From Statistical Inference by Casella and Berger:

Let $X_1, \dots X_n$ be a random sample from a discrete distribution with $f_X(x_i) = p_i$, where $x_1 \lt x_2 \lt \dots$ are the possible values of $X$ in ascending order. Let $X_{(1)}, \dots, X_{(n)}$ denote the order statistics from the sample. Define $Y_i$ as the number of $X_j$ that are less than or equal to $x_i$. Let $P_0 = 0, P_1 = p_1, \dots, P_i = p_1 + p_2 + \dots + p_i$.

If $\{X_j \le x_i\}$ is a "success" and $\{X_j \gt x_i\}$ is a "failure", then $Y_i$ is binomial with parameters $(n, P_i)$.

Then the event $\{X_{(j)} \le x_i\}$ is equivalent to the event $\{Y_i \ge j\}$

Can someone explain why these two are equivalent?

$\{X_{(j)} \le x_i\} = \{s \in \text{dom}(X_{(j)}) : X_{(j)}(s) \le x_i\}$

$\{Y_i \ge j\} = \{s' \in \text{dom}(Y_i) : Y_i(s') \ge j\}$

I'm having trouble understanding how these random variable functions show this equivalence.


The following statements are equivalent for every $\omega\in\Omega$:

  • $\omega\in\{X_{(j)}\leq x_i\}$
  • $X_{(j)}(\omega)\leq x_i$
  • $|\{k\in\{1,\dots,n\}\mid X_k(\omega)\leq x_i\}|\geq j$
  • $Y_i(\omega)\geq j$
  • $\omega\in\{Y_i\geq j\}$

Looking at the first and the last bullet we conclude that: $$\{X_{(j)}\leq x_i\}=\{Y_i\geq j\}$$


If $X_{(j)}\le x_i$, then clearly all the other smaller order statistics $X_{(1)},\ldots, X_{(j-1)}$ are also less than or equal to $x_i$ (since they are less than or equal to $X_{(j)}$). So at least $j$ of the order statistics are less than or equal to $x_i$, or in other words, $Y_i \ge j$.

Conversely, if $Y_i \ge j$, then by definition at least $j$ of the order statistics are less than or equal to $x_i$. This implies that $X_{(j)} \le x_i$. (Otherwise, $X_{(j)}$ is greater than $x_i$, and then so are all the greater order statistics, so at most $j-1$ order statistics are less than or equal to $x_i$, a contradiction.)

  • $\begingroup$ So are the events $\{X_{(j)} \le x_i\}$ and $\{Y_i \ge j\}$ just single point sets? $\endgroup$ – Oliver G May 30 at 12:49

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.