UW1

Question 1

hazard ratio?

Answer 1

ratio of an event rate occuring in the treatment group compared to an event rate occuring in the non-treatment group
less than 1: treatment radio has lower event rate)

Question 2

intention to treat analysis

Answer 2

to miminze potential confounding variables

compares the initial randomized treatment groups regardless of the evaluation treatment

Question 3

Prevalence odd ratio

Answer 3

calculated in cross sectional studies to compare the prevalence of a disease between populations

Question 4

attributable risk percent (or etiologic fraction)

Answer 4

the risk in a population that can be explained by exposure to a particular RF
(risk in exposed - risk in unexposed) / risk in exposed
OR
(RR-1)/RR

Question 5

pearson correlation coefficient - when the correlation is strong

Answer 5

when r is larger than 0.5

Question 6

case series

Answer 6

study involving only patients diagnosed with a condition of interest –> it can be helpful in determining the natural history of uncommon conditions

Question 7

ecological study

Answer 7

the unit of observation is a population
disease rates and exposures are measured in 2 (or more) populations and the association between disease rates and exposures is determined
- however, results of associations may not translate to the individual level
- not determine incidence

Question 8

effect modification

Answer 8

when an external variable positively or negatively impacts the effect of a risk factor on the disease of interest
ex. the risk of venous thrombosis is increased with estrogen therapy, and this effect is augmented by smoking

Question 9

methods to control confounding

Answer 9

design stage:
1. Matching
2. restriction (ex. only women)
3. randomization
Analysis stage
1. stratified analysis
2. statistical modeling

Question 10

in a clinical trials, randomization is said to be successful when

Answer 10

a similarity of baseline characteristics of the patients in the treatment and placebo group is seen

Question 11

factorial design

Answer 11

studies involve randomization to different interventions with additional study of 2 or more variables

Question 12

parallel study

Answer 12

randomizes one treatment to one group and a different treatment to other group such as treatment drug to 1 group vs placebo to the other
- no other variables measured

Question 13

cluster analysis

Answer 13

grouping of different data point into similar categories

- randomization at the level of groups rather than at the level of individuals

Question 14

generallizability?

Answer 14

aka external validity, pertains to the applicability of study results to other populations (eg. results of a study in middle aged women would not be expected to be applicable to elderly men)

Question 15

how to differentiate confounding from effect modification

Answer 15

by stratified analysis
in confounding, if u separate the population regarding the connfounding factor, u will not find corellation (eg. smokers vs non smokers if u checked OCP in breast cancer) –> in non of these 2 groups
on the other hand, in effect modification u will have

Question 16

accuracy of a test

Answer 16

it is defined as the proportion of true results (TP + TN) out of all the results of a given diagnostic test –> it deptneds on the sensitivity and specificity of the test as well as the prevalence of the condition in the population being tested –> increase as the total area under the ROC curve increases

Question 17

how to measure the accuracy of a test from ROC

Answer 17

total area under the curve

Question 18

selection bias - types

Answer 18

1. ascertainment sampling bias
2. nonresponse bias
3. berkson bias
4. prevalence (Neyman) bias
5. attrition bias

Question 19

attrition bias - type and definition

Answer 19

selection bias
- significant loss of study participants may cause bias if those lost to follow up differ significantly from remaining subjects

Question 20

prevalence (Neyman) bias - type and definition

Answer 20

selection bias

- exposure that happen before disease assessment can cause study to miss diseased patients that die early or recover

Question 21

ascertainment (sampling) bias - type and definition

Answer 21

selection

study population differ from target population due to nonradom selection method

Question 22

observational bias - types

Answer 22

1. recall bias
2. observer bias
3. reporting bias
4. surveillance (detection) bias

Question 23

reporting bias - type and definition

Answer 23

observational

- subjects over or under report exposure history due to perceived social stigmatization

Question 24

Surveillance (detection) bias - type and definition

Answer 24

observational
- risk factor itself causes increased monitoring in exposed group relative to unexposed group, which increases probability of identifying a disease

Question 25

best study to find incidence

Answer 25

cohort study

Question 26

Harthorne bias

Answer 26

Subjects change behavior because they know that they are being in study

Question 27

0.7 RR Means

Answer 27

0.3 reduction

Question 28

Increase precision by increase

Answer 28

Sample size