Order statistics in the uniform (probability) distribution

Mathmos6
Messages
76
Reaction score
0

Homework Statement


Hi there: I just need someone to tell me if I've made a mistake somewhere in my solution to this:

Suppose that X1 , . . . , X2n+1 are i.i.d. random variables that form a random sample
from the U (0, 1) distribution. Suppose that the values are arranged in increasing order as
Y1 ≤ Y2 ≤ . . . ≤ Y(2n+1) . Calculate expressions for the distribution function and for the probability density function of the random variable Y(n+1) (the sample median).

The Attempt at a Solution


Now if we want Y(n+1) to be in the interval [a,b] we need to have exactly n of the Xi in [0,a] and n+1 in [a,1], but ensure not all of the latter n+1 are in [b,1]. So we have {{2n+1}\choose{n+1}}a^n[(1-a)^n-(1-b)^n] where the (1-a)^n-(1-b)^n ensures not all n+1 of the latter Yi are in the [b,1] interval. But shouldn't there be some sort of symmetry in a and b with this function: shouldn't it be F(b)-F(a) where F'(x) is the pdf of the question? Because it doesn't look much like an F(b)-F(a) to me...

Thanks a lot,

Mathmos6
 
Physics news on Phys.org
Anyone? Any help would be very much appreciated, no matter how small!
 
Prove $$\int\limits_0^{\sqrt2/4}\frac{1}{\sqrt{x-x^2}}\arcsin\sqrt{\frac{(x-1)\left(x-1+x\sqrt{9-16x}\right)}{1-2x}} \, \mathrm dx = \frac{\pi^2}{8}.$$ Let $$I = \int\limits_0^{\sqrt 2 / 4}\frac{1}{\sqrt{x-x^2}}\arcsin\sqrt{\frac{(x-1)\left(x-1+x\sqrt{9-16x}\right)}{1-2x}} \, \mathrm dx. \tag{1}$$ The representation integral of ##\arcsin## is $$\arcsin u = \int\limits_{0}^{1} \frac{\mathrm dt}{\sqrt{1-t^2}}, \qquad 0 \leqslant u \leqslant 1.$$ Plugging identity above into ##(1)## with ##u...
Back
Top