This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Mathematics Department, UCLA T. Richthammer winter 09, midterm 2 Mar 02, 2009 Midterm 2: Math 170A Probability, Sec. 1 1. (5 pts) In a probability course there are 5 excellent students, 10 good students and 5 regular students. Suppose that the chance to get a good result on the second midterm is 100 % for an excellent student, 75 % for a good student and 50 % for a regular student. Is a student with a good result on the exam most likely excellent, good or regular? (Describe an appropriate model and calculate the three probabilities.) Answer: A good model for this situation is a sequential model with S = { e, g, r } { g, b } , where the first projection X 1 describes whether a student is excellent, good or regular, and the second projection X 2 describes whether a student has a good or a bad exam. P (( x 1 , x 2 )) = p x 1 p x 2  x 1 , where p e = 1 4 , p g = 1 2 , p r = 1 4 , p g  e = 1, p g  g = 3 4 and p g  r = 1 2 . Using Bayes formula we get P ( X 1 = e  X 2 = g ) = p e p g  e p e p g  e + p g p g  g + p r p g  r = 1 4 1 1 4 1+ 1 2 3 4 + 1 4 1 2 = 2 2+3+1 = 2 6 , and similarly we get P ( X 1 = g  X 2 = g ) = 3 2+3+1 = 3 6 and P ( X 1 = r  X 2 = g ) = 1 2+3+1 = 1 6 . So most likely the student is good....
View Full
Document
 Winter '10
 RICHTHAMMER

Click to edit the document details