continuous random variable with cdf [closed]

Let Y be a continuous random variable with cumulative distribution function. $$F (x) = \begin{cases} 0 &\text{ if } x < 1 \\ 1 - \dfrac{1}{x^2} &\text{ if } x ≥ 1 \end{cases}$$

and probability density function $$f(y) = \begin{cases} \dfrac{2}{y^3} &\text{ if } y ≥ 1 \\\\ 0 &\text{ otherwise} \end{cases}$$

(a) Find the median of Y.

(b) Find the interquartile range of Y.

(c) Why is the expected value of Y less than, equal to, or greater than its median?

closed as off-topic by heropup, BruceET, iadvd, Leucippus, NamasteFeb 17 '17 at 0:53

This question appears to be off-topic. The users who voted to close gave this specific reason:

• "This question is missing context or other details: Please improve the question by providing additional context, which ideally includes your thoughts on the problem and any attempts you have made to solve it. This information helps others identify where you have difficulties and helps them write answers appropriate to your experience level." – heropup, BruceET, iadvd, Leucippus, Namaste
If this question can be reworded to fit the rules in the help center, please edit the question.

• Just need to use the definition in each case, what have you tried? – Smurf Feb 16 '17 at 20:10
• stuck in integeration! – tesla Feb 16 '17 at 20:19
• All three of your posts so far have been asked without demonstrating any of your own effort, and more curiously, have specifically asked for help from a particular user on this site. Math.SE is not your personal question-answering service and users are not at your every beck and call. Your behavior suggests you created a second account after having your previous account locked for failing to adhere to community guidelines. – heropup Feb 16 '17 at 20:21
• Pareto distribution.. Quartiles and median in Answer of @Measure_theory correct: In R: x = c(2, sqrt(2), sqrt(4/3)); 1 - 1 /x^2 returns 0.75, 0.50, 0.25. Try integration for mean again, note limits $\int_1^\infty.$ Check answ in Wilkipedia link. And, I agree with previous comment that you need to show more initiative before posting hwk problems. – BruceET Feb 16 '17 at 20:42

For (a), note that the median is the point where $F(x) = 0.5$. So we need to solve for $x$ in $$0.50 = 1-\frac{1}{x^{2}}$$

multiplying through by $x^2$ and rearranging yields $$(1-0.50)x^2 = 1 = 0.5x^2$$

which gives us $x = \sqrt2$

For (b): the interquartile range can be found in a similar manner by subtracting the third quantile (where $F(x) = 0.75$) from the second (where $F(x) = 0.25$)

Using the same approach as before, we have $$(1-0.75)x^2 = 1\Rightarrow x = 2$$ and $$(1-0.25)x^2 = 1\Rightarrow x = \sqrt{1.333}$$

which gives us $2 - \sqrt{1.333}$

For (c), I would first calculate the mean and variance and then use the skewness formula $\mathbb{E}\bigg[\bigg(\frac{X-\mu}{\sigma}\bigg)\bigg]^3$ where $\mu$ is the mean and $\sigma$ is the standard deviation.

The sign of the above will tell you whether the mean is below the medium or above. See here

• That's probably a good thing to check for in general but this definitely look likes a homework question and I presume so. This should be easy since the PDF is a polynomial. – measure_theory Feb 16 '17 at 20:27
• Yes, need to check 3rd moment before recommending it: $\int_1^\infty x^3(2/x^3)\,dx = ??.$ Commonly, right skewed distributions have $\mu > \eta$ (pop mean exceeding pop median). Quartiles and median OK (+1). – BruceET Feb 16 '17 at 20:53
• how to solve the integeration .. – tesla Feb 18 '17 at 22:36