Chapter 10 Flashcards
A case-control study:
Compares the exposure histories of people with and without a particular disease in order to identify likely risk factors for the disease.
Individual participants in a case-control study are selected for inclusion in the study based on what?
On their disease status
Patients with the disease of interest are classified as ____, while patients without the disease are classified as ____.
Cases; controls
True or false:
Both cases and controls are asked the same set of questions about past exposures.
True
What statistical measure is used for case control studies?
Odds ratio
What is the first step in designing a case-control study?
1) Getting approval from an ethics committee
2) Identifying an appropriate and accessible source of individuals with the disease of interest.
When do we use case-control studies?
When the disease is relatively uncommon but a source of cases is available.
What should we watch out for in case-control studies?
Recall bias
What requirements do case-control studies have?
1) All cases must have the same disease
2) The study’s case definition must specify exactly what characteristics must be present or absent for a person to be deemed a case
3) An appropriate source of controls must be selected
Where can controls be recruited from?
1) Friends and relatives of cases
2) Hospital or clinic patients without the disease of interest 
3) The general population
What should a control definition do?
It should spell out all of the eligibility criteria for members of the comparison population.
There are three often-used options for matching cases and controls:
1) No matching
2) Frequency (group) matching
3) Matched-pairs (individual) matching
Explain “no matching” studies.
They assume that similar inclusion and exclusion criteria for cases and controls will result in case and control populations that have similar distributions according to certain characteristics that may be confounders of the association between the key exposure and the disease.
Explain frequency (group) matching.
The researcher uses a few variables to ensure comparable cases and control populations. this ensures a control population that is similar to the case population.
Explain matched-pairs (individual) matching.
Each case is personally linked to a particular individual control. This is common in genetic studies.
What should you look out for in both frequency-matching and matched-pairs matching?
It is important not to overmatch (forced similarity).
Why is it important to not overmatch?
1) The variables used as matching criteria cannot be considered as exposures during analysis.
2) When there are more matching characteristics, it can be difficult to find controls who meet all of the matching criteria. (Different study population from general population because of strict eligibility requirements) = limits external validity.
3) Results in statistical bias that obscures the relationship between exposure and disease.
What can help minimize problems associated with bias?
Careful study design and implementation
Researchers must keep two considerations in mind when designing the survey instrument for case-control studies:
1) Asking questions that confirm whether the respondent is a case control or neither. [Adhering to strict definitions for what constitutes a case and control minimizes the risk of misclassification bias].
2) Awareness of different memories between cases and controls [Recall bias].
What is the odds in a case-control study?
Compares the likelihood of having had a particular exposure to not having had it. (if 50% had it, and 50% didn’t, the odds = 1)
If 25% report having an exposure and 75% to not then what are the odds?
25%/75%
= 0.33
What is the odds ratio?
Compares the odds of exposure among cases to the odds of exposure among controls.
What is a contingency table (crosstab)?
A row-by-column table that displays the counts of how often various combinations of events happen.
What are two-by-two tables?
They compare two dichotomous (yes/no) variables.
What is the formula (point estimate) for the odds ratio?
OR = (a/c)/(b/d) OR = (ad)/(bc)
If OR=1, that means:
The odds of exposure were the same for cases and controls.
If OR>1, that means:
Cases had higher odds of exposure than controls implying that the exposure was risky.
If OR<1, that means:
Cases have lower odds of exposure than controls implying that the exposure was protective.
The 95% confidence interval shows:
Whether an OR is statistically significant.
When the entire 95% confidence interval is less than 1, The OR is _____ (significant/not significant), and the exposure is deemed to be ____ (protective/risky) in the study population.
Significant; protective
When the entire 95% confidence interval is greater than 1, The OR is _____ (significant/not significant), and the exposure is deemed to be ____ (protective/risky) in the study population.
Significant; risky
When the entire 95% confidence interval overlaps OR=1, the OR is _____ (significant/ not significant).
Not significant.
When the entire 95% confidence interval overlaps OR=1, what does the mean for the exposure?
1) The exposure and disease have no association.
OR
2) The sample size was too small (use power calculations to confirm)
A statistically significant p-value for the chi square test is:
p<0.05
When the 95% confidence interval for an OR overlaps 1, the p-value for the chi square test is:
p>0.05
True or false:
For a case-control study, we can say that “the exposed had a higher (or lower) rate of disease than the unexposed“.
False; The rates of disease in exposed and unexposed participants are not known.
Case-control studies are unable to estimate rates of disease among the exposed and unexposed because:
The study population is usually not representative of the community as a whole.
Case-control Studies are able to examine what?
The odds of exposure among the diseased and the not diseased.
The results for case-control studies should be phrased to indicate:
That cases had greater (or lesser) odds of exposure than controls.
For case-control studies, the orientation should always be from ____ to ____, and from ___ rather than ____.
Disease status; exposure history; odds; risks/rates.
Individually matched case-control Studies require special calculations. When both the case and control in a matched pair have the same history of exposure or non-exposure, their experiences are _____ (discordant/concordant). When they have different histories their experiences are ___ (discordant/concordant).
Concordant; discordant
Which provides more useful information about the potential relationship between the exposure and the disease:
Concordant or discordant experiences?
Discordant, because they give an indication about whether the exposure is risky or protective.
What is the matched-pairs odds ratio?
ORmp=b/c
When b/c>1 with 95%CI (all 4 categories) not overlapping 1, this means that:
Cases were more likely than controls to have been exposed, and the exposure is risky.
When b/c<1 with 95%CI (all 4 categories) not overlapping 1, this means that:
Cases were less likely than controls to have been exposed, and the exposure is protective.
When the 95% CI for b/c overlaps 1, that means that:
There is no statistically significant association between the disease and the exposure.
