click below
click below
Normal Size Small Size show me how
PHC 6000: Designs
Introduction to epidemiology: Study designs
Question | Answer |
---|---|
What kind of studies can be used to differentiate between environmental and genetic characteristics? | Migration studies |
In which types of studies, the unit of analyses are usually populations or groups rather than individuals? | Correlational studies ~ ecological studies |
What is ecological fallacy? | An error of deduction that involves deriving conclusions about individuals solely on the basis of an analysis of group data. |
What situation can occur when a researcher or analyst makes an inference about an individual based on aggregate data for a group? | Ecological fallacy |
What are cross-sectional studies also called? | Prevalence studies |
What is the hierarchy of study samples? | Target population > sampling population > sample |
What are the weaknesses of a cross-sectional study? | -No cause-effect -No temporality -Prevalent cases are survivors -Not suitable for rare or short duration diseases -Disease process may alter exposure |
What are the strengths of a cross-sectional study? | -Study multiple outcomes & exposures -Help assess health needs and planning -May generate new hypotheses -Short duration/low cost |
Aspirin is prescribed for heart disease. In an observational study, it may be incorrectly seen as a risk factor for heart disease. What is this an example of? | Disease process may alter exposure |
What is the outcome measure of cross-sectional studies? | Prevalence ratio |
What is the outcome measure of case-control studies? | Odds ratio |
What is the outcome measure of cohort studies? | Relative risk |
Why is the outcome measure of case-control studies not a measure of risk? | We already have the outcome at the outset of the study |
What are the strengths of a case-control study? | -Good for rare diseases -Can test many hypotheses with respect to one outcome -Requires short time when outcomes are delayed -Cheap |
What are the weaknesses of a case-control study? | -Subject to bias (selection, information) -Indirect estimate of the Relative Risk -Temporality not clear -Not good for rare exposures -Multiple outcomes cannot be studied -Reverse causation is a problem in interpretation -Ca/co selection troublesome |
What are the strengths of a cohort study? | -Can look at many outcomes with respect to one exposure -Measures risk -Suitable for rare exposures -Direct measurement of incident -Addresses temporality -Minimizes recall bias -Allows for calc of incidence of diseases in exposed and unexposed |
What are the weaknesses of a cohort study? | -Costly/time consuming -Not suitable for rare disease -Loss to follow-up -Can be very time consuming if latent period is long -Changes over time in diagnostic methods -Nonparticipation bias (selection bias) |
What are the 3 domains of person characteristics? | Demographic, socioeconomic, and behavioral |
What causes individual variation in disease occurrence? | Can be due to difference in exposure, susceptibility, or both |
What is the purpose of a case report? | Documents unusual medical occurrences that can represent the first clues in the identification of new diseases or adverse effects of exposures |
What are case series? | Collections of individual case reports |
What are correlational studies also called? | Ecological studies |
How are correlational studies used? | Measures representing characteristics of the entire population are related to factors of interest |
What is the unit of analyses for ecological studies? | Populations or groups |
It is seldomly possible to evaluate causal relationships from observed associations in which type of study? | Correlational |
In cross sectional studies, when are exposure and disease assessed? | Exposure and disease are assessed simultaneously |
What is the reverse causality problem in determining cause and effect? | The problem is when the assumption is A causes B when the truth may actually be that B causes A. Which came first? |
What are descriptive studies typically used for? | Characterizing the distribution of disease within a population and hypothesis generation about the causes of disease occurrence in the population |
What are analytic studies typically used for? | Identifying possible causes for the occurrence of disease (risks) |
What are experimental studies typically used for? | To test new treatments or interventions |
What types of studies asks questions to generate hypotheses? | Descriptive studies |
What do descriptive studies provide data on? | Who? Where? When? = Person. Place. Time. |
In this type of study, data mostly is aggregated and was previously collected for a purpose unrelated to the study. | Ecological study |
What are two types of ecologic studies? | 1) Comparative 2) Time trends |
What are comparative ecological studies? | Studies that examine an exposure-disease relationship between groups at one point in time |
What are time trends ecological studies? | Studies that examine an exposure-disease relationship over several time points in a single group |
What can ecologic variables summarize? | Individual attributes, environmental attributes, and global variables |
These types of studies usually describe groups defined by geography and/or time. | Ecologic |
When are ecologic studies most appropriate? | This study design is often appropriate for studying broad social and cultural processes (e.g., poverty, laws/policies, access to care, environmental factors) or when population-level variables are of interest |
In this type of study, the joint distribution of risk and outcome is often unknown | Ecologic |
Why is the joint distribution of risk and outcome often unknown in correlational studies? | Existing data sources are often compiled independently |
An association at the aggregate level does not guarantee an association at the individual level. (T/F) | True |
In which type of study are groups identified on the basis of the outcome? | Case-control |
Which type of study design requires smaller sample size, ca/co or cohort? | Case-control |
This type of study design is good for rare outcomes or outcomes of long latency. | Case-control |
Which study design is best suited to the study of diseases for which medical care is sought (e.g., cancers, hip fracture)? | Case-control |
Which type of study should be the first approach to testing of a hypothesis (useful for exploratory study of multiple variables looking for clues)? | Case-control |
This type of study is susceptible to bias and confounding and appropriate control group can be difficult to find | Case-control |
What is the strongest observational design for establishing a cause and effect relationship? | Cohort |
What type of study allows for calculation of incidence of diseases in exposed and unexposed individuals? | Cohort |
What type of study allows direct calculation of relative risk? | Cohort |
What type of study is efficient for study rare exposures? | Cohort |
What type of study is efficient for study rare outcomes? | Case-control |