General Biostats Flashcards

1
Q

Sensitivity is best described as:

A

True Positive

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

False negative probability can be calculated from sensitivity by:

A

1-sensitivity

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

Specificity is best described as:

A

True negative.

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

The false positive probability can be calculated by

A

1-specificity

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

Define Recall Bias

A

Cases are more likely to recall exposures than controls.

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

relative risk

A

RR = experimental event rate / control event rate

A/(A+B) / C/(C+D)

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

Regression to the mean

A

Tendency for extreme values of a variable to fall closer to the group mean when retested

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

Hawthorne Effect

A

The tendency of subjects to act differently because they are being studied.

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

Why use person years?

A

Accounts for variable follow up periods and number under observation.

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

___ percent of the population falls within 1 standard deviation on the curve.

A

68%

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

2 standard deviations contain

A

95% of the population

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

3 standard deviations?

A

1%

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

chi-square test

A
  • analyze categorical data
  • no cell has less than 1
  • no more than 20% of cells have less than five
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

fischer’s exact test

A

same as for chi-sq but w/ SMALL sample size

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

McNemars test

A
  • paired dichotomous data without fractions
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

student t test

A
  • independent continuous variables
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Differential misclassification is___

A

Not random

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

Differential misclassification cause an ____of an association.

A

overestimate

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

Non-differential classification is ____

A

random

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

Non-differential misclassification causes an ___ of an association.

A

under estimation

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

Selection bias

A

systematic errors in the way subjects are included in a study.

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

Odds ratio is good for _____ conditions.

A

Rare

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

With rare conditions, the OR approaches__

A

RR

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

The lower the confidence, the ___ the confidence interval.

A

narrower

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

Increasing the sample size ____ the confidence interval

A

Decreases

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

The probability that two independent events will occur is:

A

p(A) + p(B) - p(A+B)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

Case control studies are best suited for ___ conditions.

A

Rare

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

Length bias

A

Rapidly progressing cancer are less likely to be detected when asymptomatic.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

Lead time bias

A

screening gives the appearance that the person diagnosed earlier survived longer. Even when survival is to same age

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

Information bias

A

systematic difference in the way data is collected

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

Surveillance bias

A

over detection of disease because one population is monitor more closely

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

Positive predictive value

A

Measures how often the test is right when positive or negative

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

Positive predictive value

A

TP/(TP+FP)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

Negative predictive value

A

TN/(TN+FN)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
35
Q

You cannot calculate predictive value of a test without__

A

prevalence

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
36
Q

Sensitivity and specificity ___ depend on prevalence

A

do not

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
37
Q

Decreasing prevalence causes _____ in positive predictive value

A

decrease

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
38
Q

Decreasing prevalence causes ____in negative predictive value

A

increase

39
Q

Correlation studies

A

compare disease frequencies among entire populations

40
Q

Attributable risk

A

Ie - Iue

41
Q

Attributable risk percentage

A

(Ie-Iue)/Ie

42
Q

Population attributable risk

A

Attributable risk X Prevalence

43
Q

Intent to treat analysis

A

The inclusion of all subjects randomized to drug and placebo.

44
Q

Cross-sectional study

A

study of a population at one point in time

45
Q

Prevalence

A

of cases/population at risk

46
Q

categorized data

A

ie. ill vs not ill

47
Q

Power ___ not important with significant results.

A

is not

48
Q

secondary attack rate

A

of new cases among those exposed to index case/# of all those exposed to index case

49
Q

vaccine efficacy

A

(Iuv - Iv)/Iuv

50
Q

In decision analysis, utilities refers to

A

the relative values placed on outcomes by patients

51
Q

A method of controlling for confounding after data collection is

A

stratification and multivariate analysis

52
Q

A bar chart is useful for

A

depicting the frequency of nominal or ordinal data

53
Q

A pie chart is useful for

A

depicting frequency of categorical data

54
Q

A frequency polygon is useful for

A

illustrating frequency distributions for discrete or continuous data. Overlapping.

55
Q

Line graphs are useful for

A

presenting continuous data over time.

56
Q

A curve skewed to the left has a mean ___ than the median

A

Less, closer to the tail,or to the left.

57
Q

A curve skewed to the right has a mean ____to the median

A

Right, or greater than the median. Again, closer to the tail.

58
Q

Curves are skewed to the

A

tail

59
Q

Is there a test 100% sensitive or specific?

A

No.

60
Q

The x axis is Receiver-operator curves is

A

1-specificity.

61
Q

If alpha is set to .10, then the confidence interval is

A

90%

62
Q

Linear regression examines

A

the association between two continuous variables.

63
Q

Multiple regression is used to

A

examine the relationship between multiple dependent variables and the independent variable

64
Q

Logistic regression is used

A

when the dependent variable is is dichotomous.

65
Q

Correlation analysis is used

A

to determine a linear relationship between continuous variables in correlation studies of populations.

66
Q

Which gives a better picture of an intervention’s impact: ARR or RRR? Why?

A

AR. RR depends on mortality in control group. Low mortality in a control group means little improvement with intervention, even if RRR is large.

67
Q

Numbers needed to treat =

A

1/ARR

68
Q

If the crude and adjusted rates are the same, the stratification variable is

A

not a confounder.

69
Q

The Kappa statistic is used

A

to assess interrater/intrarater reliability.

70
Q

Wilcoxon rank sum tests, Wilcoxon signed rank test, and signed tests are used to

A

study non normally distributed sample sizes

71
Q

Kaplan-Meier Survival Curves

A

Estimates the probability of survival each time an event occurs.

72
Q

Advantage of Kaplan Meier curve:

A

Takes into account “censored data” which occurs if a patient withdraws before the outcome is reached.

73
Q

Log rank test

A

Compares the survival distributions of two samples. Non parametric.

74
Q

Hazard ratio

A

Risk of an event an instantaneous point in time between two groups.

75
Q

Cox proportional hazards model

A

Multivariate survival analysis used in studies in which participants are followed for unequal amounts of time.

76
Q

Cox proportional hazards model relies on:

A

the assumption that the proportional effect of study factors does not change over time

77
Q

Why are randomized clustered samples not as good as individual randomization?

A

Similarities of individuals in the clusters reduces variability, there by reducing the power.

78
Q

Clustered data results when:

A

preexisting group structure is used to select participants, but the researcher is interested in individual level data

79
Q

intercluster correlation coeffiient (rho) is a measure of

A

Relatedness of clustered data, can range from 0-1, 1 is all the same.

80
Q

Nominal Data

A

No intrinsic order. Ie Race.

81
Q

Sensitivity

A

Positive in disease

82
Q

Specificity

A

Negative in health.

83
Q

Ordinal

A

Have an order, but no set numerical relationship between values. “Worse, same..”

84
Q

Interval

A

Ordered with numerical units, but no actual zero. Dividing them does not make sense. Ie one date of birth cannot be twice another date of birth.

85
Q

Ratio scales

A

Order, numerical, and a real zero. Can divide them. Kelvin.

86
Q

Sensitivity

A

Chances of test being positive in those with disease.

87
Q

Specificity

A

Chances of test being negative in those without disease.

88
Q

Calculate TP:

A

Sensitivity x prevalence

89
Q

Calculate TN

A

Specificity x (1-prevalence)

90
Q

Calculate false positive

A

(1-specificity)x(1-prevalence)

91
Q

Calculate false negative

A

(1-sensitivity)x prevalence

92
Q

In a normal distribution, the mean, median, and mode are?

A

The same

93
Q

What happens to PPV as prevalence increases.

A

It increases.