Biostats Flashcards

1
Q

How many data points are within 1, 2, and 3 standard deviations?

A
  • 1SD = 68%
  • 2SD = 95%
  • 3SD = 99.7%
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What makes a set of data positively skewed?

A

mean > median > mode (long tail to the right)

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

What makes a set of data negatively skewed?

A

mode > median > mean (long tail to the left)

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

What is a type I error?

A
  • the null is rejected when it is actually true
  • a false positive
  • probability of this equals “a”
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is a type II error?

A
  • the null is accepted when it is actually false
  • a false negative
  • equals beta
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What increases the power of a study?

A

the sample size

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

How is the power of a study calculated?

A

power = 1 - B

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

What do the alpha and beta values represent?

A
  • alpha is the risk of a type I error (rejecting the null when it is true, false positive)
  • beta is the risk of a type II error (accepting the null when it is false, false negative)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What tests are used to compare categorical outcomes between two or more groups?

A
  • chi squared
  • or Fischer’s exact
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is the difference between a multivariate logistic regression versus a multivariate linear regression?

A
  • logistic is for categorical outcomes
  • linear is for numerical outcomes
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is the difference between a cohort study and a case-control study?

A
  • cohort: population of subjects are analyzed to associate certain factors with an outcome, can be retrospective or prospective, gives a relative risk
  • case-control: patients who had an outcome happen are compared to those that didn’t, always retrospective, gives an odds ratio
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is a cohort study?

A
  • looks at a group of subjects to look for factors associated with an outcome
  • can be retrospective or prospective
  • gives a relative risk
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is a case-control study?

A
  • looks at a group of subjects with a particular outcome and compare them to those who didn’t
  • can be only be retrospective
  • gives an odds ratio
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is a propensity-score-matched study?

A

an observational study that attempts to replicate an RCT by selecting cases so that the subjects in both groups are similar across multiple factors

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

What happens in each of the following phases of a drug trial?
- phase 1
- phase 2
- phase 3
- phase 4

A
  • phase 1: tests on a small group of healthy individuals for safety
  • phase 2: tests on a small number of diseased subjects for dosing/efficacy
  • phase 3: RCT to compare to existing therapies
  • phase 4: ongoing long-term evaluation to look at side-effects and efficacy
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How is relative risk calculated?

A
17
Q

How is odds ratio calculated?

A
18
Q

What is sensitivity?

A

the chance that a diseased person will test positive

19
Q

What is specificity?

A

the chance that a healthy person will test negative

20
Q

What is positive predictive value?

A

the chance that a positive test result is correct

21
Q

What is a negative predictive value?

A

the chance that a negative test result is correct

22
Q

How is a receiver-operating curve interpreted?

A

more area under the curve means a better test

23
Q

How is sensitivity calculated?

A

TP / TP + FN

24
Q

How is specificity calculated?

A

TN / TN + FP

25
Q

How is PPV calculated?

A

TP / TP + FP

26
Q

How is NPV calculated?

A

TN / TN + FN

27
Q

What is the Hawthorne effect?

A

subjects behave differently when they know they are being observed

28
Q

What is surveillance bias?

A

falsely thinking a disease is becoming more prevalent when we’re actually just testing for it more frequently

29
Q

What is length-time bias? Lead-time bias?

A
  • length time: falsely thinking screening improves survival when it only detects more benign disease courses
  • lead time: falsely thinking patients live longer when they were actually just diagnosed earlier