9: Statistical Measures

Question 1

3 Effect Measures

Answer 1

1. Attributable Fractions
2. Risk and Rate Differences
3. Risk and Rate Ratio

Question 2

Attributable Fractions

Answer 2

Measure the fraction of cases due to a factor

Question 3

Risk and Rate Differences

Answer 3

Measure the amount a factor adds to the risk or rate of a disease

Question 4

Risk and Rate Ratio

Answer 4

Measure the amount by which a factor multiples the risk or rate of disease

Question 5

Absolute Effects

Answer 5

Comparison of differences in measure of association or attributable risk. Rate Difference, Risk Difference, Population Risk Difference

Question 6

Relative Effects

Answer 6

Compare an absolute effect to a baseline reading. Relative Risk, Risk Ratio, Etiologic Fraction, Population Etiologic Fraction

Question 7

Risk Difference (Attributable Risk)

Answer 7

The difference between the incidence rate of disease in the exposed group (Ie) and the incidence rate of disease in the non-exposed group (Ine). A way to estimate the realistic potential impact of removing an exposure from the population. Risk Difference=Ie-Ine

Question 8

Population Risk Difference

Answer 8

Measures the benefit to the population derived by modifying a risk factor. The difference between the rate (risk) of disease in the non-exposed segment of the population (Ine) and the overall rate (Ip). Population Risk Difference=Ip-Ine OR (Ie)(Pe)-(Ine)(Pne) where P is proportion of population exposed or not exposed

Question 9

Etiologic Fraction (Attributable Proportion/Fraction)

Answer 9

Measures the proportion of disease in the exposed group that is due to the exposure. Etiologic Fraction=(Ie-Ine)/Ie=(RR-1)/RR

Question 10

Population Etiologic Fraction (Attributable Fraction in the Population)

Answer 10

Indication of the effect of removing a particular exposure on the burden of disease in the population. Population Etiologic Fraction=(Ip-Ine)/Ip x 100=[Pe(RR-1)]/[Pe(RR-1)+1]

Question 11

Rare exposure with high RR for disease can account for most cases but removal of exposure…

Answer 11

will have little impact on the overall incidence of disease

Question 12

Impact of exposure on a population depends on:

Answer 12

1. strength of the association between exposure and resulting disease
2. Overall incidence rate of disease in the population
3. Prevalence of the exposure in the population

Question 13

What exposures have a major impact on public health?

Answer 13

ones of high prevalence and low RR

Question 14

Null Hypothesis

Answer 14

states that there is no difference among the groups being compared (exposure has no effect on disease)

Question 15

Significance Tests

Answer 15

Used to decide whether to reject or fail to reject a null hypothesis.

Question 16

Significance Level

Answer 16

the chance of rejecting the null hypothesis when, in fact, it is true

Question 17

P Value

Answer 17

Indicates the probability that the findings observed could have occurred by chance alone.

Question 18

Possible meaning of nonsignificant differences:

Answer 18

a nonsignificant difference is not necessarily attributable to chance alone. For studies with a small sample size the sampling error may be large, which can lead to a nonsignificant test even if the observed difference is caused by a real effect. Can be corrected by increasing sample size.

Question 19

Confidence Interval (CI)

Answer 19

A computed interval of values that, with a given probability, contains the true value of the population parameter. Influenced by variability of the data and sample size

Question 20

Parameter Estimates for CI

Answer 20

a mean, OR, RR, or incidence rate

Question 21

Clinical vs. Statistical Significance

Answer 21

While small differences in disease frequency or low magnitudes of relative risk (RR) may be significant, they may have no clinical significance. Conversely, with small sample sizes, large differences or measures of effect may be clinically important.

Question 22

Statistical Power

Answer 22

The ability of a study to demonstrate an association if one exists.

Question 23

Power of study is determined by:

Answer 23

1. Frequency of the condition under study
2. magnitude of the effect
3. Study Design
4. Sample Size

Question 24

Evaluating Epidemiologic Associations with 5 questions

Answer 24

1. Could the association have been observed by chance?
2. Could the association be due to bias?
3. Could other confounding variables have accounted for the observed relationship?
4. To whom does this association apply?
5. Does the association represent a cause-and-effect relationship?

Question 25

Associations between Factors and Outcomes

Answer 25

• not statistically associated (independent)

- statistically associated

Question 26

Statistically Associated Relationships

Answer 26

• non-causal

- causal (indirect vs. direct)

Question 27

Multiple Causality

Answer 27

requirement that more than one factor be present for disease to develop