ch. 10 & ch. 11 questions

Residual confounding

An association remains confounded even after some confounders have been controlled. It arises from lack of information on all confounding variables, classifying confounders in overly broad categories, or mismeasuring confounders.

How do you determine whether a variable confounds an association?

Epidemiologists usually compare the crude/confounded measure of association with the adjusted measure of association. If there is an appreciable difference between the two (i.e., at least a 10% difference), confounding is considered present.

True or False: Bias is introduced primarily during the analysis stage of a study.

False

True or False: Epidemiologists can tell whether confounding is present by examining the strength of the crude measure of association.

False

True or False: Experimental studies always have less confounding than observational studies.

False

True or False: Including a large sample size reduces self-selection bias

False

True or False: It is possible to fix or adjust bias during the analysis phase of a study.

False

True or False: Mediating variables in a causal pathway are special types of confounders

False

True or False: Open-ended interview questions are the best way to ascertain exposure information.

False

True or False: Poor recall and recall bias are synonymous terms for the same concept.

False

True or False: Using an inaccurate case definition increases the likelihood of nondifferential misclassification of the disease

False

True or False: Bias can pull an estimate of association either toward or away from the null.

True

True or False: Collecting data on potential confounding variables enables multivariable analyses.

True

True or False: If randomization is unsuccessful in an experimental study, investigators may use other options (such as stratified and multivariable analysis) to control for confounding

True

True or False: The counterfactual ideal is used to guide the selection of a comparison group to minimize confounding.

True

True or False: Using incentives to ensure high rates of participation in a study will decrease selection bias.

True

True or False: When a positive association is biased away from the null, the true association is overestimated.

True

True or False: When a positive association is biased toward the null, the true association is underestimated

True

State which method to control for confounding is being used in the following scenarios. In each scenario, exercise is the exposure, myocardial infarction is the disease, and gender is the confounder: A study of exercise and myocardial infarction that is limited to men.

Restriction

State which method to control for confounding is being used in the following scenarios. In each scenario, exercise is the exposure, myocardial infarction is the disease, and gender is the confounder: A study of exercise and myocardial infarction that includes men and women. The study determines the relative risk separately for men and women and compares it with the crude relative risk.

Stratified Analysis

Is the variable in question a confounder? A case-control study of uterine fibroids in relation to use of oral contraceptives (OCs). In this study population, cigarette smoking is associated with uterine fibroids among OC users and nonusers and is not on the causal pathway between OCs and the occurrence of fibroids. Is cigarette smoking a confounder in this study?

Can't tell

Recall bias is most likely to occur in

Case-control studies

True or False: A study must be valid before its results can be generalized.

True

True or False: All high-quality epidemiological studies include techniques for controlling confounding.

True

Describe three methods for controlling confounding in the study design, and give one advantage and one disadvantage for each method.

(Randomization, Matching, and Restriction) 1. Randomization is the act of assigning or ordering using a random process. It means that everyone in the study has an equal chance of being assigned to one of the groups (such as treatment vs. comparison). The main advantage of randomization is that it controls for both known and unknown confounders if the sample size is sufficiently large. Its main disadvantage is that it can be used only in experimental studies. 2. Matching is the process of making the distribution of confounders identical in the compared groups while selecting the study subjects. It is good for controlling for confounding by complex nominal variables, such as neighborhood or sibship, and for controlling confounding in small studies. Its main disadvantage includes the difficulty and expense of finding appropriate matches. 3. Restriction means that the investigator limits admission into a study to individuals who fall within a specific category or categories of a cofounder. Its main advantages are simplicity and relatively low expense, and its disadvantages include difficulty in identifying a sufficient number of subjects (this depends on the number and the characteristics of the restrictions) and limiting the generalization of the study.

How can selection bias be minimized?

1. Ensure that selection of cases and controls is independent of exposure (in a case-control study) 2. And that selection of exposed and unexposed groups is independent of outcome (in a retrospective cohort study) 3. Obtain high follow up and participation rates (all types of studies).

How can interviewer bias be minimized?

1. Mask interviewers to the study hypothesis and to the disease or exposure status of the study subjects 2. Carefully design the interview instrument.

How can recall bias be minimized?

1. Mask study subjects to the study hypothesis 2. Use diseased controls if conducting a case-control study 3. Carefully design an interview instrument.

A case-control study was conducted to determine whether using antihistamines around the time of conception increased the risk of birth defects in the offspring. No personal interviews were conducted regarding the subjects' antihistamine use. Instead, women were considered exposed if computerized pharmacy records from their health maintenance organization indicated that they had filled at least one prescription for antihistamines within 500 days before the birth of the child. 1. Which type of information bias is this data collection method most susceptible to? In which direction would this type of error bias the study results? 2. Which type of information bias is this data collection method least susceptible to?

1. Nondifferential misclassification of the exposure. Some women who filled the health maintenance organization's prescriptions for antihistamines may not have used them, and other women may have obtained antihistamines from outside sources. This type of misclassification is as likely to occur among cases as controls, therefore, it is nondifferential and biases results toward the null. 2. Recall and interviewer bias. Subjects were not asked to recall their exposures, and interviews were not used to obtain the exposure data.

A prospective cohort study was conducted to determine the risk of heart attack among men with varying levels of baldness. Third-year residents in dermatology conducted visual baldness assessments at the start of the study (which was before any heart attacks had occurred). Four levels of baldness were coded: none, minimal, moderate, and severe. The follow-up rate was close to 100%. Which of the following types of bias were surely avoided in this study?

1. Recall bias of the exposure information (YES) 2. Differential misclassification of the exposure (YES) 3. Nondifferential misclassification of the exposure (NO) 4. Selection bias (YES - because it is a prospective cohort study with nearly 100% follow up)

Describe two methods for controlling confounding during the analysis, and give one advantage and one disadvantage for each method.

1. Stratification is the process of evaluating the association within homogeneous categories of a confounder. Its main advantages are that it is straightforward and easy to carry out. Its main disadvantage is that it cannot control for numerous variables simultaneously because a large number of strata are generated relative to the number of study subjects. 2. Multivariable analysis is a method for controlling confounding by constructing a mathematical model that describes the association between the exposure, the outcome, and the confounders. Its main advantage is that it can control for many confounders simultaneously. Its main disadvantage is that one can no longer view the raw data.

How can misclassification be minimized?

1. Use the most accurate source of information 2. Use sensitive and specific criteria to define the exposure and the disease.

Control selection bias

A type of selection bias that occurs in case-control studies when the controls do not accurately represent the exposure distribution in the source population that produced the cases. It occurs when different criteria are used to select cases and controls and these criteria are related to the exposure.

Directed acyclic graph (DAC)

A visual representation of the relationship between the exposure, disease, and confounding and mediating variables.

What are the key characteristics of a confounding variable?

A confounder is associated with the exposure in the source population that produced the cases and an independent cause or predictor of the outcome under study. The latter means that it is associated with the disease among both exposed and unexposed individuals. In addition, a confounder cannot be an intermediate step in the causal pathway between the exposure and disease. An intermediate variable is often called a mediator.

Selection bias is most likely to occur in:

Both retrospective and case-control studies

State the main difference between differential and nondifferential misclassification, and state which direction(s) each type of error can bias the study results.

In nondifferential misclassification, inaccuracies that occur on one axis (exposure or disease) are independent of the other axis. For example, if there is an error in exposure misclassification, it occurs with equal likelihood among diseased and non diseased individuals. In differential misclassification, inaccuracies that occur on one axis (exposure or disease) are dependent on the other axis. For example, if there is an error in exposure misclassification, it occurs more often in the case group than the control group. Nondifferential misclassification of dichotomous variables (i.e. variables with two categories) biases the results toward the null. Differential misclassification can bias the results either toward or away from the null.

State which method to control for confounding is being used in the following scenarios. In each scenario, exercise is the exposure, myocardial infarction is the disease, and gender is the confounder: A case-control study of exercise and myocardial infarction that includes men and women. Controls are selected so that the proportions of male and female controls are identical to that among cases.

Matching

Is the variable in question a confounder? A study of the relationship between air pollution and asthma among children. The crude and race-adjusted risk ratios are both 2.0. Is race a confounder in this study?

No

Is the variable in question a confounder? A study of the relationship between exercise and heart attacks that is conducted among men who do not smoke. Is gender a confounder in this study?

No

Is the variable in question a confounder? cohort study of the risk of liver cirrhosis among female alcoholics. Incidence rates of cirrhosis among alcoholic women are compared with those among nonalcoholic women. Nonalcoholics are individually matched to alcoholics on month and year of birth. Is age a confounder in this study?

No

Healthy worker effect

Occurs in occupational studies when disease and death rates in a working population are compared with those among the general population. The rates of disease among workers are typically lower than those in the general population because there is a higher proportion of ill people in the general population.

Recall bias

Occurs when the level of accuracy differs between the compared groups. It occurs in a case-control study when cases remember or report their exposures differently (more or less accurately) from controls. It occurs in retrospective cohort studies when individuals who are exposed remember or report illnesses differently than those who are unexposed.

Positive confounding

The true crude association is exaggerated

Negative confounding

The true crude association is underestimated

Is the variable in question a confounder? A case-control study of the relationship between cigarette smoking and pancreatic cancer. In this study, coffee drinking is associated with smoking and is a risk factor for pancreatic cancer among both smokers and nonsmokers. Is coffee drinking a confounder in this study?

Yes

Is the variable in question a confounder? A study of the relationship between contact lens use and the risk of eye ulcers. The crude risk ratio is 3.0 and the age-adjusted risk ratio is 1.5. Is age a confounder in this study?

Yes

Confounding

a mixing of effects between an exposure, an outcome, and a third extraneous variable that is termed the confounder. Confounding distorts the crude relationship between an exposure and an outcome because of the relationships between the confounder and the exposure and the confounder and the disease.