Statistics

Question 1

What is the lowest value when the curve is negatively skewed? Positively skewed? (mean, median, or mode)

Answer 1

Question 2

Define standard error of mean (SEM).

Answer 2

Question 3

+/- 1 SD: _% of values
+/- 2 SD: _% of values
+/- 3 SD: _% of values

Answer 3

+/- 1 SD: 68% of values
+/- 2 SD: 95% of values
+/- 3 SD: 99% of values

Question 4

Define sensitivity of a test.

Answer 4

Sensitivity: the ability of a test to correctly identify patients with a disease.

“SNOUT”
Highly sensitive tests rule OUT disease.

Question 5

Define specificity of a test.

Answer 5

Specificity: the ability of a test to correctly identify people without the disease.

Highly specific tests rule IN disease.

Question 6

Define Positive Predictive Value (PPV).

Answer 6

POSITIVE PREDICTIVE VALUE: proportion of people with a positive test who actually have the disease

Question 7

Define Negative Predictive Value (NPV).

Answer 7

NEGATIVE PREDICTIVE VALUE: proportion of people with a negative test who actually do not have the disease

Question 8

Define Null Hypothesis (H0).

Answer 8

Null Hypothesis (H0): typical statistical theory which suggests that there is no relationship between the measured phenomenon (dependent variable) and the independent variable; the null hypothesis is that the observed difference between two variables is due to chance alone. Null hypothesis is the default position.

Question 9

Define Alternative Hypothesis (H1).

Answer 9

The alternative hypothesis (H1) is the hypothesis that suggests that sample observations are influenced by a non-random cause. That there is a relationship between the independent and dependent variable.

Question 10

What is a type 1 error?

Answer 10

A type I error (false-positive) occurs if an investigator rejects the null hypothesis when the null was true. Accepts alternative, should have accepted null.

Question 11

What is a type 2 error?

Answer 11

A type II error (false-negative) occurs if an investigator fails to reject a false null hypothesis (investigator believes there was no difference but there was a difference). Accepts Null, should have accepted alternative.

Question 12

Define power of a study.

Answer 12

Power represents the probability of observing a difference in the population if a difference exists.

In other words, its the probability that a study will reject the null hypothesis (no association between the predictor and the outcome variable) when it is actually false.

Power = 1-B

As the power of a study increases, the B error (type II error) decreases. In other words, the false negatives decrease.

Question 13

How can the power of a study be increased?

Answer 13

Increase sample size
Decrease population variability
Increase effect size
Increase alpha

Question 14

What is an odds ratio (OR)?

Answer 14

Odds Ratio: measure of association between an exposure and an outcome; how strongly an event is associated with an exposure. The larger the odds ratio, the higher odds that the event will occur with exposure.

Question 15

OR = 1

Answer 15

No effect

Question 16

OR > 1

Answer 16

Odds of outcome increased

Question 17

OR < 1

Answer 17

Odds of outcome decreased

Question 18

What is relative risk (RR)?

Answer 18

Relative risk is the ratio of the probability of an event occurring with an exposure versus the probability of the event occurring without the exposure.

If we hypothetically find that 17% of smokers develop lung cancer and 1% of non-smokers develop lung cancer, then we can calculate the relative risk of lung cancer in smokers versus non-smokers as:

Relative Risk = 17% / 1% = 17

Thus, smokers are 17 times more likely to develop lung cancer than non-smokers.

Question 19

RR = 1

Answer 19

Exposure does not effect outcome

Question 20

RR < 1

Answer 20

Exposure decreases risk of outcome
(protective factor)

EX: smoking and PONV

Question 21

RR > 1

Answer 21

Exposure increases risk of outcome
(risk factor)

EX: opioids and PONV

Question 22

RR is calculated in what studies?

Answer 22

Cohort

Question 23

OR is calculated in what studies?

Answer 23

Case-control

Question 24

What does a T-test test for?

Answer 24

A t-test tests a null hypothesis about two means; most often, it tests the hypothesis that two means are equal, or that the difference between them is zero.

For example, we could test whether boys and girls in fourth grade have the same average height.

A t-test requires two variables; one must be categorical and have exactly two levels, and the other must be quantitative and be estimable by a mean.

For example, the two groups could be Republicans and Democrats, and the quantitative variable could be age.

Question 25

What does a chi-square test test for?

Answer 25

A chi-square test tests a null hypothesis about the relationship between two variables.

For example, you could test the hypothesis that men and women are equally likely to vote “Democratic,” “Republican,” “Other” or “not at all.”

A chi-square test requires categorical variables, usually only two, but each may have any number of levels.

For example, the variables could be ethnic group — White, Black, Asian, American Indian/Alaskan native, Native Hawaiian/Pacific Islander, other, multiracial; and presidential choice in 2008 (Obama, McCain, other, did not vote).

Question 26

What does ANOVA test for?

Answer 26

ANOVA is a group of statistical techniques used to compare the means of two or more samples. It is a way of generalizing the t-test (used to compare two means) to three or more groups, since applying the t-test to more than two groups would increase the likelihood of a type I error.

One-way ANOVA has one independent variable with three or more conditions. A two-way ANOVA has two independent variables each with multiple conditions.

Question 27

Define Number Needed to Treat (NTT).

Answer 27

NNT: # of patients that need to receive the intervention in order for 1 patient to gain benefit from that intervention.

NNT is the inverse of the ARR. To calculate the NNT, you need to know the Absolute Risk Reduction (ARR).

NNT = 1/ARR

Question 28

Define Absolute Risk Reduction (ARR).

Answer 28

ARR is the absolute difference between the risk of
the event in the control and experimental
groups.

ARR = CER - EER

Question 29

What is R^2?

Answer 29

R-squared (R2) is defined as a number that tells you how well the independent variable(s) in a statistical model explain the variation in the dependent variable. It goes from 0 to 1, where 1 indicates a perfect fit of the model to the data.

Whereas correlation explains the strength of the relationship between an independent and a dependent variable, R-squared explains the extent to which the variance of one variable explains the variance of the second variable. So, if the R2 of a model is 0.50, then approximately half of the observed variation can be explained by the model’s inputs.