Lecture 4

Question 1

What is the base rate neglect?

Answer 1

People tend to focus on the evidence provided by the test (specificity and sensitivity) and downplay the precense of prevelance

Question 2

What is sensitivity?

Answer 2

Sensitivity is a quantification of how well a test identifies people that have the disease and are tested positive

Question 3

What is specificity?

Answer 3

A quantification of how well the test identifies people that do NOT have the disease and are tested negative

Question 4

What is a true positive?

Answer 4

It is the proportion of people that are sick and are identified as such by the test

Question 5

What is a false positive (or false alarm)?

Answer 5

Proportion of people that are NOT sick but are identified as sick by the test

Question 6

What is a true negative?

Answer 6

Proportion of people that are NOT sick and are identified as such by the test

Question 7

What is a false negative?

Answer 7

Proportion of people that are sick but are not identified as sick by the test

Question 8

What is bayesian inference?

Answer 8

the outcome of a learning process that is governed by relative predictive success

Question 9

What is the generative model?

Answer 9

State of the world > (predictions) > data

Question 10

What does bayesian wish to do with the generative model? Give an example in the context of sensitiviy, etc.

Answer 10

Invert is so data can predict the state of the world

Instead of “given the disease, what is the probability of a positive test result”&raquo_space; “given the test is positive, what is the probability that I have the disease”

Question 11

What is positive predictive value (ppv)?

Answer 11

Quantification of how well the positive results in a test are actually predictive of disease

Question 12

What is negative predictive value (npv)?

Answer 12

Quantification of how well the negative results in a test are actually predictive of health

Question 13

What happens with the ppv when diseases are very rare?

Answer 13

It decreases drastically because the disease population is incredibly small, so the false positive population has a large effect

Question 14

What does transposing the conditional mean? give example

Answer 14

An error type where a condition P(a!b) is very different when turned around P(b!a)

P(shark attack!blood loss) does not equate P(blood loss!shark attack)

Question 15

What is baye’s rule (words)?

Answer 15

Current knowledge of world = past knowledge about world x predictive updating factor

Question 16

What are the two key ideas of baye’s rule?

Answer 16

1. Hypothesis that predicted the new data well will see a boost in plausibility and hypothesis that predicted it badly will see a decrease in plausibility
2. extraordinary claims require extraordinary evidence aka extreme claims need more data to counteract prior beliefs

Question 17

Which two factors give can make a test provide strong evidence, why may this sometimes still not be enough?

Answer 17

Sensitivity and specificity > still may not be enough to overturn effect of prevalence

Question 18

Baye’s rule (true formula and in context of disease)?

Answer 18

p(θ) x p(data!θ)/p(data) = p(θ!data)

p(D)/p(H) x p(t!D)/p(t!H) = p(D!t)/p(H!t)

Question 19

Theory aside, it is unlikely to know the exact numbers of specificity, etc. how is this “solved”?

Answer 19

With a credible interval, in which (typically) there is a 95% chance that the true number is between point a and b

Question 20

What is the difference between credible and confidence interval?

Answer 20

The confidence interval is the interval which will contain the true value on 95% of occasions if a study were repeated many times, however the credible interval means there is a 95% chance that the true number is between point a and b

Question 21

Calculation: prevalence =.1, sensitivity = .3 and specificity = .99
What is the ppv?

Answer 21

answer is .77 (circa), look at notes for calculation

Question 22

If the “marker” (signal detection theory - SDT) increases, what does this mean?

Answer 22

A higher probability of you having the disease

Question 23

What is the treshold? What does it indicate? SDT

Answer 23

Basically the value you decide to go off of for the marker, it indicates the trade-off between true positives and false positives

Question 24

What is the receiver-operating characteristic (ROC)?

Answer 24

The relationship btwn hit rates (tp) and false alarms (positives)

Question 25

What is the exact relationship between true positives and false positives in the context of moving the treshold?

Answer 25

When true positive rate increases (sensitivity), so do the false positives, which is the trade-off