Take the 2-minute tour ×
Mathematica Stack Exchange is a question and answer site for users of Mathematica. It's 100% free, no registration required.

I would like to calculate the following with Mathematica:

Let $X$ be a random variable with probability function $$p(x)= \left\{ \begin{matrix} \frac{x}{6} & \text{for }x \in \{1,2,3\}\\ 0 & \text{Otherwise} \end{matrix}\right. $$ Calculate $P(X \leq 2)$, $E(X)$ and $var(x)$

My major problem is to create the probability function with the correct distribution since there haven't been any specific distribution informed in the task. So how do I solve this?

If it is any help, then the results are respectively:

{0.5, 2.333, 0.5556}
share|improve this question
add comment

3 Answers

up vote 6 down vote accepted

This can done as follows (consistent with your own definition):

p=ProbabilityDistribution[x/6, {x, 1, 3, 1}]

This is discrete PMF using your definition. The PMF definition can be displayed:

PDF[p, x]

Your questions follow:

{Probability[x <= 2, x \[Distributed] p], Mean[p], Variance[p]}

yields:

{1/2, 7/3, 5/9}

or numerically:

N@{Probability[x <= 2, x \[Distributed] p], Mean[p], Variance[p]}

yielding:

{0.5, 2.33333, 0.555556}
share|improve this answer
    
Noting the relative ease to calculate: P(X<=2)=1/6+2/6=1/2; E[x]-1/6+2 x 2/6+ 3 x 3/6=14/6=7/3 and similarly variance E[x^2]-E[x]^2 –  ubpdqn Aug 4 '13 at 12:01
add comment
d = ProbabilityDistribution[
  Piecewise[{{x/6, x == 1 || x == 2 || x == 3}}, 0], {x, 0, 10, 1}]

Grid[{{DiscretePlot[Evaluate[PDF[d, x]], {x, 0, 10}, 
    PlotLabel -> "PDF", ExtentSize -> 0.5, 
    PlotStyle -> ColorData[1, 1]],
   DiscretePlot[Evaluate[CDF[d, x]], {x, 0, 10}, PlotLabel -> "CDF", 
    ExtentSize -> Right, PlotStyle -> ColorData[1, 1]]}}]

Mathematica graphics

Mean[d] // N
(*2.33333333333333*)

Variance[d] // N
(*0.555555555555556*)

Probability[x <= 2 , x \[Distributed] d] // N
(*0.5*)

Expectation[x, x \[Distributed] d] // N
(*2.33333333333333*)
share|improve this answer
add comment

You could also use EmpiricalDistribution:

In[1]:= di = EmpiricalDistribution[{1, 2, 3}/6 -> {1, 2, 3}];

In[2]:= {Mean[di], Variance[di], CDF[di, 2]}

Out[2]= {7/3, 5/9, 1/2}

In[3]:= N[%]

Out[3]= {2.33333, 0.555556, 0.5}
share|improve this answer
    
Thank you, I didn't know the function EmpiricalDistribution... With the setup you have created, how would you calculate eg. $P(X_1+X_2 \leq 2)$ ? –  Jens Jensen Aug 4 '13 at 16:40
    
Assuming you mean that $X_1$ and $X_2$ are independent and identically distributed, I would do Probability[x1 + x2 <= 2, {Distributed[x1, di], Distributed[x2, di]}] which yields $\frac{1}{36}$. –  Sasha Aug 4 '13 at 23:56
    
Does this work for mms 8 as well? Because it can't calculate it when I try. –  Jens Jensen Aug 5 '13 at 0:08
    
I was using version 9. –  Sasha Aug 5 '13 at 4:51
add comment

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

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