Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Kaplan: Biostats and Epidemiology Part I > Chapter 2: Biostats > Flashcards

Chapter 2: Biostats Flashcards

1
Q

What is the definition of an independent event?

A

an event when occurrence of one tells you nothing about the occurrence of the other

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

How do you calculate independent events?

A

by multiplication

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

How can you calculate the chance of a non-independent event?

A

multiply the probability of one event by the probability of the second, assuming that first has occurred.

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

What are mutually exclusive events?

A

events are mutually exclusive if the occurrence of one event precludes the occurrence of the other

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

How do you combine the occurrence of mutually exclusive outcomes?

A

by addition

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

What is a non-mutually exclusive event?
How do you calculate non mutually exclusive events?

A

2 events are non-mutually exclusive if they have at least one outcome in common.

add them together and subtract out of the multiplied probabilities to get the combination of probabilities.

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

What is central tendency?

A

a single value which attempts to describe a set of data by identifying the central (or middle) value within that set.

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

What are types of central tendency measurements?

A

mean
median
mode

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

What is a positive skew?

A

when the tail is on the right and the mean is greater than the median

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

What is a negative skew?

A

when the tail is to the left, and the mean is less than the median

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

Which type of central tendency measurement is a better representation for skewed distributions?

A

median

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

What is a more stable and useful measure of dispersion than range?

A

SD (standard deviation)

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

How do you calculate standard deviation?

A
  1. First subtract the mean from each score to obtain deviations from the mean. This will give us both positive and negative values.
  2. Then square the deviations to make them all positive.
  3. Add the squared deviations together and divide by the number of cases
  4. Take the square root of this average, and the result is the SD
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is the formula for variance?

A

the square of the SD

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

What percentage of cases falls within 1 SD of the mean?

A

68%

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What percentage of cases does a value within 2 SD include?

A

95.5%

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What percentage of cases does a value within 3 SD include?

A

99.7%

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Remember the important values on a SD curve. Draw out.

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What is the purpose of inferential statistics?

A

To determine how likely it is that a given finding is simply the result of chance.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What is a confidence interval?

A

a way of admitting that any measurement from a sample is only an estimate of the population.

(i.e. although the estimate given from the sample is likely to be close, the true values for population may be above or below the sample values)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What is the formula for confidence interval?

A

(mean) study result +/- Z score x standard error (SD/√ (n))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What are the different study results that a confidence interval may be used to assess?

A

means, RR, or any other relevant measure

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What is the requirement for the CI in medicine?

A

at least 95%

24
Q

What is the Z score for 95% CI?

A

1.96 (2)

25
Q

What is the Z score for 99% CI?

A

2.58 (2.5)

26
Q

Difference between SD and standard error?

A

SD measures the variability within a single sample, the standard error estimates the variability between samples

27
Q

The smaller the standard error, the (better or worse) the study?

A

better and more precise

28
Q

What are the 2 factors that affect the standard error?

A

SD
sample size

29
Q

The greater the SD the (higher or lower) the variation in data?

A

higher

30
Q

When comparing 2 groups, any overlap of CI means what?

A

That the groups are not significantly different.

31
Q

What is the significance of a CI that contains 1.0?

A

means there is no statistically significant effect of the exposure

32
Q

What is the significance of a CI that does not include 1?

A

statistically significant data

33
Q

What is the information you can gather if RR is > 1?

A

that there is increased risk of a condition
(read as percent increase so 1.77 RR means one group has 77% more cases than other)

34
Q

If RR is < 1 what is the information that can be gathered?

A

That there is reduced risk of a condition
(So, 0.78 means one group has 22% reduction in risk)

35
Q

What is the null hypothesis?

A

generally, the opposite of what you hope to show

36
Q

What can be inferred from a null hypothesis?

A

that the findings are the result of chance or random factors

37
Q

What are the 2 types of null hypothesis?

A

one tailed
two-tailed

38
Q

What is a one-tailed null hypothesis?

A

one group is greater than or less than the other

(Group A is not less than Group B, or Group A is not greater than Group B)

39
Q

What is a two-tailed hypothesis?

A

2 groups are not the same Group A is not equal to Group B

40
Q

Other name for one-tailed hypothesis?

A

directional or “one-sided”

41
Q

Other name for two tailed hypothesis?

A

nondirectional or “two-sided”

42
Q

What is p-value?

A

a way to interpret output from a statistical test;

computed p-values is compared with the p-value criterion to test statistical significance.

43
Q

If computed value is less than the criterion (p-value); then what can be said?

A

that we have achieved statistical significance

44
Q

What is the p value typically set at in medicine?

A

p ≤ 0.05 (assume this is the criteria unless otherwise specified)

45
Q

What is assumed if p values is less than 0.05?

A

then you can reject the null hypothesis (reached statistical significance)

46
Q

What is assumed if p values are > 0.05?

A

do not reject the null hypothesis

47
Q

What type of risk is associated with rejecting the null hypothesis?

A

Type I error, (α error)

48
Q

What type of risk is associated with not rejecting the null hypothesis?

A

Risk of type II error (β error)

49
Q

Which is considered worse? Type I or Type II error?

A

Type 1 is considered worse than a type II error (error of omission)

50
Q

In essence what is a Type I error?

A

rejecting the null hypothesis when it is really true;

assuming that a drug works when it doesn’t

51
Q

In essence what is a type II error?

A

failing to reject the null hypothesis when it is really false;

asserting the drug does not work when it really does

52
Q

Can the chance of a type II error be directly estimated from the p-value?

A

no

53
Q

What is the purpose of the p value? (List 3)

A
  1. provides criterion for making decisions about the null hypothesis
  2. quantifies the chance that a decision to reject the null hypothesis will be wrong
  3. Tells statistical significance, not clinical significance or likelihood of benefit
54
Q

What can a p-value not tell you?

A
  1. Chance that an individual patient will benefit
  2. percentage of patents who will benefit
  3. degree of benefit expected for a given patient
55
Q

What is the definition of power in statistics? Example?

A

the capacity to detect difference if there is one

(just as a microscope makes it easier to see what is going on in histology)

56
Q

What is the formula for power?

A

Power = 1-β

57
Q

What is the best way to increase statistical power?

A

to increase the sample size

Kaplan: Biostats and Epidemiology Part I (5 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions