Statistics

Question 1

Define variable

Answer 1

Aspect that can take different values for different participants

Question 2

What are the two main types of variable?

Answer 2

Categorical

Quantitative

Question 3

What are two types of categorical variable?

Answer 3

Nominal - unordered labelled characteristics

Ordinal - small set of ordered/ranked categories

Question 4

What descriptive statistics would you do for categorical data?

Answer 4

Frequency

Relative Frequency

Question 5

What type of graph would you create for categorical data?

Answer 5

Bar chat

Question 6

What descriptive statistics would you do for quantitative data?

Answer 6

Averages
Variation
Symmetry

Question 7

What types of graph would you create for quantitative data?

Answer 7

Histogram
Box Plot
Box and whisker

Question 8

What is normal distribution?

Answer 8

Mathematically defined theoretical distribution

Question 9

Define descriptive statistics

Answer 9

Describe and summarise data in the sample

i.e. how common are certain characteristics, how are different characteristics related to each other

Question 10

Define inferential statistics

Answer 10

Using sample data to make inferences about characteristics and relationships in the populations
i.e. standard errors, confidence intervals, p-values

Question 11

What is standard error?

Answer 11

Indicates how far, on average, the sample estimate is expected to be from the true population parameter value

Question 12

What is the difference between standard error and standard deviation?

Answer 12

SE summarises precision of an estimate

SD summarises variability of an estimate

Question 13

What is a confidence interval?

Answer 13

Range of values in which we can be confident the true value lies

Question 14

What is a p-value?

Answer 14

Quantifies the extent to which the sample estimate contradicts the null hypothesis

Question 15

What is a null hypothesis?

Answer 15

The most boring truth imaginable

Question 16

What is an alternative hypothesis?

Answer 16

Opposite of the null hypothesis

Usually two tailed - contradictions to the null hypothesis in either direction

Question 17

What is a Type I and Type II error in hypothesis testing?

Answer 17

Type 1 error - null being rejected when it is true, ‘significant’ result due to chance
Type 2 error - null not rejected when it is false, study not powerful enough

Question 18

What is a two sample (unpaired) t-test used for? What are the assumptions?

Answer 18

Tests for mean difference between two independent groups
Assumptions:
Variable is normally distributed
SD is similar
Observations are not paired

Question 19

What is a paired t-test used for? What are the assumptions?

Answer 19

Used when observations are linked in some way (e.g. before and after)
Analysis based on within-pair differences between groups
Assumption:
Within-pair differences are normally distributed

Question 20

What is an ANOVA used for? What are the assumptions?

Answer 20

For comparing 3 or more independent groups
Assumptions:
Each group is normally distributed
SD is similar
Observations are independent

Question 21

What is a repeated measures ANOVA used for? What are the assumptions?

Answer 21

For comparing 3 or more paired groups
Assumptions:
Difference scores between any two groups are normally distributed
SD of different scores should be the same for all combined groups

Question 22

How do non-parametric tests work?

Answer 22

Analyse rank ordering rather than actual scores

Compare distributions rather than means

Question 23

When do we use non-parametric tests?

Answer 23

When assumptions for parametric tests do not hold

e.g. variable is skewed, SD differs markedly, variable is more ordinal than quantitative

Question 24

What is a wilcoxon (rank sum) test used for?

Answer 24

Compares two independent groups

Question 25

What is a kruskal-wallis test used for?

Answer 25

Comparing three or more independent groups

Question 26

What is a wilcoxon signed rank test used for?

Answer 26

Compares two paired groups

Question 27

What is a Friedman test used for?

Answer 27

Compares three or more paired groups

Question 28

What are the advantages and disadvantages of non-parametric tests?

Answer 28

``` Advantages: Always valid for quantitative data Often provide similar p-values to quantitative tests Disadvantages: Do not make direct inferences Do not provide CIs Based on analysis of ranks, not scores When assumptions hold, not as powerful ```

Question 29

How do you calculate proportion?

Answer 29

No. in category of interest/total no. of participants

Question 30

What does the term risk mean?

Answer 30

The proportion/percentage of people with a specified disease in a population

Question 31

How do you calculate odds?

Answer 31

No. in category of interest/No. in other category OR % in category of interest/ 100-% in category of interest

Question 32

How are odds and % related?

Answer 32

The higher the %, the higher the odds

Question 33

In what type of study are odds particularly useful?

Answer 33

Case-control studies

Question 34

How would you summarise binary variables in 2 independent groups?

Answer 34

Cross tabulate - exposure variable and outcome variable

Question 35

When calculating absolute measures, what indicates no difference?

Answer 35

0

Question 36

How do you calculate risk difference?

Answer 36

% of people affected in one group - % in the other

Question 37

When calculating relative measures, what indicates no difference?

Answer 37

1

Question 38

How do you calculate risk ratio/relative risk?

Answer 38

% affected in intervention group / % in the control

Question 39

How do you calculate odds ratio?

Answer 39

Odds in one group / odds in the other

Question 40

What does 0, 0< and 0> mean in term of risk difference?

Answer 40

``` 0 = groups equally likely to have disease 0< = first group more likely to have disease 0> = second group more likely to have disease ```

Question 41

How do you calculate absolute risk reduction?

Answer 41

Difference in % points between groups

Question 42

What is number needed to treat?

Answer 42

Number of people that need to receive intervention before one person benefits from it

Question 43

How do you calculate number needed to treat?

Answer 43

100/risk difference

Question 44

What does a risk ratio of <1 mean?

Answer 44

Disease occurrence is lower in the intervention group

Question 45

How do you calculate relative risk reduction?

Answer 45

(1-risk ratio)x100

Question 46

How do you calculate odds ratio?

Answer 46

odds of disease in exposed group / odds of disease in non-exposed group

Question 47

What are risk difference and NNT good at quantifying?

Answer 47

Impact of an intervention

Question 48

What are risk ratio and odds ratio good at quantifying?

Answer 48

Strength of association between intervention and disease status

Question 49

Which two tests give p-values when comparing binary variables between two groups?

Answer 49

Chi-squared test | Fishers exact test

Question 50

How do you calculate an 'expected value'?

Answer 50

(row total x column total) / total sample size

Question 51

What are the assumptions of the Chi-sqaured test?

Answer 51

Total sample size is at least 40 OR If sample is between 20 and 39, the expected value in each cell is at least 5

Question 52

What are the assumptions of the Fisher's Exact Test?

Answer 52

Fewer than 20 participants | Between 20 and 39 participants and the expected value in at least one cell is less than 5

Question 53

What is the definition of correlation?

Answer 53

The association between two variables

Question 54

How can correlation be summarised graphically and numerically?

Answer 54

Graphically - scatterplots | Numerically - correlation coefficients

Question 55

What does a correlation coefficient do?

Answer 55

Quantifies the strength of association between two variables

Question 56

What is the difference between Pearson and Spearman correlation coefficient?

Answer 56

Pearson - linear relationship | Spearman - non-linear associations (monotonic - only positive or only negative)

Question 57

What does R Squared tell us?

Answer 57

The proportion of the variation in one variable that is explained by another variable

Question 58

How do we calculate R squared?

Answer 58

Multiply Pearson's coefficient by itself

Question 59

What is linear regression used for?

Answer 59

Estimating the mathematical equation that describes the linear relationship between a quantitative outcome and a quantitative predictor

Question 60

What is the least squares estimation?

Answer 60

Method of estimating regression coefficients Derives line of best fit/regression line Estimate of the true regression line in the population

Question 61

What are the assumptions of regression?

Answer 61

Outcome is quantitative Relationship is linear Residuals are normally distributed Constant variance

Question 62

What are the similarities and differences between regression and persons CC?

Answer 62

Pearsons quantifies strength of association | Regression describes the relationship and can be used to predict outcome variable score

Question 63

How do we calculate sensitivity?

Answer 63

TP / TP + FN

Question 64

How do we calculate specificity?

Answer 64

TN / TN + FP

Question 65

What is PPV?

Answer 65

Positive predictive value - proportion of those with a +ve result that have the condition

Question 66

What is NPV?

Answer 66

Negative predictive value - proportion of those with a -ve result that do not have the condition

Question 67

How do we calculate PPV?

Answer 67

TP / TP + FP

Question 68

How do we calculate NPV?

Answer 68

TN / TN + FN