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

1
Q

analytic study

A
  • attempts to answer why and how a health-related event occured
  • test specific a priori hypotheses
  • comparision group
  • observational and experimental
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

analytic observational studies

A
  • researchers observe relationships between variables

- may be exploratory or analytic

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

analytic experimental studies

A

-a portion of the participants are assigned the intervention

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

types of analytic observation studies

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

observational exploratory

A
  • useful for identifying clues as to cause-effect relationships
  • variety of associations examined
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

observational analytic

A
  • evaluations of associations between exposure

- outcome variables starts with a specific a prior hypothesis

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

case-control study

A

-outcome is always identified prior to the exposure

>looking back in time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

steps to a case-control study

A
  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
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

selection of cases

A
  1. Establish the diagnostic criteria
  2. Definition of disease
    - may consist of new cases (incidence) or all cases (prevelance)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

cases come from

A
  • records from public health clinics
  • physician offices
  • health maintenance organizations
  • hospitals
  • industrial and government sources
  • should be representative of all persons with the disease
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

selection of cases types

A
  1. Sampling

2. Restriction

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

sampling

A

-representation requires random selection with a sufficiently large sample size

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

restriction

A
  • may improve validity (advantage)

- may limit generalization (disadvantage)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

control subjects should

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

selection of controls places

A
  • general population
  • hospital
  • family, friends, relative
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

hospital advantages

A
  • easily identified
  • more likely to cooperate
  • more likely to be aware of exposures
17
Q

hospital disadvantage

A

-don’t accurately represent the exposure distribution

18
Q

general populaiton advantage

A

-represent population

19
Q

general population disadvantages

A
  • more costly and time consuming
  • may be difficult to contact
  • may have poorer recall
  • less motivated to participate
20
Q

special groups advantages

A
  • healthier than hospitals
  • more likely to cooperate
  • provide more control
21
Q

special groups disadvantages

A

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

22
Q

info about exposure status may be obtained

A
  • medical records
  • interviews
  • questionnaries
  • surrogates (spouses, sibilings, employees)
23
Q

time window for determining exposure

A
  • important

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

24
Q

appropriate measure of association

A
  • 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
25
Q

2x2 contingency table

A

-used to summarize relationship between exposure and health outcomes

26
Q

OR=1

A

-no association between exposure and outcome

27
Q

OR>1

A

-positive association between exposure and outcome

28
Q

OR<1

A

-negative association between exposure and outcome

29
Q

OR range

A
  • from 0 to infinity

- mathematical properties allows calculation of the OR using logistic regression

30
Q

bias

A

-systematic error in the collection or intrepretation of epidemiological data

31
Q

bias results in

A

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

32
Q

avoid bias at the design stage

A

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

33
Q

types of bias in case-control studies

A
  1. Selection bias
  2. Observation
    >recall bias
    >interview bias
  3. Misclassification
  4. Confounding
34
Q

selection bias and observation

A

-will always result in mis-classificaiton

35
Q

selection bias

A
  • cases and controls based on exposure
  • relationship among exposure and disease in participants differ
  • recruiting all cases in population avoids it
36
Q

types of selection bias

A
  1. Berkson’s bias

2. Prevelance-incidence bias

37
Q

Berkson’s bias

A

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

38
Q

recall bias

A

-differential accuray of recal between cases and controls

39
Q

interviewer bias

A
  • interviewer probes cases differently than controls

- interviewers must be blinded