Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

USPS Midterm 1 > Epi Final > Flashcards

Epi Final Flashcards

1
Q

2 types of causal relationships

A

Necessary
Sufficient

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

Necessary

A

without the factor, the disease will not exist

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

Sufficient

A

with the factor the disease will exist

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

3 characteristics of a cause

A
  1. Time order (temporality)
  2. Associtation
  3. Direction
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Time order (temporality)

A

cause must predate effect in time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Association

A

The likelihood of the outcome is different under the cause. There is a correlation between the putative cause and effect

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

Direction

A

A change in the cause will induce a change in the outcome. If you could change the cause and leave everything else the same, you should still see a change in result. requires counterfactual

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

schedule of potential outcomes

A

contains treatment, counterfactual, and difference. But this does not happen IRL because you cannot build a time machine to go back and retest the person

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

If you randomize enough units (RCTs) to intervention or controls, what factors should be balanced?

A

all pre-randomization features of the groups should be balanced. Anything else that should cause the outcome should be about the same

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

After RCT, the only remaining cause of observed differences should be wat 3 things

A
  1. the cause
  2. difference arising after randomization
  3. randomization failing by change
    If you can exclude 2 and 3, can make strong causal inference
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

3 features of strong RCT

A
  1. randomization worked
  2. Excludability - exclude other factors from explaining outcomes observed
  3. Non-interference: treatments dont spill over
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Randomized trials are the gold standard for causal inference if..

A

conducted well

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

2 major benefits of RCTs

A
  1. ensure groups are not systematically different when trial begins
  2. prevent bias in allocation
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Randomization does not equal

A

random sampling

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

A good randomization approach is truly..

A

random and cannot be predicted (like time or day of service)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

For RCTs, measuring before and after versus only after

A

before and after: account for differences in baseline. treatment effect estimated as difference between groups in the change in blood pressure
after: difference between groups in endline blood pressure

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Methods of randomization

A

simple
stratified: randomizing for a confounder (age)
Cluster: must have sufficiently large number, and clusters cannot be super different

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Crossover design

A

use each participant as their own control by switching them between placebo and treatment, but these designs only work if the effect of the treatment is temporary

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Non-inferiority and equivalency designs

A

Test hypothesis that:
one treatment produces results approx the same as existing (equivalency), or one treatment produces results that are at least as good than the other (non-inferioirty)
Useful when a new treatment is developed (not more effective, but might be faster or cheaper)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Do RCTs account for problems arising after randomization?

A

NO

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Non-adherence to treatment and solutions

A

Participants may just stop taking treatment, take wrong one, etc.
Can analyze by intention to treat (misclassification of exposre)
Can analyze by actual treatment (no longer have randomization)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Downsides of RCTs

A

If you want to describe a health problem or understand how an intervention works, not good
High internal validity often trades off with external valdiitiy (well designed observational studies often generalize better)
Unethical/unacceptable/impossible

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Analytical epi

A

seeks to understand effect of various exposures, characteritsics, or interventions on health status

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

2 steps of analystical epi

A
  1. measured association
  2. inferences draw from association? is it causal, or by chance/bias?
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

Studies (like reports or case series) only generate

A

hypotheses. valid inferences about associtions require hypotheses be rigorously tested

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

To assert association between exposure and outcomes… 3 needs

A
  1. accurately measure exposure
  2. measure outcomes
  3. see if outcome is different in presence or absence of exposure
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

2 major observational studies

A

cohort studies: group based on presence/absence of exposure, then researcher evaluates outcomes. look at association with incident disease

case control studies: classified by presence or absence of outcoome, then exposures are evaluated. look at association with prevalent disease

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

Strongest designs to identify association and approximate randomization:

A
  1. prevent bias in allocation
  2. make characteristics of both study groups comparable with respect to everything besides intervention
  3. Randomized triala - gold standard for causality
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

Fundamental elements of cohort studies

A

-2 groups of people identified: one with and one without exposure
-researcher then identifies cases among each group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

Selecting a study pop for cohort studies: two options

A
  1. select explicity on basis of exposure (good for when rare)
  2. select defined pop and classify members as exposed ot not (more generalizability, more representative pop.)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

Steps of prospective cohort

A
  1. select pop
  2. identify who smokes at start/follow nd periodiclly assess who begins smoking
  3. identify who develops lung cancer
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

Strengths/weaknesses of cohort

A

strength: you know exposure predated outcome
weakness: long, expensive, people are dying, diseases have long latent periods

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

Steps of retrospective cohort

A
  1. identifiy a pop for which there is past assessment of smoking
  2. ascertain smoking based on past records
  3. identify who has developed lung cancer
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

Strengths/weaknesses of retrospective cohort

A

strengths: faster and cheaper than prospective
weaknesses: follow up difficult, med hisotries don’t always exist, accuracy of exposure assessment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
35
Q

Combined prospective and retrospective cohort studies steps

A

enroll patients who’ve gone to same clinic for 10 years for some reason other than cancer
1. look at med records to see if they smoked previously
2. continue to assess smoking
3. follow into future to see if they develop lung cancer

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
36
Q

Association exists if…

A

outcomes are coorelated with exposure: a difference in exposure is associated with a difference in outcomes

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
37
Q

Absolute difference vs relative difference

A

absolute: this much hihger
relative: this % higher

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
38
Q

Relative risk

A

proportion who develop disease among exposed/proportion who develop disease among unexposed

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
39
Q

Incidence rate ratio

A

of cases of disease per person-year among expose / # of cases of disease per person year among unexposed
IRR should be used when participants in study for varying amounts of time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
40
Q

Interpret relative risk:

A

> 1 = means exposure associated with greater risk of outcome. RR=1.6, risk of outcome is 60% greater among exposed than not
<1 = exposure is associated with reduced risk of outcome. RR=.6, risk of outcome 40% less among exposed than not
Equal to 1= no association, same proportion developed outcome

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
41
Q

bias

A

systematic errors in design and analysis skewing observed RR away from true

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
42
Q

Common biases in cohort studies

A

bias in assessing outcomes (preconcieved notions) - blind assessor to exposure
Info bias - two groups have systematic differences in data available
non-response/LFU
analytic bias
selection bias - exposed grouop may come from different pop. than non-exposed group
confounding - other fundamental differences between exposure gorups

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
43
Q

Hypothesis testing: how do we decide whether to conclude H0 from a 1 pt difference from testing

A

Through P-value: probability of observing an association if null is trye
We reject the null if p value is sufficiently low

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
44
Q

Then problem witht he p value

A

P value tells us probability of observing dta if H0 is true (assuming no other sources of error). But we actually want probability H0 is true if we observe out data.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
45
Q

3 options of what to do with p-vaue alternatly

A
  1. Interpret P(D/H0) as if it is the P(H0/D) we want. BAD OPTION
  2. Use bayesian appraoches, estimating likelihood of H0 and Ha before data collection
  3. Use p values more informally as one inductive tool among others (disclaims that hypothesis testing is fully deductive)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
46
Q

Deducitive vs inductive

A

Inductive reasoning involves starting from specific premises and forming a general conclusion, while deductive reasoning involves using general premises to form a specific conclusion

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
47
Q

Concluding that there is a difference between treatment groups (choosing H over Ho) does not mean

A

that pop. difference = observed difference

Rather it means that if we were to reassign treatment vs control over and over, 95% of CIs would include the true pop. association (if only random change in assignment is at play)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
48
Q

A 95% CI interval not including H0 will have a p-value less than

A

.05

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
49
Q

Clinical significance

A

With large enough samples, very small associations can still be statistically signifcaint, but difference may not be large enough to matter

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
50
Q

basic design of case control sudy

A

start by identifying people w disease and those without (cases and controls)
Work backwards to determine past exposure
If exposure is associated w/disease, we expect exposure to more common among cases than controls

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
51
Q

Selection of cases for case-control

A

Often want prevalent cases (or can use people as cases as they diagnosed)
Prevalent cases are often easier to idenitfy, but using incident cases reduces biases
prevalent case - factors/exposures associted with being a cause might actually be associated with development of disease or survival

SURVIVAL BIAS IMPORTANT FOR CASE CONTROL

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
52
Q

Where do case control cases come from?

A
  1. particular medical institution (can be problematic because hospitalized cases may be poorly representative, isntitiions often serve particular sub-pops. of society)
  2. critical to use a precise case defintiion
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
53
Q

Selection of controls

A

Must be from same pop. as cases (or similar). If controls and cases come from different ref. pops., an exposure that appears associate with diseease may just be associate with pop.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
54
Q

Selection bias exists in case control studies esepcially, but is also a major threat for

A

cohort studies
we want exposed and unexposed grouop to be comparable with respect to causes of outcome of interest other than exposure of interest

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
55
Q

Sources of controls

A

Hospital: similar to cases/good quality of info, but controls may be from a differenet reference pop. than cases and sick controls may have particular exposure contributing to illnesses
Dead controls
Best friend/neighbor
Pop. controls

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
56
Q

Matching importance

A

critical to have cases and controls as similar as possible on other characteristics
matching addresses this by selecting controls identical on relevant charactertistics like cases

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
57
Q

Group vs individual amtching

A

group - if 25% of cases are male, select control so that 25% are also male. requires cases are identiifed before controls can be selected
Individual matching - controlling for relevant characterstics like age, sex, race, can be difficult to do

Inadvertant matching/accidental matching

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
58
Q

Strengths/weaknesses of amtching

A

strengths: easy to do, some factors must be amtched
weaknesses: matching on multiple factors may be impossible
can decrease extent to whichs tudy pop. represent pop as a whole
matching cannot be undone

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
59
Q

Recall Errors

A

People may incorrectly
remember whether they were
exposed to something.
* Especially when the exposure is
subtle or long ago.
* Inaccurate recall can result in
random error.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
60
Q

Recall Bias

A

If accuracy of recall is associated with outcome or another potentially causative facot,r can create a false association

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
61
Q

Rumination bias

A

For example, patients with cancer often seek a cause for the
disease and may spend much more time thinking about past
exposures than health controls. What appears to be an
association with cancer may be merely an association with
recall
can address by asking about non-associate exposure s to see if thhey are more frequent among cases than controls

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
62
Q

Multiple controls

A

Increases statistical power, can gain more info or assess quality of a control group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
63
Q

Strengths/weaknesses of case-control studies

A

strengths: cheap, fst, can examine multiple potench exposure, better for rare diseases
Weaknesses: frequently cannot determine conclusively that exposure predated illness, esposure may be associated with survival and not incidence, susceptiblet o inaccurate recall, comparison groups harder to find

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
64
Q

Measure of association for case control

A

odd ratios

could use relative prevalence of exposure, but doesn’t work well if you want to control for multiple confounding variables

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
65
Q

odds ratios can

A

approximates relative risk under rarirty condition. can be used for cohort, but relative risk preferred for ease of interetation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
66
Q

Odds are a way of assessing

A

likelihood of an outcome to likelihood of that outcome not occurring

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
67
Q

odds ratio of exposure

A

odds of exposure among cases divided by odds of exposure among control (uased in case-control)
OR of disease is algebraically equal to the OR of exposure

68
Q

odds ratio calculate

A

ad/bc
if it goes
ab
cd

69
Q

Interpreting odds ratio

A

> 1 = exposure associated w more disease
<1 = exposure associated w less disease
equal to 1 = no association between disease and exposure

70
Q

odds ratios can bea. good estimate of relative risk/relative prevalence if

A
  1. cases are representative of all ppl with disease in pop
  2. control are representative
  3. disease being studied doesn’t occur frequently among people who are either exposed or not
71
Q

Unless we are carefully using incident cases or can excluse survivor bias, an odds ratio still only approximates

A

relative prevalence, not a relative risk

72
Q

Odds raito with amtched pairs

A

We can’t learn anything from pairs that are both exposed or unexposed. ratio is b/c

73
Q

cross sectional studies are usually absolute ______ studies

A

prevalence

74
Q

Two steps for cross-secitonal study

A
  1. identify pop. to study
  2. simultatenously identify both present exposure and present disease status
75
Q

Disadvantages of cross-sectional study

A

Survivor bias
impossible (often) to know if exposure preceded outcome

76
Q

Advantages of cross-sectional studies

A

if well-designed, can be pop.representatntive (rare for case control and cohort)
repeated cross-sections can gain info about changes in pop.level ooutcomes related to an exposure in some instance

77
Q

Causal inference relies on

A

theory

78
Q

Measures of association for cross sectional

A

Odds ratios are the tradition, but can easily use a relative prevalence or difference in prevalence

79
Q

Surgeon general guidelines for causality

A

Temporal relationship
Strength of association
dose-response relationshion
replication of findings
biologic plausibility
consideration of alternate explanation
cessation of exposure
knowledge consistency

80
Q

most common ways to measure strength of association

A

relative risk, odds ratio, risk difference

81
Q
  1. temporality
A

one approach to falsifying. causal claim is to see if ssociatin exists at a time point when it should not

82
Q
  1. strenght of association
A

how closely correlated are cause and effect.
strong association guards against confounding or bias, but sometimes large effects are due to bias or confounding. and well-executed studies can still identify causal small effects

83
Q
  1. dose-response relationship
A

Increasing disease as exposure increases (strong evidence of causality, although absence doesn’t imply none)

84
Q

Replication of findings

A

will the causal relationship be consistently found

85
Q

Plausibility

A

findings should be reliable knowing the biology of the disease

86
Q

Consideration of alternate explanations

A

rule out plausible competing hypotheses, including confounding and bias
studies not considering alternate explanations usually bad

87
Q

Cessation fo exposure

A

one would expect to see cessationf of exposure lead to reduced disease

88
Q

Consistency with other knowledge

A

what it sounds like

89
Q

specificity of association

A

Not a particularly persuasive criterion.
* Some argue that a particular exposure should be
associated with a particular disease only, and vice
versa—otherwise it may be a signal of confounding.

90
Q

Coufounding variable 3 characteristics

A
  1. causes outcome of interest
  2. associated w exposure of interest
  3. Is not in thd direct causal pathway between exposure of interest and the outcome
91
Q

An association you observe due to confounding is a real association, but not a causal one. It isn’t

A

spurious

92
Q

How to address confoudning

A
  1. study design (matching/randomization)
  2. Analysis (stratification and adjustment0
  3. Only randomization can remove the effect of an unknown confounder
93
Q

How does stratification work for confounding variables?

A

When we stratify, we examine the association between our exposure and outcome at each value of a confounder (age adjustmne,t smokers v nonsmokers)

94
Q

What is adjustment?

A

Technique by which stratified results are recombined to eliminate the effect of the confounding variable. create a weighted average across strata of a confounder

95
Q

Two major types of bias

A

Selection
Information

96
Q

Seleciton bias

A

occurs when there is a systematic error in selection of study participants distorting the observed association between exposure and outcome

Occurs when selections predispose to an association

97
Q

Selection bias often occurs when

A

populations chosen are fundamentally different (primarily a problem with case-control studies)

98
Q

Nonresponse bias

A

In many studies, grouops with particular illnesses or exposures may be more likely to participate. in cohort studies, different exposure groups may have differnent rates of LTFU

99
Q

Information bias

A

Occurs when means of collecting info about subjects is inadequate, resulting in incorrect info about exposures or outcomes

100
Q

Recall bias

A

participants inaccurately remember past exposures

101
Q

rumination bias

A

ill people spend more time thinking about potench exposures than health people (a type of recall bias)

102
Q

reporting bias

A

one group may be less likely to report exposures because of attitudes or beliefs

103
Q

wish bias

A

participants seek affirmation that disease was not their fault

104
Q

interviewer bias

A

person ascertaining exposure may questions more carefully cases than controls

105
Q

bias in exposure identification typesr

A

recall bias
rumination bias
reporting bias
wish bias
interviewer bias

106
Q

bias in outcome ID

A

observer bias - classifying exposed as cases more often than non-exposed
respondent bias - participants errs in whether they have disease
detection bias - certain exposures result in more common med visits - better detection
incidence/prevalence bias (survivor) - use of prevalent cases as an outcome may result in associations that increase survivial, not development
temporal bias - factor appearing to cause disease may actually result from it
lead time bias - participnts in a screening study may have just caught the disease earlier

107
Q

Most bias cannot be addressed in analysis

A

Thus must be addressed in study design

108
Q

Why not always draw SRSs?

A

Require a listing of all units
samples units
Could result in subgroup samples too small to say anything useful/miss groups entirely
Logistically inefficient

109
Q

How to ensure a min sample of subgroup emembers or ensure you don’t miss some subgroup by cahnce?

A

stratify by subgroups

110
Q

How does stratifying impact estimates prescision

A

makes them more precise

111
Q

To reduce the risk of a bad sample drawn by change…

A

random sample proportional to strata sizes (making sure you have populations that don’t overlap)

112
Q

Benefits of stratifying

A

Make sure that characteritsics are represented in the sample at the same fraction as in the pop.
Doesn’t require sampling weights
Might get small improvement in statistical precision

113
Q

If we were to take an SRS of 100 within each stratum (with different pops)…

A

our sample estimate may be biased

114
Q

How do we reduce bias in a stratified sample?

A

Re-weight the samples so that each observation is multiplied by the number of units its represents in the populations

115
Q

What is the point of weighting data?

A

Accounts for unequal chances of selection (so when observations represent an unequal number of people in the pop.)

116
Q

Failing to correctly weight your data will cause the point estimates to be wrong (and probably the SE too)

A

Remember

117
Q

Stratification that self weights (proportional to strata size) affects precision how

A

alsmost never harms

118
Q

Stratification to overssample some subpops affects precision how?

A

harms overall precision

119
Q

Why does stratification to oversample some subpops harm overall precision?

A

You gain some precision within the smallest stratum, but lose overall precision because a larger part of the estimate is dtermined by a smaller part of the sample under the SRS

120
Q

What are the best characteristics on which to straitfy?

A

ones that explain as much variation in our outcome of interest as possible. We get max reduction in variance when stratification results in units that are essentially the same within strata and strata are quite different from one another

121
Q

PSUs and SSUs

A

primary sampling units (clusters)
secondary selection units

122
Q

Cluster sampling

A

Often only feasible approach
Reduces logistics and time
allows you to sample without needing a listing of everyone eligible for sampling

123
Q

downsides to cluster sampling

A

If very different from one another and members are very similar within each community, sample has much worse statistical precision than SRS of same size

124
Q

Draw a self-weighting possible when possible!!! where all particpants have an equal probability of selection. give examples:

A

simple/systematic random samples
stratified samples with strata sample proporiton to their size in the pop

125
Q

All things being equal, weighting will

A

cause a loss of precision
and complicate analysis

126
Q

2 options for self-weighting cluster samples

A
  1. Draw SRS of clusters and then a constant % of units within each cluster
  2. Draw a sample of clusters where likelihood of selection is proportional to size of the cluster. Then draw a constant number of unis within each cluster (AKA PPS: probability proportionate to size)
127
Q

Cluster sampling is unbiased…

A

but less precise

128
Q

Why do we lose precision?

A

Depends on how different your clusters are from each other/how many there are/how homogenous they are inside

129
Q

What improves precision

A

stratificatoin
sampling high fraction of pop. effect negligible unless sampling more than 20%

130
Q

Worsens precision

A

cluster sampling
relatively small number of clusters
weighting - especially when weights vary substantially
unequal cluster sizes
disproportionate sampling across strata

131
Q

Basic model of response

A

comprehension
retrieval
judgement/estimation
reporting

132
Q

comprehension

A

do people understand the survey instructions and the specific item

133
Q

retrieval

A

how do people recall info from long term mem

134
Q

estimation and judgment

A

converting recalled occurrences/beliefs into an estimate/assessment that can be an answer

135
Q

reporting

A

selecting a communicating an answer

136
Q

problems of encoding

A
  1. people often don’t encode all occurrences
  2. surveyors usually cannot affect encoding
  3. you can sometimes provide cues
137
Q

Why does misinterpreting Qs occur?

A

grammar
complexity
vagueness
unfamiliar terms

138
Q

Reducing vagueness often increases…

A

complexity

139
Q

To know what a Q means to respondents

A

use cognitive interviewing to understand what a question means to respondents
adapt/borrow questions that have been fully validated
another language won’t always apply

140
Q

Memory problems

A

we incoporate subsequent info, older events/blank spaces tend to be answered as a generic event
how much time has passed is faulty

141
Q

Judgement influenced by waht 3 things

A

wording
context (framing)
Placement (framing)

142
Q

tradeoffs

A

open-ended vs closed questions
with ordinal scales -label every point
for numerical scale - center around expected average, make equal categories

143
Q

When do respondents tend to be less likely to answer correctly?

A

when disclosing something illegal or risky
when perceiving that the surveyor or one’s peers expect a favored answer

144
Q

Guidelines for sensitive questions

A
  1. Have survey be self-administered whenever possible
  2. Open questions for frequency or behavior rather than closed
  3. Use familiar terminology
  4. Longer questions to for more time to recall and retrieval
  5. Deliberately load the question
  6. position sensitive questions after participants have answered others
  7. ask about sensitive behaviors from the past
  8. diary
  9. assess sensitivity of items by asking questions
  10. validate data
145
Q

Social desirability bias

A

Presence of Interviewer can induce
observable traits can change willingness to report attitudes related to trait

146
Q

Logic Models / Logical Frameworks 1

A

Inputs
Activities
Outputs
Short-term outcomes
Long-term outcomes

147
Q

Another logic model

A

structures
processes
outcomes

148
Q

Indicators

A

Can wrap around each step in logic model
Monitor points where program most likely to break down
Assess end of cascade

148
Q

Process evaluation

A

seeing if program is producing what it’s meant to and operating reasonably well in accordance with logic model theory

149
Q

When measuring programs impact, ideally want to run RCT.. but

A

unethical
politicall untenable
complicated

150
Q

Differences between traditional research adn eval

A

Research: starts with a hypothesis and is fairly unconstrained as to research design
Evaluation: starts with what is believed to be best implementation approach under circumstances

151
Q

The fundamental challenge of both traditional research and eval

A

assessing differences compared to an unobservable counterfactual

152
Q

Difference in analytics/data collection between research and eval

A

analyticl tools often the same
data collection is usually for routine program purposes so quality usually poorer than for reserach
sample size not determined ahead of time, power can be a challenge
program intervention can chnge over time
can’t really blind evaluators
randomization impossible

153
Q

4 general approaches for outcome evals

A
  1. Only sample is program recipients after program has commenced
  2. Only have program recipients but under varying program conditions
  3. Can sample non-recipients and recipients, but only after the program
  4. can sample non-recipients and recipients, both before and after program
154
Q
  1. Post implementation Program Recipients only
A

challenging for good outcome eval because no approximation of counterfactural

Solutions
Compare to objective outcome becnhmakrs
qualitative investgation of recipient’s perceptions of program

155
Q

2.Only program recipients under diff. program conditions

A

You don’t have data from people who didn’t recieve program, but do have data from before, after, or different versions

156
Q

Options for when you have only program recipients under different program conditions

A
  1. before after designs
  2. placebo outcomes
  3. ITS
157
Q

Before after studies

A

if data existed on outcomes from before an intervention, can be compared to outcmes after intervention
(biases include info bias, selection bias, confounding by time, confounding by other elements of a program)

158
Q

Interrupted time series

A

need measurement at lots of time points before and after the intervention/change
lets you assess/exclude histoircal trends that might cause misinterpretation in a simple before-after
you would know about simultaneous other big changes

159
Q

Major challenge for before-after design

A

may be confounded by simultaenous changes or selection problems

160
Q

Isolate effect of intervention by comparing improvements in target pop between…

A

outcomes the evidence base/theory suggests should result from intervention
outcomes that should not result from intervention but are subject to same confounding or bias

161
Q
  1. Non-recipients also, but only at follow up
A

Counterfactual supported by comparable participants who do not recieve program
challenge is ensuring pops. are comparable on dimensions other than receipt of the program
basically cross-sectional studies where exposure is your program

162
Q
  1. Combining control groups with before-after measurement
A

measuring before-to-after changes in an intervention group compared to comparison produces better counterfactual estimates. would only worry about time-based confounding

163
Q

Common eval strategies for combining control groups w/before-after measurement

A

difference-in-differences
interrupted time series with comparison group
step-wedge

164
Q

Difference in differences

A

Repeated cross sections among receipeints and non

use before-to-after change among comparable non-recipients to rep what you would have seen among recipients without intervention

165
Q

What can D-I-D be potench confounded by

A

different pre treatment trends
simultaneous interventions
changes in pop. over time

166
Q

Step wedge designs

A

Extension of DID

implement same program in diff locations over time

evaluate for similar trends over time, with an improvement in outcomes at the time of implementation

should see improvements over time as you finetune your methods

USPS Midterm 1 (4 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2025 Bold Learning Solutions. Terms and Conditions