Scribd
Upload
79 views2 pages

Hypothesis Testing - Poisson Notes

The document discusses hypothesis testing for the parameter λ of a Poisson distribution, specifically in the context of incident counts over multiple periods. It outlines the null and alternative hypotheses, the use of a statistical calculator to determine p-values, and provides examples of testing against specific λ values based on recorded accident data. The conclusions drawn from the p-values help determine whether to reject the null hypothesis or not.

Uploaded by

Hrishikesh Reddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
79 views2 pages

Hypothesis Testing - Poisson Notes

The document discusses hypothesis testing for the parameter λ of a Poisson distribution, specifically in the context of incident counts over multiple periods. It outlines the null and alternative hypotheses, the use of a statistical calculator to determine p-values, and provides examples of testing against specific λ values based on recorded accident data. The conclusions drawn from the p-values help determine whether to reject the null hypothesis or not.

Uploaded by

Hrishikesh Reddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

TOPIC 4: STATISTICS AND PROBABILITY Christos Nikolaidis

4.23 HYPOTHESIS TEST FOR THE PARAMETER λ OF POISSON

Suppose that the variable


X = number of incidents in a certain period
follows Poisson distribution. (e.g. X= accidents per day)

We conduct a test for the parameter λ (average) of Poisson.

They give us a sample of incidents at n different periods

either or
x1, x2, …, xn the total number for n periods
We find their sum
x
i
x i

We know that
If X ~ Po(λ) then (Sum of Χ) ~ Po(nλ)

CLAIM: for the parameter λ

λ>λ0 or λ<λ0
λ=λ0 against
only 1-tailed test

We state
[null hypothesis] Ho: λ=λ0
[alternative hypothesis] H1: λ>λ0 or λ<λ0

We use GDC
Statistics – DIST – Poisson Po(nλ0)
x
statistic
= x i

For the case H1: λ>λ0 p-value = P(X  xstatistic )


For the case H1: λ<λ0 p-value = P(X  xstatistic )

Conclusion
IF THEN
p-value < a we reject Ho

29
TOPIC 4: STATISTICS AND PROBABILITY Christos Nikolaidis

EXAMPLE 1
The number of accidents per day in a certain area follows Poisson.
We record the number of accidents in 5 different days

Day 1 Day 2 Day 3 Day 4 Day 5


7 8 8 6 10

(a) Test if the number of accidents per day follows Poisson Po(7)
(b) Test if the number of accidents per day follows Poisson Po(9.8)
For both questions use a = 0.10
Solution
For both questions, the statistic is x =39
i

We state the two hypotheses either for 1 day or for all 5 days
(a) for one day OR for all 5 days
Ho: λ=7 Ho: λ=35
H1: λ>7 H1: λ>35
(In any case) we consider Po(35).
p-value = P(X≥39) = 0.271
As p-value > 0.10, not enough evidence to reject Ho.
(we may accept that λ=7)
(b) for one day OR for all 5 days
Ho: λ=9.8 Ho: λ=49
H1: λ<9.8 H1: λ<49
(In any case) we consider Po(49)
p-value = P(X≤39) = 0.0838
As p-value < 0.10, we reject Ho.
(we reject that λ=9.8, so λ<9.8)

NOTICE
They could only give us
 that the total number in 5 days is 39, i.e. x =39.
i

 that for n=5 days, x =7.8 , thus x =nx =39.


i

30

You might also like