`=>` Consider the experiment of tossing a coin in which each trial results in success (say, heads) or failure (tails). Let S and F denote respectively success and failure in each trial. Suppose we are interested in finding the ways in which we have one success in
six trials. Clearly, six different cases are there as listed below:
`"SFFFFF, FSFFFF, FFSFFF, FFFSFF, FFFFSF, FFFFFS."`
`=>`Similarly, two successes and four failures can have `(6!)/(4! xx 2!)` combinations. It will be lengthy job to list all of these ways. Therefore, calculation of probabilities of 0, 1, 2,...,n number of successes may be lengthy and time consuming. To avoid the lengthy
calculations and listing of all the possible cases, for the probabilities of number of successes in n-Bernoulli trials, a formula is derived. For this purpose, let us take the experiment made up of three Bernoulli trials with probabilities `p` and `q = 1 – p` for success and failure respectively in each trial. The sample space of the experiment is the set
`S = {SSS, SSF, SFS, FSS, SFF, FSF, FFS, FFF}`
`=>` The number of successes is a random variable X and can take values 0, 1, 2, or 3.
The probability distribution of the number of successes is as below :
`P(X = 0) = P`(no success)
`= P({FFF}) = P(F) P(F) P(F)`
`= q * q * q = q^3` since the trials are independent
`=>P(X = 1) = P`(one successes)
`= P({SFF, FSF, FFS})`
`= P({SFF}) + P({FSF}) + P({FFS})`
`= P(S) P(F) P(F) + P(F) P(S) P(F) + P(F) P(F) P(S)`
`= p *q * q + q * p * q + q * q * p = 3pq^2`
`=>P(X = 2) = `P (two successes)
`= P({SSF, SFS, FSS})`
`= P({SSF}) + P ({SFS}) + P({FSS})`
`= P(S) P(S) P(F) + P(S) P(F) P(S) + P(F) P(S) P(S)`
`= p * p * q + p * q * p + q * p * p = 3p^2 q`
and P(X = 3) = P(three success) = P ({SSS})
`= P(S) * P(S) * P(S) = p^3`
`=>` Thus, the probability distribution of X is
Also, the binominal expansion of `(q + p)^3` is
`q^3 + 3q^2 p + 3qp^2 + p^3`
Note : The probabilities of 0, 1, 2 or 3 successes are respectively the 1st, 2nd, 3rd and 4th term in the expansion of `(q + p)^3`.
`=>`Also, since `q + p = 1,` it follows that the sum of these probabilities, as expected, is 1.
`=>` Thus, we may conclude that in an experiment of n-Bernoulli trials, the probabilities of 0, 1, 2,..., n successes can be obtained as 1st, 2nd,...,(n + 1)th terms in the expansion of (q + p)n. To prove this assertion (result), let us find the probability of x-successes in an experiment of n-Bernoulli trials.
Clearly, in case of x successes (S), there will be (n – x) failures (F).
`=>` Now, x successes (S) and (n – x) failures (F) can be obtained in `(n!)/(x! ( n-x)!)` ways.
In each of these ways, the probability of x successes and (n − x) failures is
= P(x successes) . P(n–x) failures is
` \underbrace{ P(S)\cdot P(S)\cdots P(S)}_{X\text{ times}} * \underbrace{P(F) \cdot P(F) \cdots P(F)}_{(n-x)\text{ times}} = p^x q^(n-x)`
`=>` Thus, the probability of x successes in n-Bernoulli trials is ` (n!)/( x! ( n-x)! ) p^x q^(n-x)`
or `text()^(n )C_x p^x q^(n-x)`
`=>` Thus P(x successes)` = text()^(n)C_x p^x q^(n-x) , x = 0,1,2, ...........n ` `(q = 1-p )`
Clearly, P(x successes), i.e. `text()^(n)C_x p^x q^(n-x) ` is the ` (x+1)^(th)` term in the binomial
expansion of `(q + p)^n`.
`=>` Thus, the probability distribution of number of successes in an experiment consisting of n Bernoulli trials may be obtained by the binomial expansion of `(q + p)^n`. Hence, this
distribution of number of successes X can be written as
`=>`The above probability distribution is known as binomial distribution with parameters n and p, because for given values of n and p, we can find the complete probability distribution.
`=>` The probability of x successes P (X = x) is also denoted by P (x) and is given by
`P(x) = text()^(n)C_x q^(n–x) p^x, x = 0, 1,..., n. (q = 1 – p)`
`=>` This P (x) is called the probability function of the binomial distribution.
`=>` A binomial distribution with n-Bernoulli trials and probability of success in each
trial as p, is denoted by `B (n, p).`
`=>` Consider the experiment of tossing a coin in which each trial results in success (say, heads) or failure (tails). Let S and F denote respectively success and failure in each trial. Suppose we are interested in finding the ways in which we have one success in
six trials. Clearly, six different cases are there as listed below:
`"SFFFFF, FSFFFF, FFSFFF, FFFSFF, FFFFSF, FFFFFS."`
`=>`Similarly, two successes and four failures can have `(6!)/(4! xx 2!)` combinations. It will be lengthy job to list all of these ways. Therefore, calculation of probabilities of 0, 1, 2,...,n number of successes may be lengthy and time consuming. To avoid the lengthy
calculations and listing of all the possible cases, for the probabilities of number of successes in n-Bernoulli trials, a formula is derived. For this purpose, let us take the experiment made up of three Bernoulli trials with probabilities `p` and `q = 1 – p` for success and failure respectively in each trial. The sample space of the experiment is the set
`S = {SSS, SSF, SFS, FSS, SFF, FSF, FFS, FFF}`
`=>` The number of successes is a random variable X and can take values 0, 1, 2, or 3.
The probability distribution of the number of successes is as below :
`P(X = 0) = P`(no success)
`= P({FFF}) = P(F) P(F) P(F)`
`= q * q * q = q^3` since the trials are independent
`=>P(X = 1) = P`(one successes)
`= P({SFF, FSF, FFS})`
`= P({SFF}) + P({FSF}) + P({FFS})`
`= P(S) P(F) P(F) + P(F) P(S) P(F) + P(F) P(F) P(S)`
`= p *q * q + q * p * q + q * q * p = 3pq^2`
`=>P(X = 2) = `P (two successes)
`= P({SSF, SFS, FSS})`
`= P({SSF}) + P ({SFS}) + P({FSS})`
`= P(S) P(S) P(F) + P(S) P(F) P(S) + P(F) P(S) P(S)`
`= p * p * q + p * q * p + q * p * p = 3p^2 q`
and P(X = 3) = P(three success) = P ({SSS})
`= P(S) * P(S) * P(S) = p^3`
`=>` Thus, the probability distribution of X is
Also, the binominal expansion of `(q + p)^3` is
`q^3 + 3q^2 p + 3qp^2 + p^3`
Note : The probabilities of 0, 1, 2 or 3 successes are respectively the 1st, 2nd, 3rd and 4th term in the expansion of `(q + p)^3`.
`=>`Also, since `q + p = 1,` it follows that the sum of these probabilities, as expected, is 1.
`=>` Thus, we may conclude that in an experiment of n-Bernoulli trials, the probabilities of 0, 1, 2,..., n successes can be obtained as 1st, 2nd,...,(n + 1)th terms in the expansion of (q + p)n. To prove this assertion (result), let us find the probability of x-successes in an experiment of n-Bernoulli trials.
Clearly, in case of x successes (S), there will be (n – x) failures (F).
`=>` Now, x successes (S) and (n – x) failures (F) can be obtained in `(n!)/(x! ( n-x)!)` ways.
In each of these ways, the probability of x successes and (n − x) failures is
= P(x successes) . P(n–x) failures is
` \underbrace{ P(S)\cdot P(S)\cdots P(S)}_{X\text{ times}} * \underbrace{P(F) \cdot P(F) \cdots P(F)}_{(n-x)\text{ times}} = p^x q^(n-x)`
`=>` Thus, the probability of x successes in n-Bernoulli trials is ` (n!)/( x! ( n-x)! ) p^x q^(n-x)`
or `text()^(n )C_x p^x q^(n-x)`
`=>` Thus P(x successes)` = text()^(n)C_x p^x q^(n-x) , x = 0,1,2, ...........n ` `(q = 1-p )`
Clearly, P(x successes), i.e. `text()^(n)C_x p^x q^(n-x) ` is the ` (x+1)^(th)` term in the binomial
expansion of `(q + p)^n`.
`=>` Thus, the probability distribution of number of successes in an experiment consisting of n Bernoulli trials may be obtained by the binomial expansion of `(q + p)^n`. Hence, this
distribution of number of successes X can be written as
`=>`The above probability distribution is known as binomial distribution with parameters n and p, because for given values of n and p, we can find the complete probability distribution.
`=>` The probability of x successes P (X = x) is also denoted by P (x) and is given by
`P(x) = text()^(n)C_x q^(n–x) p^x, x = 0, 1,..., n. (q = 1 – p)`
`=>` This P (x) is called the probability function of the binomial distribution.
`=>` A binomial distribution with n-Bernoulli trials and probability of success in each
trial as p, is denoted by `B (n, p).`