Expectation of continuous variable

83 Views Asked by At

CDF of a random variable $X$ is given by table:

$x < 1$ $1 \leq x < 2$ $ 2 \leq x < 3$ $3 \leq x < 4 $ $4 \leq x$
$0$ $0.2$ $0.35$ $0.9$ $1$

Find $E(X)$.

\begin{align*} E(X) &=\int_{-\infty}^{\infty} x f(x) \, dx \\ &=\int_{-\infty}^{0} (x\cdot 0) \, dx + \int_{1}^{2} (x \cdot 0.2) \, dx + \int_{2}^{3} (x \cdot 0.35) \, dx + \int_{3}^{4} (x \cdot 0.9) \, dx + \int_{4}^{\infty} (x\cdot 1) \, dx \\ &= 0+0.3+0.875+3.15 \\ &=4.325 \end{align*}

Why is my answer not correct?

1

There are 1 best solutions below

1
On

You are given the CDF, not the pdf nor pmf.

The CDF functions jumps at certain values and remains constant otherwise. This is a behavior of a discrete random variable.

We can recover the probability as follows:

$$P(X=1)=P(1 \le X<2)-P(X<1)=0.2-0=0.2$$

Note that the probability doesn't increase over $1<X<2$, the random variable take those values with probability $0$.

After recovering the probability (pmf), you can compute the expected value by $$\sum_{i=1}^4 i P(X=i)$$

Alternatively, use $$E[X]=\int_0^\infty (1-F(X))\, dx$$

to compute the expected value.