Chapter3 PDF
Uploaded by
GregorChapter3 PDF
Uploaded by
Gregor3 Diskrete Waarskynlikheids
Verdelings
Discrete Probability
Distributions
The government is extremely fond of amassing great quantities
of statistics. These are raised to the nth degree, the cube roots
are extracted, and the results are arranged into elaborate and
impressive displays. What must be kept ever in mind, however, is
that in every case, the figures are first put down by a village
watchman, and he puts down anything he damn well pleases.
Waarskynlikheidsverdeling vir Diskrete
Stogastiese Veranderlike
Probability Distribution for Discrete Random
Variable
Hoofstuk 2 waarskynlikhede is bereken deur uitkomste van
gebeurtenisse te tel.
Chapter 2 probabilities were calculated by counting the
outcomes from events.
In praktyk is dit baie moeilik om uitkomste van
gebeurtenisse te tel, so ons soek ‘n ander manier om
waarskynlikhede te bereken.
In practise it is difficult to count the outcomes of events, so
we need a different way to calculate probabilities.
‘n Waarskynlikheidsverdeling van ‘n diskrete ewekansige
veranderlike is ‘n lys van alle moontlike waardes wat die
veranderlike kan aanneem, asook die waarskynlikheid
van elke van die waardes. Waarskynlikhede sommeer
altyd tot 1.
A probability distribution for a discrete random variable is a
list of all possible values that the random variable can
have, as well as, the probability of each of the values.
The probabilities always add up to 1.
X P(X = x)
0 0.2
1 0.4
2 0.4
1
1
Waarskynlikheidsmassafunksie
Probability mass function
Kumulatiewe verdelingsfunksie
Cumulative distribution function
EXERCISE 3-14 (p. 69)
EXAMPLE 3-7 (p. 72)
EXAMPLE 3-8 (p. 72)
Verwagte Waarde
Expected Value
µ≡ Gemiddelde van ‘n waarskynlikheidsverdeling
Mean of a probability distribution
Gemiddeld, wat verwag ons gaan gebeur.
On average, what do we expect to happen.
Variansie en Standaard Afwyking
Variance and Standard Deviation
σ2 ≡ Variansie van waarskynlikheidsverdeling
Variance of probability distribution
σ≡ Standaard Afwyking van waarskynlikheidsverdeling
Standard Deviation of probability distribution
EXAMPLE 3-9 (p. 75)
EXAMPLE 3-11 (p. 76)
2
Diskrete Uniforme Verdeling
Discreet Uniform Distribution
EXAMPLE 3-14 (p. 78)
Binomiaalverdeling
Binomial Distribution
Seker gebeurtenisse of veranderliks volg vasgestelde
wiskundige formules wat ons dan kan gebruik om
waarskynlikhede te bereken.
Certain events or variables follow known mathematical
formulae that we can then use to calculate probabilities.
Binomiaal is een van hierdie formules wat baie in
alledaagse gebruik voorkom.
Binomial are one of these formulae which occur frequently
in everyday live.
Eienskappe / Properties:
1) Ons werk met ‘n vaste steekproef grote, n.
We are working with a fixed sample size, n.
2) Elke uitkoms kan in een van twee moontlike kategorieë
verdeel word, Bernoulli herhalings.
Each outcome can be classified in one of two different
categories, Bernoulli trials.
3) Die waarskynlikheid om in een van die kategorieë te
val, π, is konstant vir alle herhalings.
The probability to fall into one of the categories, π, is
fixed for all outcomes.
4) Elke uitkoms is onafhanklik van enige ander uitkoms.
Each outcome is independent from all other outcomes.
3
Indien hierdie eienskappe geld, kan ons die binomiaal
formule gebruik om waarskynlikhede te bereken.
If these properties hold we can use the binomial equation
to calculate probabilities.
Parameters
n : Steekproefgrote
Sample size
: Waarskynlikheid van een van die kategorieë
Probability of one of the categories
Verwagte Waarde en Variansie
Expected Value and Variance
Kan die formules gebruik wat ons aan die begin na gekyk
het, maar vir die binomiaalverdeling kan ons dit
vereenvoudig na ‘n maklike formule.
We could use the formulae we looked at in the beginning
of the chapter, but in the case of the binomial
distribution these simplify to a very easy equations.
EXAMPLE 3-18 (p. 82)
Geometriese Verdeling
Geometric Distribution
X is die aantal Bernoulli herhalings tot die eerste sukses
indien die waarskynlikheid van ‘n sukses .
X is the number of Bernoulli trials until the first success is
observed if the probability of a success is .
EXAMPLE 3-20 (p. 86)
4
Negatiewe Binomiaal Verdeling
Negative Binomial Dsitribution
X is die aantal Bernoulli herhalings tot die r-de sukses
indien die waarskynlikheid van ‘n sukses .
X is the number of Bernoulli trials until the r-th success is
observed if the probability of a success is .
EXAMPLE 3-25 (p. 90)
Hipergeometrieseverdeling
Hypergeometric Distribution
In die binomiaalverdeling bly die waarskynlikheid konstant
vir elke uitkoms om in ‘n kategorie te val en elke uitkoms
is onafhanklik van ander uitkomste.
In the binomial distribution the probability remains fixed for
each outcome to fall into a category and each outcome
is independent from all other outcoms.
Hierdie eienskappe geld nie vir die
hipergeometrieseverdeling nie.
These properties don’t hold for the hypergeometric
distribution.
One het steeds twee moontlikhede, in die algemeen
genoem sukses en mislukking, maar nou beïnvloed die
een uitkoms ‘n volgende uitkoms. Steekproefneming
sonder terugplasing.
We still have to possibe outcome, in general called a
success and a failure, but now the one outcome
influences influence other outcomes. Sampling without
replacement.
Parameters
N : Populasiegrote / Population size
n : Steekproefgrote / Sample size
K : Aantal suksesse in populasie / Number of successes
in population
5
Verwagte Waarde en Variansie
Expected Value and Variance
Weereens vereenvoudig die formules aan die begin van die
hoofstuk na redelik maklike uitdrukkings toe.
Again the formulae at the beginning of the chapter
simplifies to easy equations.
EXAMPLE 3-27 (p. 94)
Poissonverdeling
Poisson Distribution
‘n Handige verdeling indien ons wil weet hoeveel keer iets
gaan plaasvind in ‘n gegewe interval.
A useful distribution if we are interested in how many times
something will occure in a given interval.
Ons weet byvoorbeeld gemiddeld is daar 10 persone wat
bel in ‘n uur, nou wil ons weet wat is die waarskynlikheid
dat in die volgende uur daar 13 gaan bel.
We know for example that on average 10 individuals call in
an hour, now we want to know what is the probability
that in the next hour 13 will call.
Parameters
λ : Lambda
Verwagte aantal gebeurtenisse in ‘n interval
Expected number of events in an interval
NB: Gebruik dieselfde eenhede!
Use the same units!