Explore BrainMass

Explore BrainMass

    T distribution and F distribution

    Not what you're looking for? Search our solutions OR ask your own Custom question.

    This content was COPIED from BrainMass.com - View the original, and get the already-completed solution here!

    Please see attached problem, and please explain all aspects of both problems involving T and F distributions.

    a) Z is a standard normal random variable, and U is distributed as X(v)^2. Z and U are independent. State the distribution of T = Z/sqrt(U/v) . What is the distribution of T^2?
    b) Y is a random variable distributed as F(1,5) . Use your answer to part (a), together with the tables of the t (not the F) distribution, to find P(Y > 4) . Also find the value of c such that P(Y > c) = 0.01.

    © BrainMass Inc. brainmass.com December 24, 2021, 10:20 pm ad1c9bdddf
    https://brainmass.com/statistics/f-test/distribution-distribution-465245

    Attachments

    SOLUTION This solution is FREE courtesy of BrainMass!

    a) Z is a standard normal random variable, and U is distributed as X(v)^2. Z and U are independent. State the distribution of T = Z/sqrt(U/v) . What is the distribution of T^2?

    T, by definition, is called the student t distribution of degrees of freedom v (where v is the d.f. of the chi square). Furthermore, if T is a student t distribution of d.f. = v, then T^2 follows an F(1,v), where F is the F distribution.

    b) Y is a random variable distributed as F(1,5) . Use your answer to part (a), together with the tables of the t (not the F) distribution, to find P(Y > 4) . Also find the value of c such that P(Y > c) = 0.01.

    We note that if Y is distributed as F(1,5), and t is distributed as t(5), then t^2 = F.

    Thus, P(Y > 4) = P(t^2 > 4) = P(t > 2) + P(t < 2)

    From a t table (for example here http://en.wikipedia.org/wiki/Student%27s_t-distribution), we can see that

    P(t > 2) = 0.05 (roughly), and since t is symmetric with respect to the origin, P(t^2 > 4) = P(t > 2) + P(t < 2) = 2 X 0.05 = 0.1

    If we wish to find P(Y > c) = 0.01, we are essentially looking for P(t > sqrt c) + P(t < sqrt c) = 0.01.

    Since t is symmetric, each part should equal to 0.005.

    Using the same t table, this number is 4.032. Thus c = 4.032^2 = 16.26.

    You may check the answers by computing the probabilities using the F distribution. Here is a calculator http://stattrek.com/online-calculator/f-distribution.aspx.

    This content was COPIED from BrainMass.com - View the original, and get the already-completed solution here!

    © BrainMass Inc. brainmass.com December 24, 2021, 10:20 pm ad1c9bdddf>
    https://brainmass.com/statistics/f-test/distribution-distribution-465245

    ADVERTISEMENT