# Solving relations between statistics

**URL:** <https://community.wolfram.com/t/solving-relations-between-statistics/7709>\
**Category:** Questions\
**Tags:** equation-solving\
**Created:** [January 19, 2016, 8:18am UTC](https://community.wolfram.com/t/solving-relations-between-statistics/7709 "2016-01-19T08:18:24Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![albert](https://avatars.discourse-cdn.com/v4/letter/a/48db29/32.png) [@albert](https://community.wolfram.com/u/albert)\
**Post date:** [January 19, 2016, 8:18am UTC](https://community.wolfram.com/t/solving-relations-between-statistics/7709/1 "2016-01-19T08:18:24Z")

</div>

Good day to all the members.  
I am rather new to Mathematica and I apologise if this is a redundant question or if it has been answered elsewhere on this forum. (I searched but could not find it)  
While I have used the Solve function to solve some equations they have always been in the traditional form given by the help function.

Is it possible to solve 1 set of statistics in terms of another set, when they both depend on the same variables.

For example:

```
U1 = Y1/(Y1 + Y2 + Y3)

U2 = Y2/(Y1 + Y2 + Y3)

V1 = Y1/Y3

V2= Y2/Y3

Solve[{V1, V2}, {U1, U2}]

```

I know from doing the calculations by hand that the solution is

```
U1=V1/(1+V1+V2)

U2=V2/(1+V1+V2)

```

but I have too many of these equations to do them all by hand.

Thanks for any help

---

<div class="post-metadata">

**Author:** ![sghuisman](https://yyz1.discourse-cdn.com/wolfram/user_avatar/community.wolfram.com/sghuisman/32/27850_2.png) [@sghuisman](https://community.wolfram.com/u/sghuisman)\
**Post date:** [January 19, 2016, 10:31am UTC](https://community.wolfram.com/t/solving-relations-between-statistics/7709/2 "2016-01-19T10:31:49Z")

</div>

Hi Albert,

You want to ‘eliminate’ Y1 and Y2 from your equations if I understood correctly. This can be done using Eliminate:

```
Eliminate[{U1 == Y1/(Y1 + Y2 + Y3), U2 == Y2/(Y1 + Y2 + Y3), V1 == Y1/Y3, V2 == Y2/Y3}, {Y1, Y2}]

```

this will automatically look at all the cases, also the case for which `Y3 = 0`. You can use Refine to simplify your expressions based on assumptions…

---

<div class="post-metadata">

**Author:** ![albert](https://avatars.discourse-cdn.com/v4/letter/a/48db29/32.png) [@albert](https://community.wolfram.com/u/albert)\
**Post date:** [March 1, 2016, 1:15pm UTC](https://community.wolfram.com/t/solving-relations-between-statistics/7709/3 "2016-03-01T13:15:43Z")

</div>

Thank you very much! Solved my problem instantly
