Screening & Sampling (5) Flashcards

1
Q

Why screening?

A

one health and public health are focused on prevention, at least early detection

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

What are the desirable qualities of screening tests?

A

condition needs to be important
should have a high benefit-cost ratio
needs to be prevalent
effective treatment should be available
should demonstrate accuracy and precision

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

What is precision?

A

the ability of a measuring instrument to give consistent results on repeated trials

synonym: reliability

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

What is the synonym for precision?

A

reliability

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

What is accuracy?

A

the ability of a measuring instrument to give a true interpretation of reality

synonym: validity

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

What is the synonym for accuracy?

A

validity

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

What is not possible regarding precision versus accuracy?

A

NOT possible to be imprecise and accurate

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

T/F: It is possible to be precise but inaccurate

A

TRUE

bathroom scale can give consistently bad readings

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

What are measures of accuracy?

A

sensitivity
specificity
positive predictive value
negative predictive value

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

What is sensitivity?

A

the ability to detect disease

“positive in disease”

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

What is specificity?

A

the ability to detect the absence of disease

“negative in health”

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

What is positive predictive value (PPV)?

A

the likelihood of “disease” given a positive result

the proportion of true positives among all positive results

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

What is negative predictive value (NPV)?

A

the likelihood of “no disease” given a negative result

the proportion of true negatives among all negative results

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

What is a good screening test?

A

needs to be high in sensitivity
high in specificity
high in predictive value (+)
high in predictive value (-)

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

Screening tests tend to be very _____

A

sensitive

minimizes false negatives (aka, type II error)
therefore, you can be confident you have negative results

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

Confirmatory tests tend to be very ______

A

specific

minimizes false positives (aka, type I error)
therefore, you can be confident in positive results

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

What is the gold standard?

A

the “truth” against which we compare our tests

a definitive diagnostic test that is considered the best available

provides a standard against which sensitivity and specificity are evaluated

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

Sensitivity is [positive/negative] in disease

A

positive

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

What is sensitivity (pt. 2 definition)?

A

the probability of the test being positive when the disease is actually present

20
Q

What is the equation for sensitivity?

A

true positives divided by (true positives + false negatives)

21
Q

Specificity is [positive/negative] in health

A

negative

22
Q

What is specificity (pt. 2 definition)?

A

the probability of a test correctly classifying an individual as “disease free”

true negatives divided by (true negatives + false positives)

23
Q

What is the equation for specificity?

A

true negatives divided by (true negatives + false positives)

24
Q

What is PPV?

A

the probability of a patient actually having a disease when the test is positive

true positives / (true positives + false positives)

25
Q

What is PPV equation?

A

true positives / (true positives + false positives)

26
Q

What is NPV?

A

the probability of a patient being healthy when the test is negative

true negatives / (true negatives + false negatives)

27
Q

What is the equation for NPV?

A

true negatives / (true negatives + false negatives)

28
Q

Learn how to do 2x2 tables and practice problems in lecture

A
29
Q

Which of the following equations determines the ability of a test to predict true positives?
a. TN (TN + FN)
b. TP / (TP + FP)
c. TP / (TP + FN)
d. TN / (TN + FP)

A

c. TP / (TP + FN)

30
Q

The ability of a test to predict true positives is equal to ________

A

the ability to detect disease

31
Q

What generally is a high PPV?

A

common disease
positive result
probably true positive

32
Q

What generally is a low PPV?

A

rare disease
positive result
probably false positive

33
Q

Why a sample instead of entire population?

A

less cost
less field time
acceptable accuracy (with valid methodology)
when it’s impossible to study the whole population

34
Q

What are the two basic types of sampling schemes?

A

random sampling (probability)

non-random sampling (non-probability)

35
Q

What are the types of random sampling?

A

simple random sampling
systematic random sampling
stratified sampling
cluster shampling
multi-stage sampling

36
Q

What are the types of non-random sampling?

A

convenience samples
snowball sampling
purposive sampling (judgmental)
quota sample

37
Q

What is total deviation?

A

difference between average of a sample and actual statistic

38
Q

What is sampling bias?

A

sampled population is not representative of overall population

failure to allow for statistical weighting of samples of unequal probability (non-random sampling)

39
Q

What is sampling error?

A

difference between survey result and population value due to random nature of sample
- unavoidable unless sampling the entire population

influenced by
- sample size
- sampling scheme

40
Q

Sampling [error/bias] can be predicted, calculated, and accounted for

A

sampling bias

41
Q

What are measures of sampling error?

A

confidence limits
standard error
coefficient of variance
P values

42
Q

What is sampling error measures used for?

A

calculate sample size prior to sampling
determine how sure you are of analytic results

43
Q

What is the equation of total deviation?

A

bias + error

44
Q

What is bias?

A

due to mistakes which can be avoided

control and prevention requires careful attention

cannot be measured precisely

45
Q

Sampling error is [avoidable/unavoidable]

A

unavoidable

46
Q
A
47
Q
A