Statistics

Question 1

How do you calculate Absolute Risk Reduction (ARR)

Answer 1

ARR = Control rate - experimental rate

(If a control has a risk of PONV 20/100 compared to an experimental drug 10/100 the ARR = 0.2 - 0.1)

Question 2

How do you calculate Number Needed To Treat (NNT)

Answer 2

1/ARR

(Absolute risk reduction)

Question 3

How do you calculate Relative Risk (RR)

Answer 3

RR = Experimental event rate / Control event rate

(If a control has risk of PONV 20/100 and experimental drug has risk 10/100 RR= 0.1/0.2)

Question 4

What type of error is a false positive

Answer 4

Type 1 error (alpha)

Question 5

What type of error is a false negative

Answer 5

Type 2 error (Beta)

Question 6

How do you calculate power of a study

Answer 6

Power = 1 - Beta (Type 2 error)

Question 7

Which statistical test can be used for comparing 2 sets of continuous normally distributed (parametric) data

Answer 7

T-test

Paired if the same subject is in the control group and also in the experimental group

otherwise unpaired

Question 8

Which statistical test can be used for comparing more than 2 sets of continuous normally distributed (parametric) data

Answer 8

ANOVA test

(Can do multiple t-tests but higher risks of error)

Question 9

What percentage of a population lies within 1 standard deviation (SD) from the mean

Answer 9

68%

Question 10

What percentage of a population lies within 2 standard deviations (SD) from the mean

Answer 10

95%

Question 11

What percentage of a population lies within 3 standard deviations (SD) from the mean

Answer 11

99.7%

Question 12

How does the size of the difference you’re looking for between 2 groups affect power

Answer 12

Small difference = low power

High Beta error ( false negative)

Needs high n number

Question 13

How does the SD affect power

Answer 13

Large SD = large area = low power

high Beta error

Needs high n Number

Question 14

How does the p value affect power

Answer 14

low p value = high confidence can reject null hypothesis = low power

High Beta error

Needs high n number

Question 15

How does parametric vs non-parametric test affect power

Answer 15

Non-parametric = low power

high beta error

Needs high n number

Question 16

How do you calculate standard error of the mean

Answer 16

SD/ √n

standard deviation/ square root of sample size

Question 17

How does standard error of the mean give you 95% CI

Answer 17

95% confidence interval is 2 standard errors of the mean above and below.

Question 18

How do you calculate variance

Answer 18

Σ(x-x̄)²/ n-1

the difference of each value from the mean added together and squared then divided by the sample size -1 (degree of freedom)

Question 19

How do you calculate standard deviation from variance

Answer 19

SD = √variance

= √Σ(x-x̄)²/ n-1

Question 20

What does it mean if the 95% confidence intervals of 2 groups do not overlap

Answer 20

There is likely to be a significant statistical difference

Question 21

Which statistical test can be used for comparing more than 2 groups of quantitative non-parametric data

Answer 21

Kruskal wallis test

Question 22

Which 2 statistical tests can be used for comparing 2 groups of quantitative non-parametric data

Answer 22

Mann Whitney

Wilcoxian

Question 23

Which parameter is used to look at the central tendency of non-parametric data

Answer 23

Median

(use median instead of mean)

Question 24

Which parameter is used to look at the central tendency of parametric data

Answer 24

Mean

Question 25

Which parameters are used to look at spread of non-parametric data

Answer 25

Range Inter quartile range (from start of Q2 (25%) to end of Q3 (75%) )

Question 26

Which 2 statistical tests can be used for comparing 2 groups of qualitative data

Answer 26

Fisher's exact test Chi- Squared test

Question 27

What does a correlation coefficient of r = +1 mean

Answer 27

perfect positive linear correlation. All data points lie exactly on a straight line with +ve gradient

Question 28

What does a correlation coefficient of r = -1 mean

Answer 28

perfect negative linear correlation. All data points lie exactly on a straight line with -ve gradient

Question 29

What does a correlation coefficient of r = 0 mean

Answer 29

No linear correlation between data points

Question 30

When would you use Pearson's correlation coefficient

Answer 30

When comparing 2 groups of parametric data to look for degree of correlation with linear relationship

Question 31

When would you use Spearmen's rho correlation coefficient

Answer 31

When comparing 2 groups of which at least 1 has non- parametric data to look for degree of correlation with linear relationship

Question 32

Define what is meant by co-efficient of determination (r²)

Answer 32

(This is correlation co-efficient squared) The proportion of the variation (variance) in the dependent variable that is predictable from the independent variable e.g r ² of 0.64 means that 64% of the variance in y is predictable from the variance in x

Question 33

What is the Bland-Altman plot used for

Answer 33

Used to compare 2 different measuring devices X-axis: Both measurement device results added together and divided by 2 (average) (the true value) Y-axis: Difference between the values measured by each device

Question 34

How do you calculate Relative Risk Reduction (RRR)

Answer 34

RRR = (Control event rate - Experimental event rate) / Control event rate (If a control has risk of PONV 20/100 and experimental drug has risk 10/100 RRR= (0.2 - 0.1)/0.2

Question 35

When would you use odds ratio (OR) instead or relative risk (RR)

Answer 35

Case control studies RR can only be used in cohort studies whereas OR can also be used in cohort and case control

Question 36

What does an odds ratio (OR) of 1 mean

Answer 36

There is no association between exposure to the treatment and improved outcomes Null hypothesis

Question 37

What does an odds ratio (OR) < 1 mean

Answer 37

There is a negative association The odds of an event happening in the exposed/treated group is less than the control group (e.g treatment reduces odds of stroke)

Question 38

What does an odds ratio (OR) > 1 mean

Answer 38

There is a positive association The odds of an event happening in the exposed/treated group is higher than the control group (e.g treatment increases odds of stroke)