Scribd
Upload
33 views5 pages

Revision Formulas and Notes Forexam II - MAT 210

Uploaded by

najeebkammal63
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
33 views5 pages

Revision Formulas and Notes Forexam II - MAT 210

Uploaded by

najeebkammal63
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/ 5

MAT 210 Prepared by: Hiba Othman

Summary Notes for Final

 Statistical Terminology:
o Population: Entire set of subjects or items under study
o Sample: Subset or part of the population
 Sample size
o 4 sampling techniques:
 Random
 Systematic
 Cluster
 Stratified
o Variables
 Quantitative: could be measured by numerical values
 Discrete: Measured one by one- no decimals
 Continuous: Measured in intervals- decimals included
 Qualitative: could not be measured by numerical values
 Nominal: no order
 Ordinal: given order, rank, or hierarchy

 Discrete Probability:
𝑐𝑜𝑟𝑟𝑒𝑐𝑡 𝑐𝑎𝑠𝑒𝑠
o Basic Definition: 𝑃 (𝐸 ) = 𝑡𝑜𝑡𝑎𝑙 𝑐𝑎𝑠𝑒𝑠
∑ 𝑃(𝐸 ) = 1 & 0 ≤ 𝑃(𝐸) ≤ 1
o Complimentary Event: 𝑃(𝐸̅ ) = 1 − 𝑃(𝐸)
o Union:
o Mutually exclusive: 𝑃 (𝐴 ∪ 𝐵 ) = 𝑃(𝐴) + 𝑃(𝐵)
o Mutually inclusive: 𝑃 (𝐴 ∪ 𝐵 ) = 𝑃(𝐴) + 𝑃 (𝐵 ) − 𝑃(𝐴 ∩ 𝐵)
Note: 𝑃 (𝐴 ∪ 𝐵 ) = 𝑃 (𝐵 ∪ 𝐴)
o Intersection:
o Independent: 𝑃 (𝐴 ∩ 𝐵 ) = 𝑃 (𝐴) × 𝑃(𝐵)
o Dependent: 𝑃 (𝐴 ∩ 𝐵 ) = 𝑃(𝐵/𝐴) × 𝑃 (𝐴)
Or 𝑃 (𝐴 ∩ 𝐵 ) = 𝑃 (𝐴/𝐵 ) × 𝑃(𝐵 )

Note: 𝑃 (𝐴 ∩ 𝐵 ) = 𝑃 (𝐵 ∩ 𝐴)
o Conditional Probability formula:
𝑃(𝐴 ∩ 𝐵)
(
𝑃 𝐴/𝐵 = )
𝑃(𝐵)
o Bayes’ Theorem: (can be done using the tree diagram):
MAT 210 Prepared by: Hiba Othman

𝑃(𝐴) = ∑ 𝑃(𝐴 /𝐵𝑖 ) × 𝑃(𝐵𝑖 )


𝑖=1
o De Morgan's Rules:
𝑃(̅̅̅̅̅̅̅
𝐴 ∪ 𝐵) = 𝑃(𝐴̅) ∩ 𝑃(𝐵̅ )
𝑃(̅̅̅̅̅̅̅
𝐴 ∩ 𝐵) = 𝑃(𝐴̅) ∪ 𝑃(𝐵̅ )
𝑃(𝐴 ∩ (𝐵 ∪ 𝐶 ) = 𝑃(𝐴 ∩ 𝐵) ∪ 𝑃(𝐴 ∩ 𝐶)
𝑃(𝐴 ∪ (𝐵 ∩ 𝐶 ) = 𝑃(𝐴 ∪ 𝐵) ∩ 𝑃(𝐴 ∪ 𝐶)
o Counting Techniques:
A- Spaces: _____ × _____ × _____ ×………..
B- Arrangement:
o (n) Distinct items: 𝑛!
𝑛!
o (n) items with (k) items repeating:
𝑘!
C- Selection:
𝑛!
o No order: combination: 𝑛𝐶𝑟 = (𝑛−𝑟)!×𝑟!
𝑛!
o With order: permutation: 𝑛𝑃𝑟 = (𝑛−𝑟)!
D- Tree diagram : used when we have parts of parts
E- Venn- Diagram: used when we have intersecting sets
Notes:
o 𝑃(𝐴) = 𝑃(𝐴 ∩ 𝐵) ∪ 𝑃(𝐴 ∩ 𝐵̅ )
𝐴∩𝐵 =𝐴
o 𝐴 ⊂ 𝐵 ⇔ { 𝑎𝑛𝑑 }
𝐴∪𝐵 =𝐵
𝜙∩𝐵 =𝜙
o Since 𝜙 ⊂ 𝐵 ⇔ { 𝑎𝑛𝑑 }
𝜙∪𝐵 =𝐵
𝜙 ={}
o Probability density function: (pdf)
 Discrete Case: Rules:
1- f(x) can be found with conditions
MAT 210 Prepared by: Hiba Othman

2- the probability distribution (which is a table showing x and f(x)) could be


constructed
3- P(x) = f(x)
4- ∑ 𝑓(𝑥) = 1 𝑎𝑛𝑑 0 ≤ 𝑓(𝑥) ≤ 1 (note: those two are the conditions needed to
prove that a function is a pdf)
5- Expected value : μ𝑥 = 𝑥̅ = 𝐸(𝑥) = ∑ 𝑥𝑓(𝑥)
6- Variance: σ2 𝑥 = 𝐸(𝑥 2 ) − [𝐸(𝑥)]2 𝑤ℎ𝑒𝑟𝑒 𝐸(𝑥 2 ) = ∑ 𝑥 2 𝑓(𝑥)
7- Cumulative pdf: F(x) = ∑ 𝑓(𝑥)
 Continuous Case: Rules:
1- f(x) should be given with a domain
2- the probability distribution (which is a table showing x and f(x)) could not be
constructed
𝑏
3- P(a ≤ x ≤ b) = ∫𝑎 𝑓(𝑥)𝑑𝑥
4- ∮𝐷𝑓 𝑓(𝑥)𝑑𝑥 = 1 & 𝑓(𝑥) > 0 (note: those two are the conditions needed to
prove that a function is a pdf)
5- Expected value : μ𝑥 = 𝑥̅ = 𝐸(𝑥) = ∮𝐷𝑓 𝑥𝑓(𝑥)𝑑𝑥

6- Variance: σ2 𝑥 = 𝐸(𝑥 2 ) − [𝐸(𝑥)]2 𝑤ℎ𝑒𝑟𝑒 𝐸(𝑥 2 ) = ∮𝐷𝑓 𝑥 2 𝑓(𝑥)𝑑𝑥


𝑘
7- Cumulative pdf: F(𝑥 ≤ 𝑘) = ∫𝑖 𝑓(𝑥)𝑑𝑥
where i: initial point in the domain of the function f(x)

 Linear Relations for pdf: Rules:


Given: m(x)= ax+b:
1- E(b)=b
2- E(m(x))=E(ax+b)=aE(x)+b
3- σ2 𝑏 = 0
4- σ2 𝑎𝑥+𝑏 = 𝑎2 σ2 𝑥
o Joint Probability density function: (pdf)
 Discrete Case: Rules:
1- f(x,y) can be found with conditions
2- the probability distribution (which is a table showing x & y and f(x,y)) could be
constructed
3- P(x,y) = f(x,y)
4- ∑ ∑ 𝑓(𝑥, 𝑦) = 1 𝑎𝑛𝑑 0 ≤ 𝑓(𝑥, 𝑦) ≤ 1 (note: those two are the conditions
needed to prove that a function is a joint pdf)
5- Each function has two marginal functions:
𝑔(𝑥) = ∑𝑦 𝑓(𝑥, 𝑦) &: ℎ(𝑦) = ∑𝑥 𝑓(𝑥, 𝑦)
6- We have 3 Expected values:
a. μ𝑥 = 𝑥̅ = 𝐸(𝑥) = ∑ 𝑥𝑔(𝑥)
MAT 210 Prepared by: Hiba Othman

b. μ𝑦 = 𝑦̅ = 𝐸(𝑦) = ∑ 𝑦ℎ(𝑦)
̅̅̅ = 𝐸(𝑥𝑦) = ∑ ∑ 𝑥𝑦𝑓(𝑥, 𝑦)
c. μ𝑥𝑦 = 𝑥𝑦

7- We have 3 Variances:
a. σ2 𝑥 = 𝐸(𝑥 2 ) − [𝐸(𝑥)]2 𝑤ℎ𝑒𝑟𝑒 𝐸(𝑥 2 ) = ∑ 𝑥 2 𝑔(𝑥)
b. σ2 𝑦 = 𝐸(𝑦 2 ) − [𝐸(𝑦)]2 𝑤ℎ𝑒𝑟𝑒 𝐸(𝑦 2 ) = ∑ 𝑦 2 ℎ(𝑦)
c. σ 𝑥𝑦 = 𝐸(𝑥𝑦) − 𝐸(𝑥). 𝐸(𝑦)
 Continuous Case: Rules:
1- f(x,y) should be given with a domain
2- The probability distribution (which is a table showing x & y and f(x,y)) could not
be constructed
𝑑 𝑏 𝑏 𝑑
3- P(a ≤ x ≤ b, c ≤ y ≤ d ) = ∫𝑐 ∫𝑎 𝑓(𝑥, 𝑦)𝑑𝑥 𝒅𝒚 = ∫𝑎 ∫𝑐 𝑓(𝑥, 𝑦)𝑑𝑦 𝒅𝒙
4- ∯𝐷𝑓 𝑓(𝑥, 𝑦)𝑑𝑥𝑑𝑦 = ∯𝐷𝑓 𝑓(𝑥, 𝑦)𝑑𝑦𝑑𝑥 = 1 & 𝑓(𝑥, 𝑦) > 0 (note: those two are
the conditions needed to prove that a function is a pdf)
5- 3 Expected values :
a. μ𝑥 = 𝑥̅ = 𝐸(𝑥) = ∮𝐷𝑓 𝑥𝑔(𝑥)𝑑𝑥

b. μ𝑦 = 𝑦̅ = 𝐸(𝑦) = ∮𝐷𝑓 𝑦ℎ(𝑦)𝑑𝑦

c. μ𝑥𝑦 = 𝑥𝑦
̅̅̅ = 𝐸(𝑥𝑦) = ∯𝑫𝒇 𝒙𝒚𝒇(𝒙, 𝒚)𝒅𝒙𝒅𝒚
6- We have 3 Variances:
a. σ2 𝑥 = 𝐸(𝑥 2 ) − [𝐸(𝑥)]2 𝑤ℎ𝑒𝑟𝑒 𝐸(𝑥 2 ) = ∮𝐷𝑓 𝑥 2 𝑔(𝑥)𝑑𝑥

b. σ2 𝑦 = 𝐸(𝑦 2 ) − [𝐸(𝑦)]2 𝑤ℎ𝑒𝑟𝑒 𝐸(𝑦 2 ) = ∮𝐷𝑓 𝑦 2 ℎ(𝑦)𝑑𝑦


c. σ 𝑥𝑦 = 𝐸(𝑥𝑦) − 𝐸(𝑥). 𝐸(𝑦)

σ 𝑥𝑦
7- The correlation coefficient: 𝝆𝒙𝒚 =
σ 𝑥 .σ 𝑦
 Linear Relations for joint pdf: Rules:
Given: m(x,y)= ax+by+c:
1- E(c)=c
2- E(m(x,y))=E(ax+by+c)=aE(x)+bE(y)+c
3- σ2 𝑐 = 0
4 − σ2 𝑎𝑥+𝑏𝑦+𝑐 =

𝑖) 𝑎2 σ2 𝑥 + 𝑏 2 σ2 𝑦 in case x & y are independent

𝑖𝑖) 𝑎2 σ2 𝑥 + 𝑏 2 σ2 𝑦 + 2𝑎𝑏σ 𝑥𝑦 in case x & y are dependent


MAT 210 Prepared by: Hiba Othman

 Check for Independence: x & y are independent if:


o g(x).h(y)=f(x,y)
o E(x).E(y) =E(x,y)
o σ 𝑥𝑦 = 0

o 𝝆𝒙𝒚 = 0
 Chebychev's Formula:
1
𝑃(𝜇 − 𝑘𝜎 < 𝑥 < 𝜇 + 𝑘𝜎) ≥ 1 −
𝑘2

You might also like