Statistics

Question 1

What is meant by a nominal variable?

Answer 1

A type of qualitative variable that does not have an inherent order. Examples include sex and blood type

Question 2

What is meant by an ordinal variable?

Answer 2

A type of qualitative variable that has a natural or inherent ordering. Examples include much better/better/worse.

Question 3

What is a categorical/qualitative variable?

Answer 3

A non numerical variable. The can be either nominal (no inherent order) or ordinal (an inherent order)

Question 4

What is meant by a metric/quantitative variable?

Answer 4

A variable that is a real number. They can be either continuous (an unlimited amount of values such as weight) or discrete (limited number of values - usually from counting things_

Question 5

What are the two factors that define normal distribution?

Answer 5

Normal distribution is a bell shaped curve. It is defined by the mean (where the curve is centred) and the standard deviation (how broad or thin the curve is)

Question 6

In a normal distribution how many values will lie within +/-1 SD of the mean?

Answer 6

68.27%

Question 7

In a normal distribution how many values will lie within +/-2 SD of the mean?

Answer 7

95.45%

Question 8

In a normal distribution how many values will lie within +/-3 SD of the mean?

Answer 8

99.73%

Question 9

What is meant by the p value?

Answer 9

The probability of obtaining a specific observed result by chance. The smaller the p value the more unlikely the result is to have occured by chance. Usually a p value of less than 0.05% is accepted.

Question 10

What is meant by incidence?

Answer 10

The number of new cases of a disease occuring over a specified period of time

Question 11

What is meant by prevalence?

Answer 11

The number of existing cases of a disease at a particular point in time

Question 12

What is meant by sensitivity

Answer 12

A measure of how good a test is at detecting individuals who have the disease ie the true positive rate

Question 13

What is meant by a test sensitivity of 90%?

Answer 13

It means that 10% of people with the disease will have a negative test (false negative). Tests with high sensitivity are good screening tests

Question 14

What is meant by specificity?

Answer 14

A measure of how good a test is at detecting individuals who are not diseased ie the true negative rate.

Question 15

What does a specificity of 80% mean?

Answer 15

20% of people without the disease ill get a positive result. A test with a high specificity are used to confirm a diagnosis.

Question 16

What is the positive predictive value?

Answer 16

The probability that a patient with a positive test has the disease
PPV = Number of diseased people with a positive test/total number of tests

Question 17

What is the negative predictive value?

Answer 17

The probability that a patient with a negative test is healthy
NPV - Number of healthy people with a negative test/number of negative tests

Question 18

What is absolute risk reduction?

Answer 18

The benefit of one treatment over another. So if the risk in group 1 is R1 and the risk in group 2 in R2 then the ARR is R2 - R1

Question 19

What is relative risk reduction?

Answer 19

The proportion of initial risk that was eliminated by the given treatment.

Question 20

What is risk?

Answer 20

The probability of an occurance of an event within a given period of time

Question 21

What is relative risk?

Answer 21

Comparison of risk in 2 different groups.