BINOMIAL
To
identify Binomial question;
- It has small figures in the question
- The figures should not up to 30, it is always 5, 4, 9 etc.
- Probability of success and failure is always equal to one
- There are always two possible events i.e success or failure
POISSON
To
identify a Poisson question, it will be mentioned in the question
STATISTICAL
ESTIMATION
Note:
To identify statistical estimation question, you will be asked to test the
confidence limit for the mean of a sample taken from unknown population i.e
testing 95% = 1.96, 99%=2.58 and 90%=1.64.
Formula S
X ± Z x √ n
HYPOTHESIS
A
hypothesis is a statement about a population in which are then used to check
the reasonableness of the statement.
Hypothesis
testing: it is a procedure based on sample evidence and probability theory to
determine whether the hypothesis is a reasonable statement.
TYPES OF HYPOTHESIS
1.
Null
(negative) Hypothesis
2.
Alternative
(positive) hypothesis
Null
hypothesis: it is a statement about the value of a population parameter. It is represented by Ho
Alternative
hypothesis: It is a statement that is
accepted if the sample data provide enough evidence that the null hypothesis is
false.
Type
1 error: Rejecting the null hypothesis
(HO) when it is true
Type
2 error: accepting the null hypothesis (HO) when it is false
Question Five:
A random sample of 400 householders is
classified by two characteristics whether they own a colour television and by
what type of householder. (i.e – owner
–occupier, private tenant, council tenant).
The results of this investigation are given below:
|
ACTUAL
FREQUENCIES
|
|||
|
Owner
Occupier
|
Council
tenant
|
Private
tenant
|
Total
|
Colour
TV
|
150
|
60
|
20
|
230
|
No
Colour TV
|
45
|
68
|
57
|
170
|
Total
|
195
|
128
|
77
|
400
|
It
is required to test at 5% level, the following hypotheses using chi-square:
Ho:
the two classifications are independent (i.e no relation between classes of
householders and colour TV ownership)
|
H1: The classifications are not independent.
Solution:
Step
I.
Ho: The two classifications are independent
H1: The classifications are not independent
No comments:
Post a Comment