2
$\begingroup$

I need help with a particular problem in my statistics textbook.

Imagine rolling a normal die with six sides $100$ times. I need to find the probability that the sum of the values rolled in those $100$ times is less than $300$.

So for the sum, we want to look at the random variable $Y=X_1+X_2+...+X_{100}$. Every $X_i$ should have the same mean and variance, let's say the mean is $\mu$ and the variance is $\sigma^2$. Then the mean of $Y$ would be $100\mu$ and the variance is $100\sigma^2$.

We want to find $P(Y<300)$. Using a continuity correction, we want to look at $P(Y<300.5)$. Then $P(Y<300.5)=P(Z<\frac{300.5-100\mu}{\sqrt{100 \sigma^2}})$. I could find the answer from here.

However, I am having a hard time figuring out what $\mu$ and $\sigma^2$ should equal. I know that $\mu=np$ and $\sigma^2=np(1-p)$ for a normal approximation. But I don't know what $n$ and $p$ would be for the $X_1, X_2, ..., X_{100}$ or if that is the correct way to go about this problem.

Any help is appreciated, thank you.

$\endgroup$
3
$\begingroup$

Finding $\mu$ and $\sigma$ requires you to make use of the properties of the expectation and variance, namely:

$$ \mu = \mathbb{E}[Y] = \mathbb{E}[X_1 + \dots + X_{100}] = \mathbb{E}[X_1] + \dots + \mathbb{E}[X_{100}] = 100 \frac{1+2+3+4+5+6}{6} = 350 \\ \sigma^2 = \mathrm{Var}[Y] = \mathrm{Var}[X_1 + \dots + X_{100}] = \mathrm{Var}[X_1] + \dots + \mathrm{Var}[X_{100}] = 100\left(\frac{91}{6} - 3.5^2\right) = 2741.6666... $$

The variance of $X$ comes from first principles, i.e. $\mathbb{E}[X^2] - (\mathbb{E}[X])^2$

$\endgroup$
2
$\begingroup$

Ask yourself this: where did the formulas $\mu=np$ and $\sigma^2=np(1-p)$ come from?

If you got them in the usual way, they are formulas for the mean and variance of a binomial distribution, and they come from the fact that the binomial distribution is the sum of $n$ independent Bernoulli variables, each of which is $1$ with probability $p.$ Each of those Bernoulli variables has mean $p$ and variance $p(1-p),$ and there are $n$ of them ...

But dice are not Bernoulli variables; they don't have mean $p$ and variance $p(1-p),$ and your formula doesn't apply. But you can easily find the mean and variance of one six-sided die -- just use the definitions of mean and variance for a discrete variable, write out the possible values of the die and their probabilities, plug these into the definitions and add up the values -- so you should be able to find the mean and variance of the sum of the $100$ dice.

$\endgroup$
2
$\begingroup$

The mean roll of one die is $\frac 16(1+2+3+4+5+6)=3.5$. By the linearity of expectation, the mean of the sum of $100$ rolls is ???. You should compute the variance of the roll of one die. The variance of the sum is the sum of the variances of the individual rolls.

$\endgroup$

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.