Epidemiological Methods (PHEP 602): Basic Study Designs in Analytical Epidemiology (Chapter 1: 1-44) WEEK 1

_____________ is a strong risk factor for many health outcomes and is also frequently associated with numerous exposures

Age

• _______________________ ○ Truly "prospective ○ Present time to future § A prospective study watches for outcomes, such as the development of a disease, during the study period and relates this to other factors such as suspected risk or protection factor(s). § The study usually involves taking a cohort of subjects and watching them over a long period. The outcome of interest should be common; otherwise, the number of outcomes observed will be too small to be statistically meaningful (indistinguishable from those that may have arisen by chance). § All efforts should be made to avoid sources of bias such as the loss of individuals to follow up during the study. Prospective studies usually have fewer potential sources of bias and confounding than retrospective studies.

Concurrent

What is Analytical Epidemiology:

Designs that allow assessment of hypotheses of associations of suspected risk factors exposures with health outcomes

Why are Analysis of birth cohorts important

It is important to understand the patterns of association between age (a key determinant of health status) and disease in cross-sectional analysis

_____________ _______________ techniques can be used to disentangle these effects (Age, Cohort, Period Effect)

Multiple regression

• _______________________ ○ Historical or retrospective cohort studies ○ Less expensive and can be done more expeditiously than concurrent studies ○ Disadvantage is obligatory reliance on available information, as a result, the type or quality of exposure or outcome data may not be well suited to fulfill the study objectives. ○ A retrospective study looks backwards and examines exposures to suspected risk or protection factors in relation to an outcome that is established at the start of the study. ○ Many valuable case-control studies, such as Lane and Claypon's 1926 investigation of risk factors for breast cancer, were retrospective investigations. ○ Most sources of error due to confounding and bias are more common in retrospective studies than in prospective studies. For this reason, retrospective investigations are often criticized. ○ If the outcome of interest is uncommon, however, the size of prospective investigation required to estimate relative risk is often too large to be feasible. In retrospective studies the odds ratio provides an estimate of relative risk. You should take special care to avoid sources of bias and confounding in retrospective studies.

Nonconcurrent:

_____________ _____ ___________ _____________across successive generations (birth cohorts) distort the apparent associations of age and health outcomes that are observed at any point in time

Variability of past exposures

Age has potential , _____________ ___________ it is often important to asses its relationship with exposures and outcomes

confounding effects

Case-Cohort is

Similar to a nested case-control study in that the cases and non-cases are within a parent cohort; cases and non-cases are identified at time t1, after baseline. In a case-cohort study, the cohort members were assessed for risk factors at any time prior to t1. Non-cases are randomly selected from the parent cohort, forming a subcohort. No matching is performed.

What is Epidemiology:

The study of the distribution and determinants of health-related states or events in specified populations and the application of this study to control health problems.

What is a Birth cohort:

people born during a certain time period and geographical location. For example, if you were born in the United States between 1980 and 1985, everyone else born in the U.S. between those years could be considered your cohort.

Advantages of nested case-control

§ Efficient - not all members of parent cohort require diagnostic testing § Flexible - allows testing of hypotheses not anticipated when the cohort was drawn at t0 § Reduces selection bias - cases and controls sampled from same population Reduces information bias - risk factor exposure can be assessed with investigator blind to case status

What is Descriptive Epidemiology:

□ Makes use of available data to examine how rates (mortality) vary according to demographic variables. □ When distribution of rates is not uniform according to person, time, and place, the epidemiologist is able to define high-risk groups for prevention purposes

What is Observational epidemiology:

□ The researcher studies, but does not alter, what occurs □ Observational Studies: a) Ecologic study b) Prospective/Retrospective cohort c) Case-control d) Cross-sectional study designs

• Matching in Cohort Study ○ Not common ○ Alternative means to control for confounding are usually preferred by __________________ data

(ADJUSTMENT)

Cohort Studies are also called

Prospective studies

What is Period effect:

Result from external factors that equally affect all age groups at a particular calendar time. It could arise from a range of environmental, social and economic factors e.g. war, famine, economic crisis. Methodological changes in outcome definitions, classifications, or method of data collection could also lead to period effects in data.

A ___________ population is identified. Its subjects are classified according to exposure status, and the incidence of the disease (or any health outcome of interest) is ascertained and compared across exposure categories.

defined

• Nested Case-Control Studies within a Defined Cohort Also known as

hybrid or ambidirectional designs

Construct Validity is

is the extent to which an operational variable (ex. Body weight) accurately represents the phenomenon it purports to represent (ex. Nutritional status)

○ Advantages of Case-Cohort Study: (Similar to nested case-control study design:)

§ Efficient- not all members of parent cohort require diagnostic testing § Flexible- allows testing hypotheses not anticipated when the cohort was drawn (t0) § Reduces selection bias - cases and noncases sampled from same population § Reduced information bias - risk factor exposure can be assessed with investigator blind to case status § The subcohort can be used to study multiple outcomes § Risk can be measured at any time up to t1 (e.g. elapsed time from a variable event, such as menopause, birth) Subcohort can be used to calculate person-time risk

Disadvantages of Case-Cohort Study as compared to nested case-control study design:

§ Increased potential for information bias because subcohort may have been established after t0 § Exposure information collected at different times (e.g. potential for sample deterioration)

○ Disadvantages of nested case-control

§ Reduces power (from parent cohort) because of reduced sample size by: 1/(c+1), where c = number of controls per case Nested case-control studies can be matched, not matched or counter-matched.

Examples of group-level measures:

§ The incidence rate of cancer among a specific population, § The mean level of blood pressure of patients seen at a clinic § the average sunlight exposure at specific geographic location on the earth, or even a preventive service included in a health insurance plan. § The occurrence of disease is compared between groups that have different levels of an exposure, which affords this study design to have at least one comparison group.

Nested Case-Control Studies within a Defined Cohort are

§ They combine some of the features and advantages of both cohort and case-control designs § This is a case-control study within a cohort study. At the beginning of the cohort study (t0), members of the cohort are assessed for risk factors. Cases and controls are identified subsequently at time t1. The control group is selected from the risk set (cohort members who do not meet the case definition at t1.) Typically, the nested case-control study is less than 20% of the parent cohort.

Selection Bias:

§ This happens when "losses" occur before the study group are selected affected their comparability. § Selection bias is a particular problem inherent in case-control studies, where it gives rise to non-comparability between cases and controls. □ In case-control studies, controls should be drawn from the same population as the cases, so they are representative of the population which produced the cases. Controls are used to provide an estimate of the exposure rate in the population. Therefore, selection bias may occur when those individuals selected as controls are unrepresentative of the population that produced the cases.

What is Ecological Study

• A study in which at least one variable, either an exposure or the outcome, is measured at the group (not individual) level. • In traditional ecologic study, two ecologic variables are contrasted to examine their possible association. Typically, an ecologic measure of exposure and an aggregate measure of disease or mortality are compared.

4. Cross-Sectional Studies are

• A study with individual-level variables that measures exposure and disease at one point in time. A snapshot of the study population. • This study design provides weak evidence of causal association between exposure and outcome because we may not be certain that the exposure preceded the disease. A patient survey is an example of a cross-sectional study.

Case-Control Study is

• Odds ratio and prevalence are used instead on incident cases. • A study that identifies individuals who develop the disease (cases) and individuals without the disease (controls), and then determines the previous exposure for each case and control. • The case group is composed only of individuals known to have the disease or outcome; the control group is drawn from a comparable population who do NOT have the disease or outcome. • We then compare the odds of exposure between cases and controls. • The measure of association for a case-control study is typically an odds ratio. • ______________ -____________study is stronger than a cross-sectional study in establishing individual-level causality because we are more certain that exposure preceded the disease outcome. The case-control study design has important advantages over the cohort design, particularly over the concurrent cohort study, as the need for a follow-up time is avoided, thus optimizing speed and efficiency

Pros for Case-Control Study

○ A case-control study is stronger than a cross-sectional study in establishing individual-level causality because we are more certain that exposure preceded the disease outcome. ○ The case-control study design has important advantages over the cohort design, particularly over the concurrent cohort study, as the need for a follow-up time is avoided, thus optimizing speed and efficiency ○ Outcome is measured before exposure ○ Controls are selected on the basis of not having the outcome ○ Good for rare outcomes ○ Relatively inexpensive ○ Quicker to complete ○ Lets you simultaneously look at multiple risk factors ○ Useful as initial studies to establish an association Can answer questions that could not be answered through other study designs

• Cons for Cohort analysis

○ A cohort study takes more time, money and subjects than does ex. A case-control study ○ Most sources of error due to confounding and bias are more common in retrospective studies than in prospective ○ In retrospective cohorts, disadvantage is obligatory reliance on available information, as a result, the type or quality of exposure or outcome data may not be well suited to fulfill the study objectives. ○ Prospective studies heavily depend on follow up

Confounding is

○ A situation in which the effect or association between an exposure and outcome is distorted by the presence of another variable. Positive confounding (when the observed association is biased away from the null) and negative confounding (when the observed association is biased toward the null) both occur. § Use Stratification, Adjustment, and Matching to minimalize it

What are Cohorts:

○ A study design where one or more samples (called cohorts) ○ A set of people followed over a period of time

Case-Based Case-Control Study:

○ A study in which incident cases are identified as the individuals in whom the disease of interest was diagnosed (e.g., breast cancer) in a certain hospital during a given year and controls are selected from among members of the community served by this hospital who did not have a diagnoses of the disease of interest by the end of that same year. ○ If exposure data are obtained through interviews, it is necessary to assume that recall or other bias will not distort the findings. ○ If only living cases are included in the study, it must be also assumed that cases that survive through the time when the study is done are representative of all cases with regard to the exposure experience. ○ It is necessary to assume that they originate from the same reference population-that is, from a more or less explicitly identified cohort. § The assumption that cases and controls originate from the same hypothetical source cohort (if even undefined) is critical when judging the internal validity of case-control data. □ Both groups must originate from populations having similar relevant characteristics

What are Cohort Studies

○ A study that begins with persons who do not have the disease but with an known level of exposure to the putative risk factor ○ The known level is often no exposure. ○ Thus, the study sample is drawn only from individuals at risk of developing the disease or outcome. Individuals are followed through time until some of them develop the disease. (DEPENDS ON FOLLOW UP) ○ We then compare the rate of the outcome for the exposed group to the rate of the outcome for the non-exposed group. ○ The measure of association is a relative risk, attributable risk or depicted with survival analysis. ○ Incidence density rates can be calculated. ○ Longitudinal surveys may be considered a cohort study.

What is Age effect:

○ Are variations linked to biological and social processes of aging specific to individuals. ○ They include physiologic changes and accumulation of social experiences linked to aging, but unrelated to the time period or birth cohort to which an individual belongs (Just looking at weather or not individual has outcome). ○ In epidemiological studies age effects are usually denoted by varying rates of diseases across age groups.

• Mixed Designs:

○ Both Nonconcurrent and concurrent follow-up components are possible

Pros for Ecologic analysis

○ Can lead to more accurate conclusions than an analysis using individual-level data even if the level of inference in the ecologic study is at the individual level: i. The first situation is when the within-population variability of the exposure if interest is low, but the between-population variability is high. ii. Second situation is when, even if the intended level of inference is the individual, the implications for prevention or intervention are at the population level. iii. Goldberger used this study because it was important (potentially modifiable) link between individual indicators of means, "income" and a specific commodity in an area "food availability in the area markets" iv. Can be easy and inexpensive v. Often rely on pre-existing data. vi. Analysis and presentation are generally simple to understand vii. Exposures may truly be population-level. viii. Can generate new hypotheses for further research.

Cons for Ecologic analysis

○ Cannot examine causality ○ Potential and alternative explanations cannot be accounted for or tested ○ ______________ Fallacy-An erroneous inference that may occur because an association observed between variables on an aggregate level does NOT necessarily represent the association that exists at an individual level. Basically an observed relationship in the population may not take place among individuals • All risk factors must operate at the individual level Reductionist approach would focus only on casual pathways at the biochemical or intracellular level.

Cons for Cross-Sectional Study

○ Cannot tell us about causal relationships (only correlation) § Causality problems ○ Generalizability limited by sampled population, population definition ○ Sample size requirements may be very large (especially when looking at rare outcomes or exposures) ○ Potential for selection bias • Disadvantages of Case-crossover ○ Information bias - inaccurate recall of exposure during control window (can be overcome by choosing control window to occur after case window) ○ Requires careful selection of time period during which the control window occurs (circumstance associated with the control window should be similar to circumstances associated with case window § e.g., traffic volume ○ Requires careful selection of the length and timing of the windows e.g., in an investigation of the risk of cell phone usage on auto accidents, cell phone usage that ceases 30 minutes before accident unlikely to be relevant to accident

Cons of Matching

○ Practical - may be cumbersome, expensive, time consuming. ○ Depending on the circumstances, index subjects may be dropped if no matching referent subjects are found as a result loss of data. ○ Also very onerous when many matching factors are used. ○ The effect of the matching factor on the outcome of interest cannot be evaluated. ○ Potential for overmatching (Matching CANNOT be undone) ○ Increase internal validity (comparability) at the cost of external validity (representativeness) ○ No statistical power is gained if matching variables are week cofounders (Gain in efficiency maybe very small)

• Pros of Matching

○ Promotes efficiency ○ Controls for Confounding and could increase statistical power (efficiency) of the study ○ Studies are most efficient when the the ratio of index to referent subjects (e.g. cases: controls) is constant and comparable across the different strata of a confounder. ○ Very useful in situations where the confounder is difficult to quantify or control, making stratification impossible. Classic example: using sibling controls.

• Pros for Cohort analysis

○ Provide stronger evidence of individual-level causation because we are measuring incidence rates of the disease. ○ Prospective studies usually have fewer potential sources of bias and confounding than retrospective studies. ○ Retrospective cohort studies are less expensive and can be done more expeditiously than concurrent studies

Pros for Cross-Sectional Study

○ Relatively quick and easy to conduct (no long periods of follow-up). ○ Low to moderate cost ○ Data on all variables is only collected once. ○ Able to measure prevalence for all factors under investigation. ○ Multiple outcomes and exposures can be studied. ○ The prevalence of disease or other health related characteristics are important in public health for assessing the burden of disease in a specified population and in planning and allocating health resources. ○ Good for descriptive analyses and for generating hypotheses. ○ Advantages of Case-crossover § Efficient - self-matching § Efficient - select only cases § Can use multiple control windows for one case window

What are Global measures:

○ Represent characteristics of the group that are not reducible to characteristics of individuals § Example: That do not have analogs (a person or thing seen as comparable to another) at the individual level □ The type of political or healthcare system in a given region □ A certain regulation or law □ The presence and magnitude of health inequalities

What are Environmental measures:

○ Represent physical characteristics of the geographic location for the group of interest. ○ Individuals have different degrees of exposure to a given characteristic, which could theoretically be measured. § Example: □ Air pollution intensity and hours of sunlight

Cons for Case-Control Study

○ Selection bias is a particular problem inherent in case-control studies, where it gives rise to non-comparability between cases and controls. § Prone to selection bias Prone to recall/retrospective bias

What are Aggregate measures:

○ Summarize the characteristic of individuals within a group as the mean value of a certain parameter or the proportion of the population or group of interest with a certain characteristic § Example: □ Prevalence of a given disease, average amount of fat intake

Ecologic fallacy (aggregation bias):

○ The bias that may occur because an association observed between variables on an aggregate level does not necessarily represent the association that exists at an individual level. ○ Failure in reasoning that arises when an inference is made about an individual based on aggregate data for a group.

What is a Cohort effect:

○ The influence that a person's date and place of birth has on social research is known as the cohort effect ○ which refers to the similarities in experiences and social influences across a particular age group. ○ This does not ignore the influence of individual beliefs or values; rather, it takes a big-picture view of how major social, cultural, or political influences and events experienced by everyone can shape their perspectives.

Case-Crossover Study is

○ This design is useful when the risk factor/exposure is transient. § For example, cell phone use or sleep disturbances are transitory (lasting only for a short time; impermanent) occurrences. ○ Each case serves as its own control, § i.e the study is self-matched. ○ For each person, there is a 'case window', the period of time during which the person was a case, and a 'control window', a period time associated with not being a case. Risk exposure during the case window is compared to risk exposure during the control window