Brainscape's Knowledge GenomeTM

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


See full index

PUBH192 > lectures 11-23 > Flashcards

lectures 11-23 Flashcards

1
Q

what is randomisation and what does it achieve

A

randomly splitting participants into groups. Eliminates confounding because known and unknown confounders should be balanced

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

cluster randomisation

A

randomise groups (clusters) of participants instead of individuals, which may be difficult. E.g. GP practices, hospital wards

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

stratified (block) randomisation

A

If you want to be certain that important confounders are eliminated. Randomise individuals within each age group, sex, or hospital

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

cross over studies

A

Each person gets both treatments -confounding is effectively eliminated. Can only be done for long-term conditions and treatments that do not cure disease

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

protecting randomisation

A
  • concealment of allocation - Make sure that people can’t cheat and pick the treatment that they prefer
  • intention-to-treat analysis - Analyse participants as randomised, this reflects real world
  • blinding - of researchers and participants
  • complete follow-up
  • use large numbers - balance confounding
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

per-protocol analysis

A

Analyse as treated (not necessarily as randomised)

Lose the benefit of randomisation

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

potential sources of bias

A
  • lack of blinding - participants or researchers may act differently if they know the groups
  • loss to follow up - cant analyse their results
  • non-adherence - e.g. stop taking treatment
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

4 strengths of RCTs

A
  1. The best study design to test an intervention
  2. Well conducted studies should eliminate confounding and bias
  3. You can calculate Incidence, Relative Risks, and Risk Differences
  4. The strongest design for testing cause-and-effect associations
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

clinical equipoise

A

must have genuine uncertainty about benefit or harm of intervention in RCTs

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

practical issues of RCTs

A
  1. can be expensive - need many participants, long time
  2. often funded by pharmaceutical companies - unlikely to fund studies for cheap treatments
  3. Participants in RCTs are often not representative - They need to meet all the inclusion criteria
  4. RCTs are not efficient for rare outcomes
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

internal validity

A

whether or not there is a real association in the group you looked at, or if its due to chance, bias or confounding

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

external validity

A

can findings be generalised to broader population

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

effect of increasing sample size in random sample

A
  • Makes it more likely to represent sample
  • Reduces sample variability (standard deviation etc)
  • Increases precision of parameter estimate - Confidence intervals get narrower
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

2 interpretations of confidence intervals

A
  • A 95% Confidence Interval represents the range of values within which the parameter will lie between 95% of the time if we continue to repeat the study with new samples
  • 95% CI = We are 95% confident that the true population value lies between the limits of the confidence interval
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

what does it mean if 0 in included in a CI for difference between two means

A

result could be due to chance

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

null hypothesis

A

There is no association between exposure and outcome

There is no difference between groups

Parameter equals null value

if this is true, any differences must be due to chance

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

alternative hypothesis

A

There is an association between exposure and outcome

Parameter does not equal null value

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

p value

A

The probability of getting an estimate as extreme as the one that you have observed if there is really no association

i.e. probability of it occurring by chance

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

statistically significant p value

A

P values < 0.05

Less than 5% probability of a result this extreme due to chance

We can reject the null hypothesis and accept alternative hypothesis

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

not statistically significant

A

if P value > 0.05

More than 5% probability of this result occurring by chance

We cannot reject the null hypothesis

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

type I error

A

false positive

occurs when we find a “statistically significant” result when there is no real difference

we reject H0 even though it is correct and the difference is due to chance

P(type I error) = alpha (significant level - usually 0.05)

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

type II errors

A

false negative

occurs when we don’t find a “statistically significant” result when there is a real difference

we fail to reject H0 even though it is false and the difference is real

More likely if we use smaller samples

Also more likely if we look for a smaller P value (e.g. ≤ 0.01)

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

clinical importance

A

if it will have a substantial effect/make a decent difference that makes it work funding

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

selection bias in case-control studies

A

Controls not representative of the population which gave rise to cases

If inclusion/exclusion criteria differ between cases and controls

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

selection bias in cohort studies

A

Loss to follow up

If comparison group selected separately from exposed group can lead to bias - healthy worker effect

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

how can measurement error occur

A

Participants provide inaccurate responses

Data is collected incorrectly/inaccurately

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

effect of measurement error

A

in a descriptive study could over/underestimate prevalence

In an analytic study can lead to misclassification

28
Q

non-differential misclassification

A

When measurement error and any resulting misclassification occur equally in all groups being compared

29
Q

differential misclassification in cross-sectional study

A

people with the outcome might report the exposure differently to those without the outcome

30
Q

differential misclassification in a case-control study

A

cases might more accurately recall past exposures compared to controls

31
Q

differential misclassification in a cohort study

A

interviewer aware of the exposure status may ask more probing questions about the outcome among those exposed compared with those in the comparison group - this is known as interviewer bias

32
Q

minimising interviewer bias

A

Clearly defined study protocol and measures

Blinding

Training of interviewers

Structured questionnaire and standard prompts

33
Q

recall bias in case-control studies

A

Cases would have had much more time actively thinking about their exposure than controls

If investigating effect of living by powerlines growing up on brain cancer, cases would be more aware of exposure status because they would have thought about it

34
Q

minimising recall bias

A

objective measures

memory aids

35
Q

what is confounding

A

A mixing or muddling of effects when the relationship we are interested in is confused by the effect of something else

36
Q

confounders are: (3 things)

A
  1. associated with the exposure
  2. associated with the outcome (independent of exposure)
  3. not on the causal pathway
37
Q

potential effects of confounding

A
  1. Reverse an association (“Simpson’s paradox”)
  2. Underestimate an association
  3. Overestimate an association
38
Q

identifying confounding

A

Look at the associations before and after adjustment or stratification

If these are very different (i.e. more than 10% different), the factor was probably a confounder

39
Q

common confounders

A

age, sex, socioeconomic status, lifestyle factors

40
Q

minimising confounding

A

randomisation

restriction

matching

41
Q

what is matching and advantages and disadvantages

A

Individual matching: match each case to one (or more) controls

Frequency matching: select controls to match age & sex distribution of cases i.e. same proportions

advantages:

  • Good way to control for confounders – Can select multiple controls for each case

disadvantages:

  • Individual matching for multiple confounders can be difficult
  • Finding appropriate controls can be difficult
  • It is possible to over-match: can miss a true association if controls are so similar that they share the same risk factors
42
Q

what is restriction and disadvantages

A

Only include one group (stratum) of potential confounder e.g. only use men older than 35 for sample population

disadvantages:

  • It is only practical to restrict for 1 or 2 known confounders
  • Reduces generalisability to other groups
  • Reduces number of potential participants
43
Q

controlling confounding at an anaylsis level

A
  1. standardisation
  2. stratification
  3. multivariable analysis
44
Q

what is stratification and disadvantages

A

Analyse in groups (“strata”) of potential confounders

disadvantages:

  • Smaller numbers in each stratum
  • Can usually only stratify on one (maybe 2) confounders
45
Q

what is standardisation and disadvantages

A

Age standardisation: removes age as a confounder when age structure differ

Sometimes standardise for other confounders

disadvantages:

  • Less suitable for multiple confounders
  • Multivariable analysis is often more efficient
46
Q

what is multivariable analysis and pros and cons

A

Mathematically adjust the analyses for multiple confounders

Provides “adjusted” measures of association

advantages:

  • Greater sample size (more power) than stratifying into groups
  • Can adjust for several confounders at the same time
  • Easy to do with statistical software

disadvantages:

  • Not always obvious what the data look like
  • Unlike stratification, you may not detect effect modification
47
Q

what is effect modification

A

A 3rd factor modifies the association between exposure and outcome. This factor is on the causal pathway

48
Q

identifying effect modification

A
  1. Stratify the findings
  2. Associations in each group are very different –probably effect modification
  3. Similar associations each group –no effect modification (but there could still be confounding)
49
Q

necessary cause

A

component cause which is necessary for disease to occur

Must be part be part of every sufficient cause (if there are multiple)

50
Q

guidelines to judge whether association means causation

A
  1. Biological plausibility
  2. Experimental evidence
  3. Specificity
  4. Temporal sequencing (exposure must come before outcome)
  5. Consistency
  6. Dose-response relationship (risk of developing disease increases as dose of exposure increases)
  7. Strength of association
51
Q

efficacy trial

A

Analyse the individuals as they are actually treated- not the with intention to treat

52
Q

when carrying out randomisation

A

Equal chance of being in any group
Limit selection bias
Equal distribution of patient characteristics
Same proportion of confounders

53
Q

factors to consider about research ethics

A
  1. balancing benefits and harms
  2. protecting potentially vulnerable groups
  3. conflict of interest
  4. informed consent
  5. justice (being fair)
54
Q

balancing benefits and harms

A

clinical equipoise

Awareness of various costs or harms to participants and strategies to address these harms or costs

Evidence of scientific validity of the research

55
Q

protecting potentially vulnerable groups

A

someone who is more at risk of exploitation because of social or physical disadvantage

  • e.g. poorer people
  • Those subject to racial pr religious discrimination
  • Those who are less educated
  • Those suffering cognitive impairment
  • Older people
  • Prisoners
  • Children
56
Q

conflict of interest

A

Situation where a person holds two or more potentially incompatible interests, which might compromise values of research

Can be managed by peer review, blinding, auditing

57
Q

informed consent

A

Disclosure of purpose, risks and processes of study

Reasonable efforts from researcher to explain this info

That the person is competent to give consent

Absence of coercive factors

Must be in writing

58
Q

critical appraisal

A

the process of evaluating research in the best way

59
Q

systematic review

A

a way of putting a heap of different studies together and then analysing them to answer a question

60
Q

advantages of systematic review

A

Reproducibility

Comprehensive

Transparent limits

Gaps in knowledge

Basis for decisions

61
Q

challenges of systematic review

A

Doing all steps well

Publication bias

Heterogeneity

Poor quality trials

Conflicting reviews

Inconclusive results

62
Q
A
63
Q

steps of stratification

A
  1. calculate crude MoA between exposure and outcome
  2. divide data by level of suspected confounder (done for us)
  3. calculate MoA between exposure and outcome for each stratum
64
Q

if stratum specific values are all similar to each other and to the crude value:

A

no evidence of confounding

65
Q

stratum specific values are all similar to each other but different from crude value:

A

evidence of confounding

66
Q

stratum specific values are different from each other

A

effect modification

67
Q

looking for confounding in multivariable analysis

A

compare OR for unadjusted and adjusted data

if they are similar then no confounding

if they are different then confounding

PUBH192 (3 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions