Statistics

Question 1

Parametric tests:

Require data to have normal distribution

Answer 1

True

Question 2

Parametric tests:

Give the results as odds ratios

Answer 2

False

Question 3

Parametric tests:

Are appropriate for comparing the incidence of hypotension in two groups

Answer 3

False

Question 4

Parametric tests:

Are less powerful than non-parametric ones

Answer 4

False

Question 5

Parametric tests:

Include analysis of varience

Answer 5

True

Question 6

95% confidence intervals:

Indicate the range of plausible values for the true result

Answer 6

True

Question 7

95% confidence intervals:

become wider, the larger the sample size

Answer 7

False

Question 8

95% confidence intervals:

Can be used to describe a difference between two groups

Answer 8

True

Question 9

95% confidence intervals:

Can be used to indicate the incidence of a rare complication

Answer 9

True

Question 10

95% confidence intervals:

Indicate whether a difference is statistically significant

Answer 10

True

Question 11

The ASA physical status of a group of patients:

Is best described by median and standard deviation

Answer 11

True

Question 12

The ASA physical status of a group of patients:

Is an example of ordinal data

Answer 12

True

Question 13

The ASA physical status of a group of patients:

Is usually normally distributed

Answer 13

False

Question 14

The ASA physical status of a group of patients:

Can be plotted as a bar chart

Answer 14

True

Question 15

The ASA physical status of a group of patients:

May be compared using the chi-squared test

Answer 15

True

Question 16

Standard deviation:

Is always less than 1

Answer 16

False

Question 17

Standard deviation:

Indicates the scatter of data around the central tendency

Answer 17

True

Question 18

Standard deviation:

Is the square root of varience

Answer 18

True

Question 19

Standard deviation:

Increases as sample size increases

Answer 19

False

Question 20

Standard deviation:

Is interchangeable with standard error

Answer 20

False

Question 21

Continuous data:

Are always symmetrical when plotted

Answer 21

False

Question 22

Continuous data:

May be transformed using logarithms

Answer 22

True

Question 23

Continuous data:

Are compared using T-tests

Answer 23

True

Question 24

Continuous data:

Can include negative numbers

Answer 24

True

Question 25

Continuous data:

Can also be called categorical data

Answer 25

False

Question 26

if p = 0.05 for a comparison of two treatments:

There is a 95% chance that there is no difference between the treatments

Answer 26

False

Question 27

if p = 0.05 for a comparison of two treatments:

The null hypothesis is incorrect

Answer 27

False

Question 28

if p = 0.05 for a comparison of two treatments:

The chance of a false negative is 5%

Answer 28

False

Question 29

if p = 0.05 for a comparison of two treatments:

We can conclude that one treatment is more effective

Answer 29

False

Question 30

if p = 0.05 for a comparison of two treatments:

The data we have observed would only occur 5% of the time or less if the treatments were equally effective

Answer 30

True

Question 31

The interquartile range is:

The variance between four groups

Answer 31

False

Question 32

The interquartile range is:

The middle 50% of the data

Answer 32

True

Question 33

The interquartile range is:

The same as standard deviation

Answer 33

False

Question 34

The interquartile range is:

Often represented by the box in a box-whisker plot

Answer 34

True

Question 35

The interquartile range is:

Often represented by the tails of a normal distribution curve

Answer 35

False

Question 36

In a clinical trial:

Blinding reduces the effects of the confounding factors

Answer 36

False

Question 37

In a clinical trial:

A placebo is usually considered unethical nowadays

Answer 37

False

Question 38

In a clinical trial:

Controls may be standard treatment, placebo or historical

Answer 38

True

Question 39

In a clinical trial:

Randomisation is always required

Answer 39

False

Question 40

In a clinical trial:

Intention to treat is always required

Answer 40

False

Question 41

In a study comparing two airway devices, the incidence of sore throat is 20% with the standard device and 15% with the new device. Which of the following are true:
The relative risk reduction is 5%

Answer 41

False

Question 42

In a study comparing two airway devices, the incidence of sore throat is 20% with the standard device and 15% with the new device. Which of the following are true:
The absolute risk reduction is 5%

Answer 42

True

Question 43

In a study comparing two airway devices, the incidence of sore throat is 20% with the standard device and 15% with the new device. Which of the following are true:
The p value is 5%

Answer 43

False

Question 44

In a study comparing two airway devices, the incidence of sore throat is 20% with the standard device and 15% with the new device. Which of the following are true:
The odds ratio is 5%

Answer 44

False

Question 45

In a study comparing two airway devices, the incidence of sore throat is 20% with the standard device and 15% with the new device. Which of the following are true:
The number needed to treat is 5

Answer 45

False

Question 46

The power of a study:

Depends on the statistical test used to compare the data

Answer 46

True

Question 47

The power of a study:

Is the ability to detect a significant difference between the groups

Answer 47

True

Question 48

The power of a study:

Only applies to parametric tests

Answer 48

False

Question 49

The power of a study:

Equals 1-? where ? is the type II error

Answer 49

True

Question 50

The power of a study:

May be calculated before or after a study

Answer 50

True

Question 51

Randomisation:

Always results in equal groups

Answer 51

False

Question 52

Randomisation:

Should always be tested by comparing the groups baseline data

Answer 52

False

Question 53

Randomisation:

Requires a power analysis to be valid

Answer 53

False

Question 54

Randomisation:

Increases the likelihood that any significant difference is due to the treatment being studied

Answer 54

True

Question 55

Randomisation:

Helps preserve blinding

Answer 55

True

Question 56

Comparing two sets of urine output volumes:

A t-test is appropriate unless the data are normally distributed

Answer 56

False

Question 57

Comparing two sets of urine output volumes:

The comparison should always be paired

Answer 57

False

Question 58

Comparing two sets of urine output volumes:

The results may be expressed as a 95% confidence interval

Answer 58

True

Question 59

Comparing two sets of urine output volumes:

The standard deviations should be similar in order to do a statistical comparison

Answer 59

False

Question 60

Comparing two sets of urine output volumes:

Can be done using parametric tests

Answer 60

True

Question 61

The following measures of central tendency could correctly describe the matched type of data:
Variance and normally distributed data

Answer 61

False

Question 62

The following measures of central tendency could correctly describe the matched type of data:
The standard error of the mean and normally distributed data

Answer 62

False

Question 63

The following measures of central tendency could correctly describe the matched type of data:
Mode and positively skewed data

Answer 63

False

Question 64

The following measures of central tendency could correctly describe the matched type of data:
Median and negatively skewed data

Answer 64

True

Question 65

The following measures of central tendency could correctly describe the matched type of data:
Mode and categorical data

Answer 65

True

Question 66

Regarding correlation coefficient:

A positive value implies that a rise in one variable causes a rise in the other

Answer 66

False

Question 67

Regarding correlation coefficient:

Can be calculated for parametric and non-parametric data

Answer 67

True

Question 68

Regarding correlation coefficient:

Is measured on a scale of -1 to1

Answer 68

True

Question 69

Regarding correlation coefficient:

Is usually denoted by the symbol r

Answer 69

True

Question 70

Regarding correlation coefficient:

A value of -1 indicates perfect positive correlation

Answer 70

False

Question 71

The following are non-parametric tests:

Chi-squared test

Answer 71

True

Question 72

The following are non-parametric tests:

ANOVA

Answer 72

False

Question 73

The following are non-parametric tests:

The mann-whitney test

Answer 73

True

Question 74

The following are non-parametric tests:

The students T-test

Answer 74

False

Question 75

The following are non-parametric tests:

The wilcoxon signed rank sum test

Answer 75

True

Question 76

An odds ratio is the probability of a given outcome, divided by the probability of the alternative outcome

Answer 76

False

Question 77

Odds ratios and risk ratios are both valid measures of association

Answer 77

True

Question 78

Risk ratios can be affected by the incidence of the disease we are studying

Answer 78

True

Question 79

A risk ratio can be defined as the risk of a certain outcome given certain conditions, divided by the risk of that outcome given other conditions

Answer 79

True

Question 80

Risk ratios are more intuitive than odds ratios

Answer 80

True

Question 81

Statistical definitions:

Variance is the sum of the differences divided by the degrees of freedom

Answer 81

True

Question 82

Statistical definitions:

A normal distribution is one where the mean, median and mode are the same

Answer 82

True

Question 83

Statistical definitions:

Mode is the most frequently occurring variable

Answer 83

True

Question 84

Standard error of the mean is the square root of the variance

Answer 84

False

Question 85

Standard deviation is the standard error of the mean divided by the square root of the number observed

Answer 85

False

Question 86

Concerning errors in statistics:

The power of a study will be greater if you are trying to detect a small difference

Answer 86

False

Question 87

Concerning errors in statistics:

A type 1 error is a false negative

Answer 87

False

Question 88

Concerning errors in statistics:

A type 1 error is the same as the beta error

Answer 88

False

Question 89

Concerning errors in statistics:

The power of a study describes the likelihood of detecting a real difference if it exists

Answer 89

True

Question 90

Concerning errors in statistics:

A type 1 error is unlikely to influence the conclusions of a trial

Answer 90

False

Question 91

The following are parametric tests:

Spearman’s rank correlation

Answer 91

False

Question 92

The following are parametric tests:

Fishers exact test

Answer 92

False

Question 93

The following are parametric tests:

ANOVA

Answer 93

True

Question 94

The following are parametric tests:

Kruskal-Wallis

Answer 94

False

Question 95

The following are parametric tests:

Forest plots

Answer 95

False

Question 96

The Chi-squared test:

Can be used to test nominal data

Answer 96

True

Question 97

The Chi-squared test:

Requires the standard error of the mean to be calculated

Answer 97

False

Question 98

The Chi-squared test:

Does not requires a knowledge of the number of degrees of freedom

Answer 98

False

Question 99

The Chi-squared test:

Should not be used for data with small groups

Answer 99

True

Question 100

The Chi-squared test:

Can be used to compare more than 2 groups

Answer 100

True