BIOL 437 Week Eight P.1 (Statistical Methods in Analytical Epidemiology)

Question 1

analytic study

Answer 1

• attempts to answer why and how a health-related event occured
• test specific a priori hypotheses
• comparision group
• observational and experimental

Question 2

analytic observational studies

Answer 2

• researchers observe relationships between variables

- may be exploratory or analytic

Question 3

analytic experimental studies

Answer 3

-a portion of the participants are assigned the intervention

Question 4

types of analytic observation studies

Answer 4

-case-control
-case-crossover
-nested case-control
-cohort
>prospective
>retrospective

Question 5

observational exploratory

Answer 5

• useful for identifying clues as to cause-effect relationships
• variety of associations examined

Question 6

observational analytic

Answer 6

• evaluations of associations between exposure

- outcome variables starts with a specific a prior hypothesis

Question 7

case-control study

Answer 7

-outcome is always identified prior to the exposure

>looking back in time

Question 8

steps to a case-control study

Answer 8

1. Identify cases
2. Identify controls
3. Investigate whether the cases are more or less likely than controls to have had past experiences, lifestyle behaviours or exposures

Question 9

selection of cases

Answer 9

1. Establish the diagnostic criteria
2. Definition of disease
   - may consist of new cases (incidence) or all cases (prevelance)

Question 10

cases come from

Answer 10

• records from public health clinics
• physician offices
• health maintenance organizations
• hospitals
• industrial and government sources
• should be representative of all persons with the disease

Question 11

selection of cases types

Answer 11

1. Sampling

2. Restriction

Question 12

sampling

Answer 12

-representation requires random selection with a sufficiently large sample size

Question 13

restriction

Answer 13

• may improve validity (advantage)

- may limit generalization (disadvantage)

Question 14

control subjects should

Answer 14

-look like case subjects, with the exception of not having the disease
-representative of the general population
>same possibility of being selected or exposed

Question 15

selection of controls places

Answer 15

• general population
• hospital
• family, friends, relative

Question 16

hospital advantages

Answer 16

• easily identified
• more likely to cooperate
• more likely to be aware of exposures

Question 17

hospital disadvantage

Answer 17

-don’t accurately represent the exposure distribution

Question 18

general populaiton advantage

Answer 18

-represent population

Question 19

general population disadvantages

Answer 19

• more costly and time consuming
• may be difficult to contact
• may have poorer recall
• less motivated to participate

Question 20

special groups advantages

Answer 20

• healthier than hospitals
• more likely to cooperate
• provide more control

Question 21

special groups disadvantages

Answer 21

-if exposure is similar, an underestimation of true association could result

Question 22

info about exposure status may be obtained

Answer 22

• medical records
• interviews
• questionnaries
• surrogates (spouses, sibilings, employees)

Question 23

time window for determining exposure

Answer 23

• important

- influenced by understanding of potential causal factors associated with the disease

Question 24

appropriate measure of association

Answer 24

• depends on nautre of data
• when dichotomous:
  1. Odds ratio (OR) (relative odds): case-control
  2. Risk ratio (relative risk): cohort
  3. Rate ratio: cohort

Question 25

2x2 contingency table

Answer 25

-used to summarize relationship between exposure and health outcomes

Question 26

OR=1

Answer 26

-no association between exposure and outcome

Question 27

OR>1

Answer 27

-positive association between exposure and outcome

Question 28

OR<1

Answer 28

-negative association between exposure and outcome

Question 29

OR range

Answer 29

• from 0 to infinity

- mathematical properties allows calculation of the OR using logistic regression

Question 30

bias

Answer 30

-systematic error in the collection or intrepretation of epidemiological data

Question 31

bias results in

Answer 31

-inaccurate (over or under) estimation of the association between exposure and disease

Question 32

avoid bias at the design stage

Answer 32

-paramount because of the difficulty identifying and accounting for it later

Question 33

types of bias in case-control studies

Answer 33

1. Selection bias
2. Observation
   >recall bias
   >interview bias
3. Misclassification
4. Confounding

Question 34

selection bias and observation

Answer 34

-will always result in mis-classificaiton

Question 35

selection bias

Answer 35

• cases and controls based on exposure
• relationship among exposure and disease in participants differ
• recruiting all cases in population avoids it

Question 36

types of selection bias

Answer 36

1. Berkson’s bias

2. Prevelance-incidence bias

Question 37

Berkson’s bias

Answer 37

-hospital-patient bias
-controls from hospital may be more likely to have confounding conditions
-minimize by doing randomization
>not possible in observational analytic studies

Question 38

recall bias

Answer 38

-differential accuray of recal between cases and controls

Question 39

interviewer bias

Answer 39

• interviewer probes cases differently than controls

- interviewers must be blinded