Statistics

Question 1

Sensitivity

Answer 1

Ability of a test to correctly identify patients with the disease

True positive rate =

True positives / (True positive + False negative)

snNout : in highly sensitive test, negative will rule out disease

Question 2

Specificity

Answer 2

Ability of test to identify patients without a disease

True negative rate =

True negative / True negative + False positive

spPin: highly specific will rule in disorder

Question 3

Positive predictive value

Answer 3

Probability a person having the disease will test positive

PPV= True positives / True positives + False positives

Question 4

Negative predictive value

Answer 4

Probability a person not having the disease if the test is negative

NPV = True negative / (True negative + False negative)

Question 5

Likelihood Ratio

Answer 5

If the test is positive the odds of patient having the disease

LR= Sensitivity ( 1-Specificity)

Question 6

Accuracy

Answer 6

(True positive + True negative) / Population

Question 7

Null hypothesis

Answer 7

Any difference between study groups is by chance. i.e no true difference

Question 8

Alternate Hypothesis

Answer 8

Two study groups have a true difference

Question 9

Type 1 error (alpha)

Answer 9

False positive

Question 10

Type 2 error (Beta)

Answer 10

False negative

Probability of missing an effect that is really there

Question 11

Power

Answer 11

Ability to detect a true difference in outcome between two arms

Probability a type II error will not occur

Power = 1 - Beta

*B usually arbitrarily set as 0.2, from postulation that type 1 error 4 x as serious as type 2 error: alpha x 4 = beta (0.05 x 4 =0.2)

Question 12

Effect size

Answer 12

The quantitative measure of the magnitude of the difference between groups

Question 13

P-value

Answer 13

Probability of results given a true null hypothesis

<0.05 is statistically significance: result due to chance is less than 1 in 20

Question 14

How to calculate sample size?

Answer 14

• acceptable level of significance
• power of the study
• expected effect size
• underlying event rate in population (prevalence)
• standard deviation in population

Question 15

Prevalence

Answer 15

Proportion of population with disease at a given time point

= number of existing disease/ population

Question 16

Incidence

Answer 16

Rate of occurrence of new cases over a period of time

= number of new cases (in a given period of time) / population

Question 17

Absolute risk

Answer 17

Incidence rate of outcome in a group

number of event during FU / number of persons event free at the start

Question 18

Relative risk

Answer 18

Exposed group absolute risk/ Control group absolute risk

Question 19

Absolute risk reduction

Answer 19

Change in risk of outcome after intervention

= AR of control group - AR of experimental group

Question 20

Relative Risk Reduction

Answer 20

Absolute risk reduction / Absolute risk fo control group

Question 21

Number needed to treat

Answer 21

Number of subjects must be treated for one extra person to experience benefit

= 1 / Absolute risk reduction

Question 22

Odds ratio

Answer 22

Probability of event / Probability of non-event

used in cohort or case control study

Question 23

When does Odds ratio = Relative Risk?

Answer 23

When incidence of disease if very small

Question 24

What is a ROC curve?

Answer 24

Receiver operating characteristics curve; a graphical plot used to show the diagnostic ability of binary classifiers

Question 25

What is the y and x axis of an ROC curve?

Answer 25

X: false positive rate (1- specificity)

Y: true positive rate (sensitivity)

Question 26

How to interpret a ROC curve?

Answer 26

the better the test is, the closer it will lie to upper left corner fo graph

Question 27

What is AUC?

Answer 27

Area under the curve: used to summarizse the performance of the test at various thresholds

>0.8 = good discrimination

<0.6 = poor discrimination

Question 28

What are types of statistical data?

Answer 28

Numerical

Categorical

Ordinal

Question 29

What are types of numerical data?

Answer 29

• Discrete: can be counted
• Continuous: cannot be counted, only described using intervals of real number line

Question 30

What is categorical data?

Answer 30

Qualitative data

Question 31

What is ordinal data?

Answer 31

Data where order of variables have a significance

Question 32

Types of qualitative data

Answer 32

• Nominal
• Ordinal

Question 33

What are the statistical tests to analyze significance of categorical data?

Answer 33

• unpaired
  
  • Large sample: Chi square
  • Small sample: Fisher’s exact test
• paired: McNemar’s test

Question 34

What is parametric data?

Answer 34

Continuous data that is normally distributed (Gaussian)

Question 35

How to test whether a set a data is parametric?

Answer 35

• Visualization
• Skewness
• Formal test for normality

Question 36

What are the statistical tests used to compare means for parametric data?

Answer 36

• one sample: one sample t-test
• two groups: t-test
• more than two groups: ANOVA

Question 37

What are statistical tests used for comparing means in non-parametric data?

Answer 37

• one sample: Wilcox
• two groups: Mann-Whitney
• More than two groups:
  
  • unpaired: ANOVA, Kruskall-Wallis
  • paired: Friedman’s test

Question 38

List the nine Hill’s Criteria for causality

Answer 38

• Strength
• Consistency
• Specificity
• Temporality
• Biological gradient
• Plausibility
• Coherence
• Experimental evidence
• Analogy

Question 38

List the nine Hill’s Criteria for causality

Answer 38

• Strength
• Consistency
• Specificity
• Temporality
• Biolgoical gradient
• Plausbility
• Coherence
• Experimental evidence
• Analogy