Combinations and Permutations

Download as pdf or txt
Download as pdf or txt
You are on page 1of 5

Gr 12 FSM | Statistics Elective Revision | Notes

COUNTING METHODS

© Advantage Learning Technologies (Pty) Ltd 3


Gr 12 FSM | Statistics Elective Revision | Notes

NORMAL DISTRIBUTIONS
𝑋~𝑁(𝜇; 𝜎 2 )

random variable mean of the distribution variance (not std deviation)


𝑥 = a value from the original normal distribution
𝜇 = the mean of the original distribution 𝜇
𝜎 = the standard deviation of the original normal distribution.
Standardizing formula (on the formula sheet)
𝑋−𝜇
𝑍=
𝜎
Used to convert from a normal distribution to a standard normal distribution

Note:
• Changing the mean shifts the entire curve left or right on the horizontal axis
• Changing the standard deviation either squeezes or spreads out the
distribution along the horizontal axis

THE STANDARD NORMAL DISTRIBUTION

Parameters for the standard normal 𝜇 = 0 and 𝜎 2 = 1


Standard Normal Distribution - 𝑁(0; 1)
0
mean variance
The variable 𝑍 is used to denote the standard distribution rather than 𝑋.
∴ 𝑍~𝑁(0; 1)

© Advantage Learning Technologies (Pty) Ltd 8


Gr 12 FSM | Statistics Elective Revision | Notes

CONFIDENCE INTERVALS
Point estimate ± margin of error
Common confidence levels and their associated critical 𝑍-values:
Confidence Level 90% 95% 98% 99%
Critical 𝑍-Value 1,645 1,960 2,326 2,576

Confidence level = (1 − 𝛼)100%


Confidence limits = ±𝑍𝑐𝑟𝑖𝑡 ∵ 𝑃(−𝑍𝑐𝑟𝑖𝑡 < 𝑍 < 𝑍𝑐𝑟𝑖𝑡 ) = 1 − 𝛼
= 2 × 𝑃(0 < 𝑍 < 𝑍𝑐𝑟𝑖𝑡 )

CONFIDENCE INTERVALS FOR THE MEAN


𝜎
Confidence interval for a population mean is: 𝑥̅ ± 𝑍𝑐𝑟𝑖𝑡 ∙
√𝑛
Where:
𝑥̅ = sample mean 𝜇 = population mean 𝜎 = population standard deviation
𝑛 = sample size 𝑍𝑐𝑟𝑖𝑡 = critical 𝑍-value from standard normal table
𝜎 𝜎
Margin of error = 𝑍𝑐𝑟𝑖𝑡 ∙ Interval length = 2 × margin of error = 2 × 𝑍𝑐𝑟𝑖𝑡 ∙
√𝑛 √𝑛

For a given interval:


upper + lower CI boundary
𝑥̅ =
2

CONFIDENCE INTERVALS FOR PROPORTION


̂(𝟏−𝒑
𝒑 ̂)
̂ ± 𝒁𝒄𝒓𝒊𝒕 ∙ √
Confidence interval for a population proportion (𝒑) is: 𝒑
𝒏
Where:
𝑥𝑠
𝑝̂ = sample proportion, point estimate for 𝑝 and 𝑝̂ =
𝑛

𝑛 = sample size 𝑥𝑠 = sample successes 𝑍𝑐𝑟𝑖𝑡 = the critical 𝑍-value


𝑝
̂ (1−𝑝̂)
Margin of error = 𝑍𝑐𝑟𝑖𝑡 ∙ √
𝑛
𝑝
̂ (1−𝑝̂)
Interval length = 2 × margin of error = 2 × 𝑍𝑐𝑟𝑖𝑡 ∙ √
𝑛

For a given interval:


upper + lower CI boundary
𝑝̂ =
2
© Advantage Learning Technologies (Pty) Ltd 9
Gr 12 FSM | Statistics Elective Revision | Notes

HYPOTHESIS TESTING
HYPOTHESIS TEST FOR A POPULATION MEAN

Every hypothesis test will consist of 4 important steps:


1. Null hypothesis and alternate hypothesis
2. Level of significance 𝛼, establishing rejection regions, sketching the normal
curve and finding the critical 𝑍-value
3. Calculate the test statistic
4. Acceptance/rejection and conclusion
Sign in 𝑯𝟏 Type of test Rejection region(s) Critical Z-value
𝛼
2 Rejection regions, 𝑃(0 < 𝑍 < 𝑍𝑐𝑟𝑖𝑡 ) = 0,5 −
≠ 2-tail test 𝛼 2
each ±𝑍𝑐𝑟𝑖𝑡
2

Left 1-tail 𝑃(0 < 𝑍 < 𝑍𝑐𝑟𝑖𝑡 ) = 0,5 − 𝛼


< 1 Rejection region, 𝛼 −𝑍𝑐𝑟𝑖𝑡
test
Right 1-tail 𝑃(0 < 𝑍 < 𝑍𝑐𝑟𝑖𝑡 ) = 0,5 − 𝛼
> 1 Rejection region, 𝛼 +𝑍𝑐𝑟𝑖𝑡
test

Setting up 2 hypotheses:
𝐻0 : null hypothesis (No change, what is expected, historical value) Must have =
𝐻1 : alternate hypothesis
• ≠ → 2-tailed test • < ; > →1-tailed test
• < left tail test
• > right tail test

Level of significance = 𝛼
The test statistic is a 𝑍-value calculated from the sample data:
• 𝑥̅ is the sample mean
̅ − 𝝁
𝒙
𝒁= • 𝜇 is the population mean, value from 𝐻0
𝝈
• 𝜎 is the standard deviation of the population
√𝒏
• 𝑛 is sample size

© Advantage Learning Technologies (Pty) Ltd 10


Gr 12 FSM | Statistics Elective Revision | Notes

If the test statistic 𝒁-value is found to lie in a rejection region then the sample has
provided sufficient evidence against 𝐻0
→ reject 𝑯𝟎 in favour of 𝑯𝟏
Conclusion: Reject 𝑯𝟎 at the _% level of significance and suggest sufficient evidence
to support the claim.

If the test statistic 𝒁-value is found to lie outside the rejection region (in the
acceptance region) then the sample has provided insufficient evidence against 𝐻0
→ fail to reject 𝑯𝟎
Conclusion: Fail to reject 𝑯𝟎 at the _% level of significance and suggest insufficient
evidence to support the claim.

HYPOTHESIS TEST FOR 2 DIFFERENT POPULATION MEANS


The 2 normally distributed populations are:
𝑋~𝑁(𝜇𝑥 ; 𝜎𝑥2 ), 𝑥̅ is the sample mean. Number in the sample is 𝑛𝑥

𝑌~𝑁(𝜇𝑦 ; 𝜎𝑦2 ) 𝑦̅.is the sample mean. Number in the sample is 𝑛𝑦


𝑥̅ − 𝑦̅ − (𝜇𝑥 − 𝜇𝑦 )
The test statistic is: 𝑍=
𝜎𝑥2 𝜎𝑦2

𝑛𝑥 + 𝑛𝑦

Null hypothesis:
There is no difference between the two populations or that there is some
established/known exact difference between them (𝑎).
𝐻0 : 𝜇𝑥 = 𝜇𝑦 ⇒ 𝜇𝑥 − 𝜇𝑦 = 0 or 𝐻0 : 𝜇𝑥 − 𝜇𝑦 = 𝑎

Alternate hypothesis:
There is a difference between the two means
𝐻1 : 𝜇𝑥 ≠ 𝜇𝑦 ⇒ 𝜇𝑥 − 𝜇𝑦 ≠ 0
Or
Mean of population 𝑋 is greater than that of 𝑌 (Right tail)
𝐻1 : 𝜇𝑥 > 𝜇𝑦 ⇒ 𝜇𝑥 − 𝜇𝑦 > 0
Or
Mean of population 𝑋 is less than that of 𝑌 (Left tail)
𝐻1 : 𝜇𝑥 < 𝜇𝑦 ⇒ 𝜇𝑥 − 𝜇𝑦 < 0

© Advantage Learning Technologies (Pty) Ltd 11

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy