Statistics and critical appraisal Flashcards

1
Q

Internal and external validity

A

Internal - was the study done right? Do the results accurately reflect the truth?

External - does the same thing happen elsewhere? Is this study applicable to real life?

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

Efficacy and effectiveness

A

Efficacy - impact of an intervention under ideal conditions

Effectiveness - impact of an invervention under clinical/real life conditions

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

Berkson bias

A

Sample population is taken from hospital setting, but these are not representative of target population (rate or severity)

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

Diagnostic purity bias

A

Comorbidity excluded, so complexity of target population not represented

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

Neyman bias

A

Time gap between exposure and sample selection, meaning some are not available for study (eg due to death)

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

Membership bias

A

Particular group is targeted for study, which is not representative (eg in a particular organisation)

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

Historical control bias

A

Subjects and controls chosen over time, so affected by changes in social definitions, treatment modalities etc.

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

Performance bias

A

Subjects behave differently because they know which group they are in. Controlled for by blinding and randomisation.

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

Ascertainment/interviewer bias

A

Researcher not blinded, which affects recording of results

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

Recall bias

A

Subjects mis-remember past

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

Response bias

A

Subjects answer questions in the way they think the researcher wants them to answer

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

Attrition bias

A

Bias due to subjects leaving the study at different rates in different groups in the study (eg due to side-effects)

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

Hawthorne effect

A

Subjects alter their behaviour, as they know they are being observed

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

Pygmalion (Rosenthal) effect

A

Subjects perform to meet expectations set by others (usually positively). Known as placebo effect in medical settings.

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

Inter-rater reliability

A

Agreement between different assessors at the same time (do different people agree with each other?)

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

Intra-rater reliability

A

Agreement between the results from one assessor at different times, whilst assessing the same material (does one person agree with herself?)

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

Test-retest reliability

A

Agreement between results of a test, and the results of the same test repeated at a later date.

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

Alternative form reliability

A

Agreement between the results of different versions of the same test

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

Split half reliability

A

Reliability of a test that is divided in two, with each half assessing the same material (do all parts of the test contribute equally?)

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

Cohen’s statistic (k)

A

Measures agreement between raters in tests measuring categorical variables. If no more than expected by chance, k=0. Statistically significant if k≥0.7

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

Crohnbach’s alpha

A

Measures agreement between variables when using complicated tests with several parts or measuring several variables.

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

Intraclass correlation co-efficient

A

Measures agreement. For use with quantitative variables

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

Predictive validity

A

Ability of a test to predict something it should theoretically be able to predict (eg predicting employment whilst at school)

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

Concurrent validity

A

Ability of a test to distinguish between 2 groups that it should theoretically be able to distinguish between (eg angina vs gastritis)

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

Convergent validity

A

The extent to which a test agrees with other tests it should theoretically be similar to (eg different types of thermometer)

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

Discriminant validity

A

The extent to which a test differs from a test it should theoretically be different from (eg exam results and SJT test)

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

Face validity

A

The extent to which the test, on superficial consideration, measures what it is supposed to measure.

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

Content validity

A

The extent to which the test measures variables that are related to that which should be measured by the test.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

Construct validity

A

The extent to which the test measures a theoretical concept by a specific measuring device or procedure.

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

Incremental validity

A

The extent to which the test provides a significant improvement in addition to the use of another approach. (eg ultrasound in estimating foetal age cf dates alone)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

Incidence

A

Number of new cases in a period of time / population size

Usually expressed per year

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

Categorical data

A

Data that has no numerical value and cannot be measured on a scale (eg. marital status, dead/alive).

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

Nominal data

A

Categorical data that does not have an order (eg male/female)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

Ordinal data

A

Categorical data in which there is an order (eg social class)

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

Quantative data

A

Data with a numerical value

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

Discrete data

A

Data that exists as discrete numbers, and is not on a scale (eg. number of children)

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

Continuous data

A

Data that can have any value within the range of possible values (eg height, age)

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

Descriptive statistics for categorical data

A

Mode and frequency

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

Descriptive statistics for non-normally distributed quantitative data

A

Median and range or IQR

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

Descriptive statistics for normally distributed data

A

Mean and standard deviation

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

Proportion of data that falls within 1SD of the mean

A

68%

42
Q

Proportion of data that falls within 2SD of mean

A

95%

43
Q

Varience

A

Sum of all the differences between all values and the mean, squared, divided by (n-1).

44
Q

Standard deviation

A

Square root of varience

45
Q

Standard error

A

Estimate of the standard deviation that would be obtained from the means of a large number of samples drawn from the same population.

SE = SD/sqrt(n)

46
Q

Confidence interval

A

CI = mean +/- 1.96 x standard error

47
Q

Positive skew

A

long tail to the right

48
Q

Negative skew

A

long tail to the left

49
Q

Type 1 error

A

Null hypothesis is rejected when it is in fact true (false positive). Represented as alpha.

50
Q

Type 2 error

A

Null hypothesis is accepted when it is in fact false (false negative). Represented as beta.

51
Q

Convention for power

A

0.8

52
Q

Information needed for power calculation

A

Power (1-beta)
Level of significance (alpha)
Underlying population event rate
Size of treatment effect

53
Q

Statistical test for categorical, unpaired data

A

Chi-squared test

54
Q

Statistical test for categorical, paired data

A

McNemar’s test

55
Q

Statistical test for categorical, unpaired data with small sample set

A

Fisher’s exact test

56
Q

Statistical tests for non-normal data comparing one sample with a hypothetical sample

A

Sign test or Wilcoxon’s signed rank test

57
Q

Statistical test for non-normal data comparing two groups of unpaired data

A

Mann-Whitney U test

58
Q

Statistical test for non-normal data comparing two groups of paired data

A

Wilcoxon’s matched pairs test

59
Q

Statistical test for non-normal data comparing more than 2 groups of unpaired data

A

Kruskal-Wallis ANOVA

60
Q

Statistical test for non-normal data comparing more than 2 groups of paired data

A

Friedman’s test

61
Q

Statistical test for normal data comparing one sample with a hypothetical sample

A

One-sample t test

62
Q

Statistical test for normal data comparing 2 groups of data

A

Student’s t-test (paired or unpaired)

63
Q

Statistical test for normal data comparing more than 2 groups of data

A

ANOVA

64
Q

Experimental event rate

A

events/total exposed

65
Q

Control event rate

A

events/total control

66
Q

Absolute risk reduction

A

CER-EER

Lies between -1 and +1

67
Q

Relative risk

A

EER/CER

Risk in exposed/risk not-exposed

68
Q

Relative risk reduction

A

(CER-EER)/CER

Proportional change in risk in exposure group

69
Q

Number needed to treat

A

1/(CER-EER)

70
Q

Risk

A

Outcome/total possibilities

71
Q

Odds

A

Outcome/Not outcome

72
Q

Odds ratio

A

Odds expsed/Odds not exposed

73
Q

Face vailidity

A

Does the test seem to test what it claims to?

74
Q

Content validity

A

Does a test test all of what it claims to? (Eg all symptoms of depression)

75
Q

Criterion validity

A

Does a test test what it claims to better than the alternative test?

76
Q

Construct validity

A

How well does a test examine the construct it claims to? Does it agree with other tests which test this construct, and differ from tests which measure different constructs?

77
Q

CONSORT

A

Consolidated Standards of Reporting Trials - RCTs

78
Q

TREND

A

Transparent Reporting of Evaluations with Non-randomized Designs

79
Q

QUORUM

A

Quality of Reporting of Meta-analyses

80
Q

PRISMA

A

Preferred Reporting Items for Systematic Reviews and Meta-Analyses

81
Q

MOOSE

A

Meta-analysis Of Observational Studies in Epidemiology

82
Q

STROBE

A

Strengthening the Reporting of Observational Studies in Epidemiology

83
Q

SQUIRE

A

Standards for QUality Improvement Reporting Excellence

84
Q

STARD

A

STAndards for the Reporting of Diagnostic accuracy

85
Q

MIAME

A

Minimum information about a microarray experiment

86
Q

COREQ

A

Consolidated criteria for reporting qualitative research

87
Q

Senitivity

A

Proportion of subjects with the disorder picked up by positive test.

Positive results/total true positives (a/a+c)

88
Q

Specificity

A

Proportion of subjects without the disorder that have a negative test

Negative results/total true negatives (d/b+d)

89
Q

Positive predictive value

A

Proportion of people who have a positive result on the test who DO have the disorder

True positive/total positive results (a/a+b)

90
Q

Negative predictive value

A

Proportion of people with a negative result on the test who DO NOT have the disorder

True negatives/total negative results (d/c+d)

91
Q

Likelihood ratio for a positive test

A

sensitivity/(1-specificity)

92
Q

Likelihood ratio for a negative test

A

(1-sensitivity)/specificity

93
Q

Pre-test probability

A

Probability that a person will have the disorder BEFORE test is done = prevalence

94
Q

Pre-test odds

A

Odds that a person will have the disorder BEFORE test is done.

pre-test probability/(1-pre test probability)

95
Q

Post-test odds

A

Odds that a person will have the disorder AFTER test is positive

pre-test probability x likelihood ratio for pos result

96
Q

Post-test probability of a positive test

A

Probability that the person will have the disorder AFTER positive result

post-test odds/(1+post-test odds)

Same as positive predictive value

97
Q

Post-test probability of a negative result

A

Probability that the person will have the disorder AFTER negative result

1-NPV

98
Q

Cost-effectiveness analysis

A

Compares a number of interventions by relating costs to a single clinical measure of effectiveness (e.g. symptom reduction, improvement in activities of daily living).

99
Q

Cost-benefit analysis

A

All the costs and benefits of an intervention are measured in terms of money and establish which has the greatest net benefit.

It requires that all the consequences of an intervention, such as life-years saved, treatment side-effects, symptom relief, disability, pain and discomfort, are allocated a monetary value.

100
Q

Cost-utility analysis

A

A form of CEA in which health benefits / outcomes are measured in broader, more generic ways enabling comparisons between treatments for different diseases and conditions.

Multidimensional health outcomes are measured by a single preference- or utility-based index such as the QALY. Can compare treatments for different conditions.

101
Q

Cost-minimisation analysis

A

An economic evaluation in which consequences of competing interventions are the same and in which only inputs, that is, costs are taken into consideration. The aim is to decide the least costly way of achieving the same outcome.