okay, so I've created a problem in stats to keep me entertained but i'm not sure how to approach it.
find a general equation for![]()
what I was thinking of doing was saying that. Then I would work out the probability for 2 of the possible values, multiply them together and assume that the last distributional probability will be one and then divide by the A probability.
Only issue is that I feel as if that isn't correct or if it is that it is a lot of work and that there should be a simpler way.
-
Aph
- Follow
- 118 followers
- 22 badges
- Send a private message to Aph
- Very Important Poster
- Thread Starter
Offline22ReputationRep:Very Important Poster- Follow
- 1
- 01-03-2016 10:08
Last edited by Aph; 01-03-2016 at 10:11. -
- Follow
- 2
- 01-03-2016 10:38
-
Gregorius
- Follow
- 20 followers
- 13 badges
- Send a private message to Gregorius
Online13ReputationRep:- Follow
- 3
- 01-03-2016 10:38
(Original post by Aph)
okay, so I've created a problem in stats to keep me entertained but i'm not sure how to approach it.
find a general equation for
what I was thinking of doing was saying that. Then I would work out the probability for 2 of the possible values, multiply them together and assume that the last distributional probability will be one and then divide by the A probability.
Only issue is that I feel as if that isn't correct or if it is that it is a lot of work and that there should be a simpler way.
I think this will work by observing that
P(X+Y = a | X+Y+Z=p) is simply
P((X+Y) = a | (X+Y) + Z = p)
That is, condition the binomial RV (X+Y) on the sum (X+Y) + Z. -
Aph
- Follow
- 118 followers
- 22 badges
- Send a private message to Aph
- Very Important Poster
- Thread Starter
Offline22ReputationRep:Very Important Poster- Follow
- 4
- 01-03-2016 10:47
(Original post by Zacken)
I take it that you're assuming all three are independent? -
Gregorius
- Follow
- 20 followers
- 13 badges
- Send a private message to Gregorius
Online13ReputationRep:- Follow
- 5
- 01-03-2016 10:57
(Original post by Aph)
Yes, although in reality they likely won't be.Time to crank up the computer!
-
Aph
- Follow
- 118 followers
- 22 badges
- Send a private message to Aph
- Very Important Poster
- Thread Starter
Offline22ReputationRep:Very Important Poster- Follow
- 6
- 01-03-2016 11:02
(Original post by Gregorius)
I haven't worked through this in detail, but I think you may be able to attack this by observing that the distribution of a binomial RV conditional on the sum of two binomial RVs with the same probability is hypergeometric. That is, P(X=a | X+Y=p) is hypergeometric. The details for this are worked out in this Stackexchange thread.
I think this will work by observing that
P(X+Y = a | X+Y+Z=p) is simply
P((X+Y) = a | (X+Y) + Z = p)
That is, condition the binomial RV (X+Y) on the sum (X+Y) + Z.does not necessitate that x be greater or equal to 22 or Y be greater or equal to 18.
-
Gregorius
- Follow
- 20 followers
- 13 badges
- Send a private message to Gregorius
Online13ReputationRep:- Follow
- 7
- 01-03-2016 11:15
(Original post by Aph)
That sort of makes sense, although I would have though that wouldn't apply here as you want all the variables to be above a certain number and say for instancedoes not necessitate that x be greater or equal to 22 or Y be greater or equal to 18.
If this is actually an applied problem, you haven't considered some sort of monte-carlo simulation have you? -
Aph
- Follow
- 118 followers
- 22 badges
- Send a private message to Aph
- Very Important Poster
- Thread Starter
Offline22ReputationRep:Very Important Poster- Follow
- 8
- 01-03-2016 11:17
(Original post by Gregorius)
Yes, I see the problem. It works fine if you step down a dimension as you can get P(X > b, Y> c | X+Y=p) by simply summing the P(X=a | X+Y=p) for those a that allow both constraints to be satisfied. I will think some more...
If this is actually an applied problem, you haven't considered some sort of monte-carlo simulation have you?
Posted from TSR Mobile -
Gregorius
- Follow
- 20 followers
- 13 badges
- Send a private message to Gregorius
Online13ReputationRep:- Follow
- 9
- 01-03-2016 11:33
(Original post by Aph)
That sort of makes sense, although I would have though that wouldn't apply here as you want all the variables to be above a certain number and say for instancedoes not necessitate that x be greater or equal to 22 or Y be greater or equal to 18.
You can then sum the probabilities over the indices that meet all three constraints. -
Gregorius
- Follow
- 20 followers
- 13 badges
- Send a private message to Gregorius
Online13ReputationRep:- Follow
- 10
- 01-03-2016 11:38
(Original post by Aph)
It is sort of applied and I'm not sure what you mean by monte-carlo
Posted from TSR Mobile -
Aph
- Follow
- 118 followers
- 22 badges
- Send a private message to Aph
- Very Important Poster
- Thread Starter
Offline22ReputationRep:Very Important Poster- Follow
- 11
- 01-03-2016 12:29
(Original post by Gregorius)
OK, if you go back to that answer on the Stackexchange forum and work through the algebra, I think that you will find that you can do the conditioning "all at once". So you can work out P(X= k & Y = l | X+Y+Z = p). I think it comes out as
You can then sum the probabilities over the indices that meet all three constraints.
(Original post by Gregorius)
A monte-carlo technique is where you crank up a random number generator to repeatedly simulate from the distributions that you're interested in and you simply count the proportion of occurences that meet the constraints. -
Gregorius
- Follow
- 20 followers
- 13 badges
- Send a private message to Gregorius
Online13ReputationRep:- Follow
- 12
- 01-03-2016 12:47
(Original post by Aph)
I feel like that would take forever. not that I think any methord wouldn't take a long time.Last edited by Gregorius; 01-03-2016 at 12:49. -
Aph
- Follow
- 118 followers
- 22 badges
- Send a private message to Aph
- Very Important Poster
- Thread Starter
Offline22ReputationRep:Very Important Poster- Follow
- 13
- 01-03-2016 12:53
(Original post by Gregorius)
Just out of interest, I coded this up in the simplest way possible (simulate from the binomial distributions given, select only those that meet the sum constraint, and then count the X,Y,Z values that satisfy the >= constraints). With p = 54 and simulating 10,000,000 triples, I get an answer in about 5 seconds (in R, on an Intel 4770). -
Gregorius
- Follow
- 20 followers
- 13 badges
- Send a private message to Gregorius
Online13ReputationRep:- Follow
- 14
- 01-03-2016 13:02
(Original post by Aph)
I'm afraid as i'm only doing A-levels and am on a school computer I'm limited to excel. Plus I haven't done programming before so I wouldn't know where to begin on that. -
Aph
- Follow
- 118 followers
- 22 badges
- Send a private message to Aph
- Very Important Poster
- Thread Starter
Offline22ReputationRep:Very Important Poster- Follow
- 15
- 01-03-2016 13:11
(Original post by Gregorius)
Ah well, Excel will really limit what you can do like this. "R" has become the lingua franca of statisticians - it's wonderfully flexible and allows you to knock up this sort of code very rapidly. If you're interested in probability and/or statistics it would be a good idea to learn it sometime!I've worked out what I needed anyway, its just a lot of doing things manually on excel
- Statistics yr12 question - binomial distribution...someone help!
- Help with binomial approximation
- Help with maths- Binomial Distribution... HELP
- HELP !! C2 QUESTION ON SERIES AND SEQUENCES ...
- binomial distribution help needed
- Binomial expansion help please!
- need help with binomial theorem related proof by induction
- AS maths Binomial Distribution help!?
- Can someone help me with this binomial expansion?
- Maths AQA C4 Help - Binomial Expansions
-
Imperial College
-
University of Surrey
-
Loughborough University
-
Cardiff University
-
University of Stirling
-
University of Derby
-
University of Oxford
-
Mathematics (with a year in USA)
University of Leicester
-
Mathematics with International Year
University of Birmingham
-
Mathematics, Operational Research, Statistics and Economics (MORSE)
University of Warwick
We have a brilliant team of more than 60 Support Team members looking after discussions on The Student Room, helping to make it a fun, safe and useful place to hang out.
- SherlockHolmes
- Notnek
- charco
- Mr M
- Changing Skies
- F1's Finest
- rayquaza17
- RDKGames
- davros
- Gingerbread101
- Kvothe the Arcane
- TeeEff
- The Empire Odyssey
- Protostar
- TheConfusedMedic
- nisha.sri
- claireestelle
- Doonesbury
- furryface12
- Amefish
- harryleavey
- Lemur14
- brainzistheword
- Rexar
- Sonechka
- TheAnxiousSloth
- EstelOfTheEyrie
- CoffeeAndPolitics
- an_atheist
- Labrador99
- EmilySarah00