical trial)-blinding can reduce various types of bias
• What are the types of binding

  Single blinded and double blinded
• Define single blinded


  subjects do not know which group they are in
• Define double blinded


  neither the subjects nor the investigators know which groups the subjects are in
• Define community trial


  intervention designed for the usual purpose of educational and behavioral changes at the population level
• Relative risk (sometimes referred to as the "risk ratio")


  -used when comparing outcomes of those who were exposed to something to those who were not exposed-calculated in cohort studies and randomized clinical trials-cannot be calculated in case-control studies because the entire population at risk is not included or represented in the study
• Define odds ratio


  -used most commonly in case control studies-odds of exposure among cases divided by odds of exposure among controls-provides a rough estimate of the relative risk
• What is the analysis tool for both RR and OR

  2x2 table
• Define relative risk


  a measure of the strength of association based of cohort studies and randomized clinical trials
• Relative risk=


  [a /(a+b)] / [c /(c+d)]
• Define odds ratio meaning


  a measure of the strength of association between exposures and outcomes in case control studies