BCCCP FINAL EXAM ACTUAL QUESTIONS AND SOLUTIONS
RATED A+
✔✔Case-control studies - ✔✔Case-control
i. Retrospective design
(a) Provides an efficient means to determine the association between the risk factor and
the
outcome of interest
(b) Two groups (with and without the outcome) are compared to identify the differences
and
risk factors for developing the outcome of interest
(c) Potential for selection bias and confounding
✔✔Odds ratio - ✔✔An odds ratio (OR) is a measure of association between an
exposure and an outcome. The OR represents the odds that an outcome will occur
given a particular exposure, compared to the odds of the outcome occurring in the
absence of that exposure.
The OR is interpreted in relation to a reference point (1.0). If the 95% confidence
interval (CI)
includes 1, the odds of the event occurring are equally likely in either group.
✔✔Case-cohort study - ✔✔b. Case-cohort study
i. Prospective or retrospective design
(a) Observational study of a given population over a given time to determine the
association
between risk factors and the outcome of interest. Identifies the relationship between
exposure and outcome
(b) Describes the natural progression of a disease
✔✔Different types of bias
- Selection
- Observation
- Recall - ✔✔iii. Bias - Systematic error
(a) Selection bias: Systematic selection of subjects that leads to an imbalance, or an
advantage,
in favor of one cohort over the other
(b) Observation bias: Observers (research team) are aware of the research purpose
and allow
this knowledge to influence interpretation of results.
(c) Recall bias: Methodological error that is introduced in survey research when the
participant
is asked to provide recall of a past event.
✔✔Type 1 error (stats) - alpha error
- think REJECT - ✔✔To reject the H0 when it is true.
, Decisional threshold to accept/reject the H0 is conventionally set at α = 0.05.
The α value represents the likelihood that a type I error will be made
✔✔Type 2 error (stats) - beta error
- think ACCEPT - ✔✔Type II error (beta [β] error): To accept the H0 when, it is in fact
false
(i.e., the H1 should be accepted). Decisional threshold to set β between 0.2 and 0.1
i. What does "power" really mean? The ability to detect a difference if one truly exists.
Contingent on sample size. However, this is an estimate and may be inaccurate (usually
based on previous literature).
✔✔Power (1 − β) - ✔✔The ability to detect differences between
groups if one actually exists (H1 is true)
Dependent on:
a. alpha
b. sample size
c. size of difference between outcomes you wish to detect (If unknown, you will have to
specify how large a change is worth detecting)
d. variability of outcomes being measured
**c and d are usually determined from previous data/the literature
✔✔Necessary components for estimating appropriate sample size - ✔✔i. Acceptable
type II error rate (usually 0.10-0.20)
ii. Observed difference in predicted study outcomes that is clinically signi cant iii. The
expected variability in the effect of interest
iv. Acceptable type I error rate (usually 0.05)
v. Statistical test that will be used for primary end point
✔✔P value - ✔✔tells us the probability of being wrong when we conclude that a true
difference exists - FALSE POSITIVE
✔✔Parametric data statistical tests - ✔✔Parametric Data
1. Student t-test: Comparison of means between two independent groups
2. Analysis of variance: Comparison of means between three or more groups
✔✔Nonparametric data statistical tests - ✔✔Nonparametric Data
1. Two groups: Wilcoxon rank sum or Mann-Whitney U test
2. Three or more groups: Kruskal-Wallis
✔✔Nominal data statistical tests - ✔✔Nominal Data
1. Chi-square test
2. Fisher exact test: Unique to small data sets (fewer than five observations)
✔✔Correlation versus regression - ✔✔1. Correlation examines the strength of the
association between two variables. It does not necessarily
RATED A+
✔✔Case-control studies - ✔✔Case-control
i. Retrospective design
(a) Provides an efficient means to determine the association between the risk factor and
the
outcome of interest
(b) Two groups (with and without the outcome) are compared to identify the differences
and
risk factors for developing the outcome of interest
(c) Potential for selection bias and confounding
✔✔Odds ratio - ✔✔An odds ratio (OR) is a measure of association between an
exposure and an outcome. The OR represents the odds that an outcome will occur
given a particular exposure, compared to the odds of the outcome occurring in the
absence of that exposure.
The OR is interpreted in relation to a reference point (1.0). If the 95% confidence
interval (CI)
includes 1, the odds of the event occurring are equally likely in either group.
✔✔Case-cohort study - ✔✔b. Case-cohort study
i. Prospective or retrospective design
(a) Observational study of a given population over a given time to determine the
association
between risk factors and the outcome of interest. Identifies the relationship between
exposure and outcome
(b) Describes the natural progression of a disease
✔✔Different types of bias
- Selection
- Observation
- Recall - ✔✔iii. Bias - Systematic error
(a) Selection bias: Systematic selection of subjects that leads to an imbalance, or an
advantage,
in favor of one cohort over the other
(b) Observation bias: Observers (research team) are aware of the research purpose
and allow
this knowledge to influence interpretation of results.
(c) Recall bias: Methodological error that is introduced in survey research when the
participant
is asked to provide recall of a past event.
✔✔Type 1 error (stats) - alpha error
- think REJECT - ✔✔To reject the H0 when it is true.
, Decisional threshold to accept/reject the H0 is conventionally set at α = 0.05.
The α value represents the likelihood that a type I error will be made
✔✔Type 2 error (stats) - beta error
- think ACCEPT - ✔✔Type II error (beta [β] error): To accept the H0 when, it is in fact
false
(i.e., the H1 should be accepted). Decisional threshold to set β between 0.2 and 0.1
i. What does "power" really mean? The ability to detect a difference if one truly exists.
Contingent on sample size. However, this is an estimate and may be inaccurate (usually
based on previous literature).
✔✔Power (1 − β) - ✔✔The ability to detect differences between
groups if one actually exists (H1 is true)
Dependent on:
a. alpha
b. sample size
c. size of difference between outcomes you wish to detect (If unknown, you will have to
specify how large a change is worth detecting)
d. variability of outcomes being measured
**c and d are usually determined from previous data/the literature
✔✔Necessary components for estimating appropriate sample size - ✔✔i. Acceptable
type II error rate (usually 0.10-0.20)
ii. Observed difference in predicted study outcomes that is clinically signi cant iii. The
expected variability in the effect of interest
iv. Acceptable type I error rate (usually 0.05)
v. Statistical test that will be used for primary end point
✔✔P value - ✔✔tells us the probability of being wrong when we conclude that a true
difference exists - FALSE POSITIVE
✔✔Parametric data statistical tests - ✔✔Parametric Data
1. Student t-test: Comparison of means between two independent groups
2. Analysis of variance: Comparison of means between three or more groups
✔✔Nonparametric data statistical tests - ✔✔Nonparametric Data
1. Two groups: Wilcoxon rank sum or Mann-Whitney U test
2. Three or more groups: Kruskal-Wallis
✔✔Nominal data statistical tests - ✔✔Nominal Data
1. Chi-square test
2. Fisher exact test: Unique to small data sets (fewer than five observations)
✔✔Correlation versus regression - ✔✔1. Correlation examines the strength of the
association between two variables. It does not necessarily
