Statistical Data

Question 1

What are descriptive statistics?

Answer 1

Describe the sample of interest

Question 2

What are inferential statistics?

Answer 2

What we collect from the research and the meaning we infer from the population we have drawn the sample from

Question 3

What are confidence intervals?

Answer 3

An estimated range of values that might contain the true value of the population parameter e.g. population mean height

Question 4

When is a confidence interval statistically significant?

Answer 4

When it does not cross the null value of 0.

If it crosses 0 it is NOT STATISTICALLY SIGNIFICANT

Question 5

What are the three factors needed for correlation analysis?

Answer 5

Direction
Strength
Statistical significance

Question 6

What numbers determine the strength of a linear relationship?

Answer 6

1 or -1: perfect

0. 75-0.99: strong to very strong
1. 50-0.75: moderate to strong
2. 25-0.50: weak to moderate
3. 01-0.25: weak

Question 7

What is relative risk?

Answer 7

The ratio of probability of an outcome occurring in an exposure group compared to the non-exposure group.

Question 8

How would we interpret data when the relative risk is 1?

Answer 8

The risk in the exposure is equal to the risk in the unexposed. There is no association.

Question 9

How would we interpret data when the relative risk is greater than (>) 1?

Answer 9

Positive association. Risk in the exposed is greater than risk is the unexposed. If relative risk is 2.5, the risk is 2.5 times higher in the exposed group.

Question 10

How would we interpret data when the relative risk is less than (

Answer 10

Negative association/protective factor. Risk in exposed is less than risk in unexposed. If relative risk is 0.8, (1-0.8x100) = 20. Risk in the exposed is 20% less than those in the unexposed.

Question 11

What is odds ratio?

Answer 11

Measure of association between exposure and an outcome. Represents the odds that an outcome will occur given a particular exposure, compared to the odds of the outcome occurring in the absence of that exposure.

Question 12

How would we interpret data when the odds ratio is 1?

Answer 12

The odds in the exposure is equal to the odds in the unexposed. There is no association.

Question 13

How would we interpret data when the odds ratio is greater than (>) 1?

Answer 13

Positive association. Odds in the exposed is greater than odds is the unexposed. If odds ratio is 2.5, the odds are 2.5 times higher in the exposed group.

Question 14

How would we interpret data when the odds ratio is less than (

Answer 14

Negative association/protective factor. Odds in exposed is less than odds in unexposed. If odds is 0.8, (1-0.8x100) = 20. Odds in the exposed is 20% less than those in the unexposed.

Question 15

How would we interpret data when the confidence interval for RR/OR crosses 1?

Answer 15

The true RR of the population could be 1, meaning there is no difference between the exposed and unexposed groups. The null hypothesis is accepted and the results are NOT statistically significant.

Question 16

How would we interpret data when the confidence interval for RR/OR does not cross 1?

Answer 16

This means that the true RR of the population can’t be 1, suggesting that the risk is either higher or lower in the exposed compared to the unexposed. This means there is an association, so the null hypothesis is rejected and the result is statistically significant.