Brainscape's Knowledge GenomeTM

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


See full index

LMAP-2 > Designing epidemiological studies [Epidemiology] > Flashcards

Designing epidemiological studies [Epidemiology] Flashcards

1
Q

What type of epidemiological study…
- Involves hypothesis testing and the use of statistical tests
- Identifies the impact of interventions or specific exposures
- Typically used more in research settings

A

analytical epidemiology

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

What type of epidemiological study…
- is typically used more in public health practice
- typically provides estimates of morbidity such as prevalence or incidence rate

A

Descriptive epidemiology

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

In 2 words, what do analytic epidemiology studies do?

A

test hypotheses

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

In 3 words, what do descriptive epidemiology studies do?

A

describes a problem

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

What type of descriptive study is this:

  • a short write up of findings (usually unusual)
  • often used to communicate new diseases, presentations or findings
A

case reports

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

What type of descriptive study is this:

  • collection of case reports
A

case series

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

What type of descriptive study is this:
- describes prevalence or incidence of an exposure or outcome over time
- measuring something over time
- aggregated data (2+ cross-sectional analysis)
- person-level data (follow up on same participants)

A

longitudinal

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

What type of descriptive study is this: (can employ analytic studies)

  • typically describes the prevalence of a condition at a single point in time
  • provides a snapshot view
  • surveys!! → descriptive purposes, not discovering causal relationships
  • prevalence measures may be an outcome, exposure or both
A

cross-sectional
(can employ analytic)

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

What type of descriptive study is this: (can employ analytic studies)

  • focuses on comparison of groups, does not require data from individuals
  • analyse only aggregate linked data
  • (ie countries, communities, ethnicities, school, work site, occupation, time interval)
  • cross sectional or longitudinal
A

ecological
(can employ analytic)

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

Name some pros and cons of a cross-sectional study

A

pros:
- tests exposure and outcome at the same time
- can measure prevalence
- cheap, easy to conduct

cons:
- lacks follow-up so risk or temporal relationships cannot be easily determined
- can’t measure incidence or risk

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

Name some pros and cons of an ecological study.

A

pros:
- hypothesis generation
- use secondary data
- level of interest is at population anyway
- suitable when variability in group is limited

con:
- subject to ecological fallacy
- relies on secondary data collected for different purposes
- unclear if exposure preceded outcome

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

What is the term used to describe the following:

assuming that association between groups holds for individuals

A

ecological fallacy / aggregation bias

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

What term is used to describe the following:

fixed value, derived from a sample that estimates the value in a population

A

statistics

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

What term is used to describe the following:

fixed value, often unknown value, describes an entire population

A

parameters

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

What term is used to describe the following:

a statistic that aims to estimate the parameter

A

point estimate

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

What term is used to describe the following:

describe range of values in which we are 95% confident that the true value lies

A

confidence intervals

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

What do we call data collected by the researcher first-hand?

A

primary data

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

What do we call data that has been collected for another purpose – and then potentially ‘recycled’ for a different purpose

A

secondary data

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

Name some and cons of primary data.

A

pros
- collected for a pre-specified purpose: to test the hypotheses or answer the research question(s) set by the researcher

cons
- money
- time

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

Name some and cons of secondary data.

A

pros
- money
- time

cons
- may have to make a series of assumptions because the data analysed weren’t intended for the new purpose
- introduce critical limitations on how the findings of such a study are interpreted

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

What type of data is this:

  • form the mainstay of day-to-day demography and epidemiology in the field
  • large administrative datasets that allow us to understand populations and their health

Give some examples?

A

routinely collected data

  • census
  • Hospital Episode Statistics (HES)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What is routinely collected data very useful?

A
  • immensely useful and a very easy go-to resource when we’re trying to epidemiologically understand what’s going on around us
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What type of data is this:

  • corollary (consequence) to primary data
A

Non-routinely collected data

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

What is a limitation of non-routinely collected data?

A
  • in professional practice (outside research) non-routinely collected data is usually prohibitively expensive and time-consuming to operate, so their use is limited
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

What is data linkage

A

the joining two or more datasets together and in doing so, finding out more than was possible by analysis of either original dataset alone

26
Q

Name some advantages and disadvantages of case-control studies

A
27
Q

There is a case control study trying to discover if there is a link between the types of food eaten by those who were later diagnosed with cancer and those who were not.

The interviewer is blinded, so they do not know whether the patient has/had cancer or not.

What bias is at risk here?

A

recall bias

28
Q

What is the difference between an observational case control study and an experimental case control study?

A

observational: the investigator does not interfere or manipulate exposure

experimental: does

29
Q

Calculate the odds ratio of having smoked if you have lung cancer.

A

if you had lung cancer you were 81% more likely to smoke than if you didn’t have lung cancer

30
Q

How do we calculate odds ratio?

A

by dividing the odds of the first group by the odds of the second group

31
Q

What does an odds ratio tell us?

A

how much higher the odds of exposure are among case-patients than among controls

32
Q

What do we call a study where the medical records of groups of individuals who are alike in many ways but differ by a certain characteristic (for example, female nurses who smoke and those who do not smoke) are compared for a particular outcome (such as lung cancer)?

A

historical cohort study

33
Q

Why are historical cohort studies typically lower quality than prospective cohort studies?

A

because there is a greater risk of both selection and information biases

34
Q

How do deal with loss to follow-ups

A
  1. be transparent
    (report it; consider why if proportion is high and if study still of good quality)
  2. be conservative
    (if there’s the potential for the loss to bias away from the null hypothesis, then reporting the output statistic which biases towards the null is generally the more sensible course of action)
35
Q

What are randomised controlled trials?

A

experimental studies that compare and assess the effectiveness of one or more treatment

36
Q

What do we call a randomised control trial which uses a placebo?

A

placebo control trials

37
Q

Does randomisation completely protect against bias?

A

no

38
Q

What does ‘intention to treat’ mean in a trial? Why do we use this?

A

analysing patients according to which group they were originally assigned

it ignores noncompliance, protocol deviations, withdrawal, and anything that happens after randomization

39
Q

How do we call it when the randomised allocations are given to the patients without the anyone knowing the allocations?

A

allocation concealment

40
Q

Explain the different blinding strategies in randomised trials

A
41
Q

What is blinding?

A

a procedure whereby one or more parties in a trial are kept unaware of which treatment arm a participant has been assigned to

42
Q

Why do we use ‘blinding’?

A

to avoid and prevent conscious and unconscious bias

43
Q

What is this bias?

systematic differences between groups in care that is provided, or in exposure to factors other than the exposure of interest

A

performance bias

44
Q

What is this bias?

systematic differences between groups in how outcomes are determined

A

detection bias

45
Q

What is this bias?

systematic differences between groups in how outcomes are determined

A

detection bias

46
Q

Why can blinding help prevent withdrawals from studies?

A

if patient knows what treatment they are receiving and feel that it is inferior, it can chance whether the patients follows instructions, or may drop out

47
Q

What is ‘power’ in the context of control trials?

A

the ability to detect an association if one truly exists

48
Q

In a trial, what should the power be?

A

80% or preferably 90%

49
Q

What does it mean if a trial has a power of 90%?

A

if the true difference between treatments is equal to the one we planned, then the chance that the study will not detect it is 10%

50
Q

power _____ with increasing sample size

A

increases

51
Q

Why is blinding not always possible?

A

logistically impossible?
ethically impossible?
more costly?

52
Q

What affects the sample size of your case study population?

A
  • difference between the groups that you’d be looking to investigate
  • study power
  • study’s alpha
  • don’t forget loss to follow-up
53
Q

How will difference between the groups that you’d be looking to investigate affect your sample size?

A
  • for example, if investigating blood pressure, we might want to look for perhaps 5 mmHg or 10 mmHg difference
  • larger difference will require a smaller sample size – just like photographing a larger object doesn’t require as good a camera (as photographing a smaller object).
54
Q

How will a study’s power affect your sample size?

A

As you increase your power, your sample size will increase.

55
Q

How will a study’s alpha affect your sample size?

A
  • how much you want to rule out chance causing a positive finding
  • the equivalent of specifying the p-value
  • it’s also connected with one/two-tailed testing
  • decreasing alpha from 0.05 to 0.01 will increase your sample size
56
Q

What is a study’s alpha?

A

the equivalent of specifying the p-value

The alpha is the decimal expression of how much they are willing to be wrong. For the current example, the alpha is 0.05. We now have the level of uncertainty the researcher is willing to accept (alpha or significance level) of 0.05 or 5% chance they are not correct about the outcome of the study.

57
Q

What is a type I error?

it is related to p-value/power?

A

a false positive

the p-value is the probability of getting your results if actually there’s no real difference. That means it’s the probability of a false positive.

58
Q

What is a type II error?

it is related to p-value/power?

A

a false negative

to explain your situation we’d want to know what your study design was powered to detect. Typically we use 80% or 90% power. Bear in mind that going from 80% to 90% power halves the risk of you deriving a false negative.

59
Q

If the OR is > 1 the control is ____ than the intervention.

If the OR is < 1 the intervention is _____ than the control.

A

If the OR is > 1 the control is better than the intervention.

If the OR is < 1 the intervention is better than the control.

60
Q

What is the difference between a type I error and type II error?

A

A type I error (false-positive) occurs if an investigator rejects a null hypothesis that is actually true in the population

a type II error (false-negative) occurs if the investigator fails to reject a null hypothesis that is actually false in the population.

LMAP-2 (7 decks)

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