Chapter 17 Flashcards Preview

Stats Test 3 > Chapter 17 > Flashcards

Flashcards in Chapter 17 Deck (45)
Loading flashcards...
1
Q

Cell A

A

(Top Left) Contains cases in which both the exposure and the response are present (ex. Injured subjects who warmed up); True Positive

2
Q

Cell B

A

(Top Right) Contains cases in which the exposure is present but the response is absent; False Positive

3
Q

Cell C

A

(Lower Left) Contains cases in which the exposure is absent but the response is present; False Negative

4
Q

Cell D

A

(Lower Right) Contains cases in which the exposure and response are both absent; True Negative

5
Q

Relative Risk (risk ratio)

A

Ratio of proportions; A ratio of the rate of exposure in the individuals who have the condition (or response) divided by the rate of exposure in the individuals who do not have the condition

6
Q

A warm up program would be the…

A

Exposure (independent variable)

7
Q

The knee injury is the…

A

Condition (dependent variable)

8
Q

If the warm up program is effective, we would expect the rate of knee injuries to be…

A

Lower in those who do the warm-up than those in the control group (If the program is dangerous we would expect the opposite, if ineffective we would expect the rates of each group to be the same)

9
Q

If the rate of knee injuries is about the same in the two groups then the relative risk should be…

A

Around 1.0, this means that the null hypothesis value for relative risk is 1.0 and we need to assess how different our sample data have to be for us to be confident that the exposure influences the rate of the condition.

10
Q

If the relative risk is 3.0 or 0.33 then we are estimating that the rate of condition is…

A

3 times greater (exposure is increased risk) or one-third of that in the unexposed group (exposure is decreased risk)

11
Q

Relative Risk Formula

A

RR= [A/(A+B)]/[C/(C+D)]

12
Q

What does relative risk tell us? (Ex: .52)

A

The warm-up program was associated with a reduction of risk of approximately 48%

13
Q

Absolute Risk Reduction

A

The difference between the portions of injured subjects in the exposed group and the proportions of injured subjects in the unexposed group

14
Q

Absolute Risk Reduction Formula

A

ARR= [A/(A+B)]-[C/C+D)]

15
Q

What does Absolute Risk Reduction tell us? (Ex: -.13)

A

We can interpret this as meaning that about 13 injuries will be prevented for every 100 individuals who perform the warm-up program

16
Q

Number Needed to Treat

A

The inverse of the Absolute Risk Reduction

17
Q

Number Needed to Treat Formula

A

NNT= 1/ARR

18
Q

What does Number Needed to Treat tell us? (Ex: 7.69)

A

Indicates that we need to treat about 7.69 individuals with a warm-up program to prevent one injury

19
Q

Odds Ratio (relative odds)

A

Calculate a ratio of odds; used in case studies that the subjects already have the condition (Odds=p/1-p) P= the probability of the outcome in question

20
Q

Odds ratio greater or less than 1.0

A

Greater than 1.0 suggests the exposure is delirious because the cases have higher odds of experiencing it; Less than 1.0 suggests that the expose is protective because the controls have higher odds of being exposed

21
Q

Odds Ratio Formula

A

OR= (A/C)/(B/D)

22
Q

What does Odds Ratio tell us? (Ex: .375)

A

The odds of a case having polymorphism is about 1/2 of the odds of a case having it

23
Q

Sensitivity

A

The true positive rate and is an index that quantifies how well a diagnostic test identifies those with the condition

24
Q

Specificity

A

The true negative rate and is an index of how well a diagnostic test identifies those without the condition

25
Q

Sensitivity

A

A/(A+C)

26
Q

What does Sensitivity tell us? (Ex: .80)

A

Of all the individuals with a torn ACL, the Lachman test correctly identified 80% of them

27
Q

Specificity Formula

A

=D/(B+D)

28
Q

What does Specificity tell us? (Ex: .55)

A

Of all the individuals who do not have a torn ACL, the Lachman test correctly identified 55% of them as not having torn the ACL.

29
Q

Positive Predictive Value

A

the proportion of individuals with a positive test who really do have the condition.

30
Q

Positive Predictive Value Formula

A

A/(A + B)

31
Q

What does Positive Predictive Value tell us? (Ex: .64)

A

About 64% of the individuals who have a positive Lachman test really do have a torn ACL. T; If that person has a positive Lachman test, the probability that that person has a torn ACL is about 64%.

32
Q

Negative Predictive Value

A

The proportion of individuals with a negative test who really do not have the condition. (Specificity is the proportion of individuals who do not have the condition who have a negative test)

33
Q

Negative Predictive Value Formula

A

D/(C + D).

34
Q

What does Negative Predictive Value tell us? (Ex: .73)

A

About 73% of individuals with a negative Lachman test do not have a torn ACL; For an individual with a suspected ACL tear, if the subsequent Lachman test is negative, then that person has about a 73% probability of not having a torn ACL. Both positive and negative p

35
Q

Positive Likelihood Ratio

A

A ratio of probabilities in which the numerator is the probability of a positive test in a person with the condition and the denominator is the probability of a positive test in a person without the condition.

36
Q

Positive Likelihood Ratio Formula

A

[A/(A + C)]/[B/(B + D)].

37
Q

What does Positive Likelihood Ratio tell us? (Ex: 1.78)

A

Individuals with a torn ACL are 1.78 times more likely to have a positive Lachman test than are individuals who do not have a torn ACL. (positive likelihood ratios greater than 10 are considered strong evidence that the condition is present.)

38
Q

Negative Likelihood Ratio

A

A ratio of probabilities in which the numera-tor is the probability of a negative test in an individual with the condition and the denominator is the probability of a negative test in an individual without the condition.

39
Q

Negative Likelihood Ratio Formula

A

[C/(A + C)]/[D/(B + D)].

40
Q

What does Negative Likelihood Ratio tell us? (Ex: .52)

A

Individuals with a torn ACL are about one-third as likely to have a negative Lachman test as are those who do not have a torn ACL.

41
Q

What does the use of likelihood ratios allow for?

A

Allows clinicians to make probabilistic statements about an individual’s test results in manner that is different than statements that can be made with predictive values. (if the pretest probability of the condition is known, then based on the test result (positive or negative) and the applicable likelihood ratio, a posttest probability of the condition can be estimated)

42
Q

Postest Probability Formula

A

Posttest odds = Pretest odds × Likelihood ratio.

43
Q

What does Postest Probability tell us? (Ex: 7.4)

A

For every one injured athlete with a positive Lachman test that does not have a torn ACL, about 7.4 injured athletes with a positive Lachman test do have a torn ACL.

44
Q

Convert the Posttest Odds to a Posttest Probability Formula

A

p = odds/(1 + odds).

45
Q

What can be used to allow clinicians for probabilistic estimates for individual athletes and patients?

A

predictive values and likelihood ratios