Let D denote the event that a subject has a certain disease. Let S denote the event that a subject is sampled from the population under study. Let the probabilities related with this sampling be r0 and r1 where r0 = P(S|D) and r1= P(S|Dc). Note that Dc denotes the complement of D, which refers to the event that a subject does not have the disease under study. Suppose a logistic regression holds for probability of the disease, that is P(D|x) = exp(α+Xβ) / (1+exp(α+Xβ)). i. Using Bayes Theorem, show that P(D|S,x) also follows a logistic regression model with the same effect coefficients β but with a different intercept, namely α* = α +log(r0/ r1). ii. Comment on what the result in (i) means in practice?
Let D denote the event that a subject has a certain disease. Let S denote the event that a subject is sampled from the population under study. Let the probabilities related with this sampling be r0 and r1 where r0 = P(S|D) and r1= P(S|Dc). Note that Dc denotes the complement of D, which refers to the event that a subject does not have the disease under study. Suppose a logistic regression holds for probability of the disease, that is P(D|x) = exp(α+Xβ) / (1+exp(α+Xβ)). i. Using Bayes Theorem, show that P(D|S,x) also follows a logistic regression model with the same effect coefficients β but with a different intercept, namely α* = α +log(r0/ r1). ii. Comment on what the result in (i) means in practice?
Algebra & Trigonometry with Analytic Geometry
13th Edition
ISBN:9781133382119
Author:Swokowski
Publisher:Swokowski
Chapter10: Sequences, Series, And Probability
Section10.8: Probability
Problem 29E
Related questions
Question
. Let D denote the event that a subject has a certain disease. Let S denote the event that a subject is sampled from the population under study. Let the probabilities related with this sampling be r0 and r1 where r0 = P(S|D) and r1= P(S|Dc). Note that Dc denotes the complement of D, which refers to the event that a subject does not have the disease under study. Suppose a logistic regression holds for probability of the disease, that is P(D|x) = exp(α+Xβ) / (1+exp(α+Xβ)).
i. Using Bayes Theorem, show that P(D|S,x) also follows a logistic regression model with the same effect coefficients β but with a different intercept, namely α* = α +log(r0/ r1).
ii. Comment on what the result in (i) means in practice?
Expert Solution
This question has been solved!
Explore an expertly crafted, step-by-step solution for a thorough understanding of key concepts.
Step by step
Solved in 2 steps
Recommended textbooks for you
Algebra & Trigonometry with Analytic Geometry
Algebra
ISBN:
9781133382119
Author:
Swokowski
Publisher:
Cengage
Glencoe Algebra 1, Student Edition, 9780079039897…
Algebra
ISBN:
9780079039897
Author:
Carter
Publisher:
McGraw Hill
Algebra & Trigonometry with Analytic Geometry
Algebra
ISBN:
9781133382119
Author:
Swokowski
Publisher:
Cengage
Glencoe Algebra 1, Student Edition, 9780079039897…
Algebra
ISBN:
9780079039897
Author:
Carter
Publisher:
McGraw Hill