Stats Flashcards

1
Q

What is the sensitivity of an assay and how is it calculated?

A

The proportion of positive results correctly identified by a test, calculated as follows:

= True positives / (True positives + False negatives) x 100%

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

What is the specificity of an assay and how is it calculated?

A

The proportion of negative results correctly identified by a test, calculated as follows:

= True negatives / (True negatives + False positives) x 100%

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

What is the accuracy of an assay and how is it calculated?

A

How often a test gives the correct result (either positive or negative), calculated as follows:

= True results / (True results + False results) x 100%

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

What is the trueness of an assay?

A

For quantitative tests, where the result can have any value between two limits, this is a measurement of how close the test result is to the reference value. Any deviation from the reference value indicates a systematic error or bias.

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

What is the precision of an assay?

A

The degree to which separate measurements differ, which indicates how well a single test result is representative of a number of repeats. Precision can be expressed as the standard deviation of a set of replicate results or as a confidence interval around the mean result.

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

What is the repeatability of an assay?

A

The closeness of agreement of results obtained when using the same samples under the same test conditions (technicians/analysts, instruments, reagent lots etc.) and repeated over a short period of time.
This essentially represents ‘within-run’ precision.

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

What is the reproducibility of an assay?

A

The closeness of agreement of results obtained when using the same samples under different test conditions (technicians/analysts, instruments, reagent lots etc.).
This essentially represents ‘between-run’ precision

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

What is the positive predictive value and how is it calculated?

A

The positive predictive value is a measure of the chance that a positive result is correct and is calculated as follows:
True positives / (True positives + False Positives )

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

What is the negative predictive value and how is it calculated?

A

The negative predictive value is a measure of the chance that a negative result is correct and is calculated as follows:
True negatives / (True negatives + False negatives )

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

What is the mode?

A

The most frequent observation

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

What is the robustness of a test?

A

Reliability of the test, in terms of how well it maintains precision, when certain variables (including test conditions) are changed. Examples of such variables are sample type and sample quality, as well as technicians/analysts, instruments, reagent lots etc.

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

What is the limit of detection?

A

For quantitative tests, where the result can have any value between two limits, this is the lowest quantity of analyte that can be reliably detected by the test.

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

What is the limit of quantification?

A

The extremity at which accurate quantification can still be achieved.

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

What are type I and type II error?

A

Type I: Rejecting the null hypothesis when it’s true.

Type II: Not rejecting the null hypothesis when it’s false

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

What is a p value?

A

The probability of finding the observed, or more extreme, results when the null hypothesis (H0) of a study is true

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

When should you use non-parametric testing?

A
  • No assumption that the underlying distribution comes from a specific family.
  • Very small sample size
  • Lots of outliers
  • Data is better represented by the median.