Quantitative Study Design Flashcards

1
Q

Sampling/selection bias

A

sample does not represent population of interest (may colllect more extreme views)

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

Recall bias

A

inaccurate recall of past events/exposures/behaviours

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

Information bias

A

incorrect measurement eg miscalibrated machine

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

The Hawthorne effect

A

participants change their behaviour when they know they are being observed

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

Attrition bias

A

differential dropout from studies eg sicker participants drop out so our outcome is only measured on healthier participants

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

Experimental study design

A

researchers have intervened in some way (prospective)

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

Observational study design

A

the researchers have not intervened, merely observed. Can be:
• retrospective- looking back into the past
• Cross-sectional- a single snapshot of time
• Prospective- following up over time

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

Types of data

A

• categorical variables: binary, ordinal, nominal
• numeric variables: discrete, continuous

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

Binary

A

Only 2 categories

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

Ordinal

A

categories with natural order eg stage of cancer

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Nominal

A

categories with no natural order eg blood group, ethnicity

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

Discrete

A

observations can only take certain numerical values eg number of children

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

Continuous

A

observations can take any value within a range eg age, body temperature
Restriction is precision of measurement tool

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

Proportion

A
  • the number with a characteristic or outcome divided by the total number. Used to describe the probability or risk (scale 0 to 1)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Risk

A

probability of event occurring - probably occurring divided by total

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

Odds

A

the number with an exposure or outcome divided by the number without. The ratio of the probability of an event occurring to the probability of it not occurring- occurring divided by not occurring

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

Rate

A

incidence of health-related events or outcomes. Allows account for variation if follow-up time or time at risk of an outcome

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

Risk difference

A

absolute risk difference (subtraction)- no difference = 0

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

Risk ratio

A

relative risk- risk in one group divided by the risk in the other

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

Ratios

A

No difference = 1
Ratios > 1 indicate higher risk/odds in group of interest
Ratios < 1 indicate lower risk/odds in group of interest

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

Numbers needed to treat (NNT)

A

1 divided by absolute risk difference
• always round up- has to be a whole number

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

Prevalence

A

number of existing cases in a population at a defined time point

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

Incidence

A

number of new cases in a population over a defined time period

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

PICO framework

A

• Intervention studies: PICO
• Observational studies: PECO → ‘exposure’ rather than ‘intervention’
• Non-comparative studies (e.g. in qualitative research): PEO
• Example research question framed using PICO:
Population
In middle-aged women (>40 years old) with raised cholesterol (>5 mmol/L)
Intervention
…does new statin x
Comparator
…compared to current statin y
Outcome
…provide greater reduction in cholesterol?
(Ideally with clinically meaningful reduction in cholesterol defined)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
9 Bradford Hill criteria
1. Strength of association – the stronger an association, the more likely it is to be causal 2. Consistency – association shown across different studies in different locations, populations, using different methods, etc. 3. Specificity – specific exposure-outcome relationship, e.g. asbestos and asbestosis 4. Temporality – exposure must precede outcome 5. Biological gradient – dose-response, i.e. increase in exposure = increase in outcome 6. Plausibility – biological mechanism that would explain outcome development 7. Coherence – compatible with existing theories 8. Experiment – outcome altered with experimentation, e.g. reversible 9. Analogy – similar cause-effect relationships established
26
When designing studies must consider
• Ethics: are the rights, safety and wellbeing of participants protected? • Feasibility: will it give the best quality evidence given our resources (time, money, personnel, etc.)? • Efficiency: is there a faster/cheaper way to address the question without compromising quality?
27
Which type of study can only use odds ratio
Case-control study
28
Absolute risk
Probability of event within time period
29
Relative risk
Probability of event relative to exposure
30
Proportion
Outcome/ total number Scale : 0-1
31
Odds
Outcome with exposure/ outcome without exposure Probability / (1-probability)
32
Odds ratio
Odds that case was exposed/ odds that control was exposed
33
Ratio >1
Higher risk
34
Ratio <1
Lower risk
35
Risk ratio/ relative risk
Disease incidence in exposed/ disease incidence in non-exposed
36
NNT (numbers needed to treat)
1/ |relative difference| Number needed to take drug for one success
37
NNH (number needed to harm)
1/|relative difference| Number needed to take drug for one adverse effect
38
Parametric
Make distributional assumptions
39
95% reference range
Mean +/- 1.96*SD
40
What percentage of values lie within 1SD of the mean
68%
41
What percentage of values lie within 2SD of the mean
95%
42
What percentage of values lie within 3SD of the mean
99.7%
43
What is the y axis height of normal distribution determined by
SD variation
44
What is the x axis location of a normal distribution determined by
Mean
45
Normal distribution
Bell-shaped curve Mean = median = mode Report mean +/- 2 SD
46
Negative skewed distribution
Skewed negative (left): median> mean left skewed distribution: same mean but median is higher
47
Positively skewed distribution
right skewed distribution: same mean but median is lower Mean > median
48
Skewed distribution
Report median and interquartile range (centiles)
49
Meta-analysis
Combining systematic reviews to address a question
50
Ecological fallacy
Can’t make individual-level inference
51
What does PICO stand for
Patient Intervention Control Outcome
52
Systematic sampling
Selected at equal intervals
53
Advantages and disadvantages of systematic sampling
+ve - easy -ve - need list, large standard error, periodicity pattern
54
Random sampling
Sampling error can be managed
55
Cluster random sampling
Cluster population then sample whole clusters
56
Advantages and disadvantages of cluster sampling
+ve - list not needed, cheap -ve - increases standard error
57
Simple random sampling
Computer generated numbers
58
Advantages and disadvantages of simple sampling
+ve - easy, quick -ve - poor representation of minorities, bigger standard error than stratified
59
Stratified random sampling
Samples taken from each group
60
Advantages and disadvantages of stratified sampling
+ves - increases representation, decreases standard error -ves - expensive, require prior population info
61
Types of random sampling
Systematic Cluster Simple Stratified
62
Advantages and disadvantages of Non random sampling
+ve - convenient -ve - sampling error can’t be measured, high potential for bias
63
What is bias affected by
Sample size NOT population size
64
Observer bias
Researcher
65
Confounding variables
Relate to exposure and outcome but not on causal pathway or with intervening variable
66
Preventing confounding
Randomisation: generates comparable groups Restriction: eliminates variation in confounders eg only recruiting females Matching: control group matches confounders in case group
67
What is the Most appropriate study design to investigate an infectious outbreak
Case-control study