Scribd
Upload
18 views

Quantitative Analysis 2

Uploaded by

Blessed Adetutu
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
18 views

Quantitative Analysis 2

Uploaded by

Blessed Adetutu
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
You are on page 1/ 9

ATS 2

HYPOTHESIS TESTING

JUNE
2020
PROBLEM ?

H0 H1
After this lecture, you should be able to:
• (a) understand the concept of hypothesis;

• (b) distinguish between two types of errors in


hypothesis testing;

• (c) understand the level of significance;

• (d) understand the concepts of one-tailed and two-


tailed tests; and

• (e) understand test of hypothesis on population


mean and population proportion for both large
and small samples
07040297989, 08188343879 2
State the Hypothesis
State the level of Significance
Compute Test Statistics
Check Tabulated value
Decision
Conclusion

07040297989, 08188343879 3
Hypothesis testing can be done under two conditions namely;
(i) when we have large samples and
(ii) when we have small samples

Small Sample

Large Sample

4
Small Sample

Large Sample
For small samples (n < 30),
For large samples (n > 30),
the test – statistic is the t – test
It is usually assumed that the
sampling distribution of the desired
𝑥ҧ − µ0
statistic is normally distributed or
tcal =
approximately normal. 𝑠/√𝑛
It is for this reason that tests
concerning large samples assumed
normal and used the Z test where x = sample mean;
μ0 = hypothesis value of μ.
σ = the given value of the standard deviation;
𝑥ҧ − µ0 but when this not given, one can use sample
Zcal= standard deviation (s) for large samples.
σ/√𝑛 5
n = sample size
07040297989, 08188343879
The final decision on the tests is made by comparing the computed values
(Zcal or tcal) with the table values.
The normal table is used for Z – test (for large samples)
while t – distribution table at (n – 1) degrees of freedom is used for small
samples.

Decisions
(Zcal > Ztable) Reject H0
(Ztable > Zcal) Accept H0

(tcal > ttable) Reject H0

(ttable >tcal) Accept H0 6

07040297989, 08188343879
In a University, a sample of 250 female students was taken in order to find the
average height. From the samples, the computed average height was 180cm while
the mean of actual population height was 170cm with a standard deviation of
120cms. You are required to show if the sample mean height is significantly
different from the population mean at 5% significant level.

Statement of hypothesis Level of Significance


H0: μ = 𝑥ҧ ⇒ H0: 170 = 180 α = 5% = 0.05
H1 :μ ≠ 𝑥ҧ ⇒ H1 : 170 ≠ 180
Tabulated Value
Compute test statistics
Table value of Z at 5% level of significance
𝑥ҧ − µ0 180 − 170 (for two tailed test) = 1.96
Zcal= =
σ/√𝑛 120/√250
= 1.32
Decision Conclusion 7

No significance difference between the sample


since Zcal < Ztable (1.32 <1.96), we accept H0 mean and population mean.
JOIN US ON TELEGRAM 8

https://t.me/joinchat/QRkIIBs2mywqG_iC4-9nQg
07040297989,
08188343879

WWW.ANNTEXTECHNOLOGIES.COM

You might also like