Biostats Flashcards

0
Q

What does 100% sensitivity indicate?

A

Low false negative rate

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
1
Q

What is the equation for sensitivity?

A

TP/(TP+FN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is sensitivity used for?

A

Used for screening in diseases with low prevalence

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is the equation for specificity?

A

TN/(TN+FP)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What does 100 percent specificity indicate?

A

A low false positive rate

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is the equation for positive predictive value?

A

TP/(TP+FP)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is the positive predictive value?

A

Probability that person actually has the disease given a positive test result

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is negative predictive value?

A

The probability that a person is actually drug free given a negative test result

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is the equation of negative PPV?

A

TN/(FN+TN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is the true positive rate?

A

Sensitivity

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is the true negative rate?

A

Specificity

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is the equation for calculating incidence?

A

Number of new cases/number of people in population at risk (don’t already have the disease)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is the equation for prevalence?

A

Number of cases in a population/total number of people in the population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is the equation for odds ratio?

A

Ad/bc

Used in case-control studies (outcome –> exposure)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is the equation for relative risk?

A

A/(a+b)/c/(c+d)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is relative risk?

A

Risk among exposed/risk among unexposed

16
Q

What is the equation for absolute risk?

A

(A/a+b) - (c/c+d)
(RR-1)/RR
#of adverse events in tx/# of adverse events in placebo

17
Q

What is the number needed to treat?

A

The number of patients who need to be treated for 1 patient to benefit

18
Q

What is the equation for the number needed to treat?

A

1/absolute risk

1/ (event rate -control) - (event rate - tx)

19
Q

What is the number needed to harm?

A

Number of patients who need to be exposed to a risk factor for 1 patient to be harmed

20
Q

What is the equation for the number needed to harm?

A

1/attributable risk = 1/(a/a+b) - (c/c+d)= 1/((RR-1)/RR)

21
Q

What is the equation for event rate?

A

of subjects per tx/total # of subjects

22
Q

What is precision?

A

The consistency, reproduciblity and reliability of a test

23
Q

What lowers precision?

A

Random error

24
What is accuracy of a test?
Validity | Absence of systematic error
25
What is the equation for SEM?
SD / square root sample size | So as sample size increases, standard error of mean decreases
26
What is the null hypothesis?
Says there is no difference btween two groups | P = high
27
What is the p-value?
The likelihood of observing what we did if the null is true. The lower the p-value the more evidence for the alternative hypo
28
What is a type I error?
False positive error Stating there s a difference when there really isn't. P-value is judged against this Ex: convicting an innocent man
29
What is a type II error?
Stating there isn't an effect or different when there is one False negative error Ex: Setting a guilty man free
30
What is power?
The probablility of seeing a difference when one is there Ex: convicting a guilty man = 1- B
31
What does power increase with?
Sample size Expect effect size Precision of measurement
32
What is the equation for confidence interval?
Mean - Z(SEM) to mean + Z(SEM) Z= 1.96 for 95% CI Z = 2.58 for 99% CI
33
What is the equation for likelihood ratio?
Sensitivity/1-specifity | The higher the better likelihood the patient has a disease they are being treated for