- #1
broegger
- 257
- 0
I've been staring at this for hours. Any hints?
Let the vector [tex]Y = (Y_1,Y_2,\dots,Y_k)[/tex] have a multinomial distribution with parameters n and [tex]\pi = (\pi_1,\pi_2,\dots,\pi_k)[/tex]:
Show that the conditional distribution of [tex]Y_1[/tex] given [tex]Y_1+Y_2=m[/tex] is binomial with n = m and [tex]\pi = \frac{\pi_1}{\pi_1+\pi_2}[/tex].
I've tried to apply the definition of a conditional probability and sum over the relevant events in the multinomial distribution, but it gives me nothing.
Thanks.
Let the vector [tex]Y = (Y_1,Y_2,\dots,Y_k)[/tex] have a multinomial distribution with parameters n and [tex]\pi = (\pi_1,\pi_2,\dots,\pi_k)[/tex]:
[tex]\sum_{i=1}^{k}Y_i = n, \quad \sum_{i=1}^{k}\pi_i = 1[/tex]
Show that the conditional distribution of [tex]Y_1[/tex] given [tex]Y_1+Y_2=m[/tex] is binomial with n = m and [tex]\pi = \frac{\pi_1}{\pi_1+\pi_2}[/tex].
I've tried to apply the definition of a conditional probability and sum over the relevant events in the multinomial distribution, but it gives me nothing.
Thanks.