DHS Distribution Summary Updated Oct 2013

Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

H2 Math Statistics Summary H2 MATHS

2013 / YR 6
Distribution BINOMIAL POISSON NORMAL UNKNOWN
DECIDE ON THE APPROPRIATE DISTRIBUTION
1) Discrete 1) Discrete
1) Continuous
2) “Number of success out of n 2) “Number of occurrences in fixed Distribution
2) Stated in question, e.g
Clues trials” length/period not stated in
- follows a normal distribution
3) Exists an upper bound n for 3) No upper bound for number of question
- is normally distributed
number of success occurrences
DEFINE & STATE DISTRIBUTION
Define Random
Variable Let X be the number of success out Let X be the number of occurrences in Let X be the attribute of a randomly
of n trials. fixed length/period. chosen object/person.
State
X ~ B(n, p) X ~ Po( )
Distribution X ~ N(  , 2 )
where n is the number of trials & where  is the mean occurences in
where  is the mean of X and
p is the probability of success of fixed length/period.
1 trial.  2 is the variance of X .

(1)The experiment consists of n (1)Events occur singly and at random


repeated trials that are identical in a given interval of time or space.
and independent. (2)The number of outcomes that occur
(2)Each trial has exactly 2 in any interval is independent of the
Conditions
mutually exclusive outcomes: number of outcomes occurring in any
“success” and “failure”. other interval.
(3)The probability, p, of “success” (3)The mean number of occurrences in
is constant for each trial. each interval,  , is constant.

E( X ) = np E( X ) = 
Properties E( X ) = Var( X ) = 
Var( X ) = np (1 − p ) Var( X ) =  2
Distribution BINOMIAL POISSON NORMAL UNKNOWN
FIND THE REQUIRED DISTRIBUTION OR USE A SUITABLE APPROXIMATION
For ANY distribution, the following results holds:

1) E(aX  bY  c) = aE( X )  bE(Y )  c


2) Var(aX  bY  c) = a 2 Var( X ) + b 2 Var(Y ) for any constants a, b, c.
If X ~ N( 1,12 ) & Y ~ N( 2 ,  22 ),
If X ~ Po( ) & Y ~ Po(  )
 aX  bY ~ N(a 1  b2 , a 212 + b 2 22 )
Linear then X + Y ~ Po( +  )
combination of where a, b are constants.
R.V Note: X – Y do not follow Poisson
Distribution ** Note the difference between
3 X and X1 + X 2 + X 3

Binomial approximated to Poisson


Conditions : 1) n is large (  50 )
2) np  5
X ~ Po(np) approximately
Poisson approximated to Normal
Condition :   10
Approximation
Binomial approximated to Normal X ~ N( ,  ) approximately
Conditions : 1) n is large (  50 ) (Remember to use c.c)
2) np  5
3) n(1 − p)  5
X ~ N ( np, np(1 − p) ) approximately
(Remember to use c.c)
Distribution BINOMIAL POISSON NORMAL UNKNOWN
Sample Mean

Key words: Suppose E( X ) =  & Var( X ) =  2 . If sample size n is large (≥ 50), by CLT,
 2  Use CLT if
Mean,  2  X ~ N  ,  regardless of sample size n sample size n
X ~ N  ,  approximately  n 
Average  n    is large
X + ... + X n 
X= 1
n
Sample Sum
Suppose E( X ) =  & Var( X ) =  2 . If sample size n is large (≥ 50), by CLT, Use CLT if
Key words:
Sum, Total ( )
S ~ N n , n 2 approximately
(
S ~ N n , n 2 ) regardless of sample size n sample size n
is large
S = X1 + ... + X n

EVALUATE
Strategies
1) Standardise if either  or  2 is
Note: Use c.c when applicable Note: Use c.c when applicable unknown.
2) Draw the normal curve when using
invnorm.

Clues to use the Central Limit Theorem (1, 2, 3 CLT)


X + ... + X n
1) Required to find probabilities involving X = 1 (mean, average) or S = X1 + ... + X n (sum, total).
n
2) Distribution of X is not normal.
3) Sample size n is large (≥ 50).
(Note: Also applicable for Hypothesis Testing)

You might also like