Scribd
Upload
2 views

Lecture 3 Probabilitydescription

probability description

Uploaded by

jagritisingh2006
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
2 views

Lecture 3 Probabilitydescription

probability description

Uploaded by

jagritisingh2006
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 15

Probability basic concepts

• Sample space or ensemble is the set of points containing all possible outcomes of an
experimental measurement. Sample space or ensemble can be finite or infinite.
• Event space is any subset of sample space
• Suppose the set of sample space is denoted by 𝑆
• Suppose an event space is denoted by 𝐸 and the probability of event 𝐸 is denoted by
𝑃(𝐸)
• Axioms of probability:
• For an event 𝐸 ⊆ 𝑆, 0 ≤ 𝑃(𝐸) ≤ 1
• 𝑃 𝑆 =1
• For mutually exclusive events 𝐸𝑗 with 𝑗 = 1,2, … , 𝑁 and 𝐸𝑖 ∩ 𝐸𝑗 = 𝜙 (𝑖 ≠ 𝑗),
𝑁 𝑁

𝑃 ራ 𝐸𝑗 = 𝑃 𝐸1 ∪ 𝐸2 ∪ ⋯ 𝐸𝑁 = ෍ 𝑃(𝐸𝑗 )
𝑗=1 𝑗=1

19 August 2024 APL103, Experimental Methods 1


Probability basic concepts
• Principle of counting
• Suppose 2 experiments are performed. Suppose exp. 1 can have 𝑀 outcomes.
Suppose for each outcome of exp. 1, the number of possible outcomes for
exp. 2 is 𝑁. Then for the two experiments, there are 𝑀𝑁 possible outcomes.
• Generalization to R experiments:
• Suppose R experiments are performed. Suppose exp. 1 can have 𝑁1 outcomes. Suppose
for each outcome of exp. 1, there are 𝑁2 possible outcomes for exp. 2. Suppose for each
outcome of exp. 1 and exp. 2, there are 𝑁3 possible outcomes for exp. 3 and so on, that
is, for each outcome of (1,2, … , 𝐽) experiments there are 𝑁𝐽+1 possible outcomes for
exp. 𝐽 + 1. Then the total possible outcomes for R experiments are 𝑁1 𝑁2 … 𝑁𝑅

19 August 2024 APL103, Experimental Methods 2


Probability basic concepts
• Conditional probability:
• Let 𝐸 and 𝐹 be events in sample space 𝑆. Then 𝑃(𝐸|𝐹) is the conditional
probability of the occurrence of 𝐸 given that 𝐹 has occurred.
𝑃 𝐸⋂𝐹
𝑃 𝐸𝐹 =
𝑃 𝐹
• Independent events:
• Let 𝐸 and 𝐹 be events in sample space 𝑆. Events 𝐸 and 𝐹 are independent if
𝑃 𝐸 ∩ 𝐹 = 𝑃 𝐸 𝑃(𝐹)
• For independent events 𝐸 and 𝐹, 𝑃 𝐸 𝐹 = 𝑃(𝐸)

19 August 2024 APL103, Experimental Methods 3


Probability basic concepts
• Types of random variables:
• Discrete random variable: A discrete random variable, say 𝑋, can have finite or
infinite number of possible values in the form of a discrete sequence 𝑥1 , 𝑥2 , …
• Continuous random variable: A continuous random variable, say 𝑌, can have a
continuum of possible values
• Probability distribution function for a random variable, say 𝑋, is defined as
𝑃 𝑥 = 𝑝𝑟𝑜𝑏𝑎𝑏𝑖𝑙𝑖𝑡𝑦[𝑋 ≤ 𝑥]
where
𝑃 𝑥 = 0 for 𝑥 → −∞
𝑃 𝑥 = 1 for 𝑥 → ∞

19 August 2024 APL103, Experimental Methods 4


Probability basic concepts
• Probability density function for a random variable 𝑋 is defined as
𝑝 𝑥 = lim 𝑝𝑟𝑜𝑏𝑎𝑏𝑖𝑙𝑖𝑡𝑦 𝑥 ≤ 𝑋 ≤ 𝑥 + ∆𝑥 /∆𝑥
∆𝑥→0

• The following points can be noted


𝑑𝑃
•𝑝 𝑥 = relates the probability distribution to the density function
𝑑𝑥
∞
• ‫׬‬−∞ 𝑝 𝑥 𝑑𝑥 = 1 (normalization condition)
• 𝑝 𝑥 ≥0
• For discrete random variable, 𝑝 𝑥 can be expressed in terms of Dirac Delta
functions

19 August 2024 APL103, Experimental Methods 5


Probability basic concepts
• Joint probability distribution function
• Suppose there are two random variables 𝑋 and 𝑌. We are interested in
looking at the relation between the two random variables 𝑋 and 𝑌.
• Define the joint probability distribution function for variables 𝑋 and 𝑌 as
𝑃 𝑥, 𝑦 = 𝑝𝑟𝑜𝑏𝑎𝑏𝑖𝑙𝑖𝑡𝑦[𝑋 ≤ 𝑥, 𝑌 ≤ 𝑦]

• Joint probability density function for the two random variables 𝑋 and
𝑌 can be obtained from the joint distribution function from
𝜕2𝑃
𝑝 𝑥, 𝑦 =
𝜕𝑥𝜕𝑦

19 August 2024 APL103, Experimental Methods 6


Probability basic concepts
• Suppose there are two random variables 𝑋 and 𝑌
• Independent random variables: 𝑋 and 𝑌 are independent random
variables if
𝑝𝑟𝑜𝑏𝑎𝑏𝑖𝑙𝑖𝑡𝑦 𝑋 ≤ 𝑥, 𝑌 ≤ 𝑦 = 𝑃 𝑥, 𝑦 = 𝑃 𝑥 𝑃(𝑦)

• For two independent random variables 𝑋 and 𝑌, the joint probability density
function can be written as a product
𝑝 𝑥, 𝑦 = 𝑝 𝑥 𝑝(𝑦)

19 August 2024 APL103, Experimental Methods 7


Probability basic concepts
• Expected value or mean value or average value for a random
variable 𝑋 is given by 𝐸[𝑋]
• For a discrete random variable 𝑋 which can take values from a discrete
sequence 𝑥1 , 𝑥2 , …, 𝑥𝑁
𝑁

𝐸 𝑋 = ෍ 𝑥𝑗 𝑃(𝑥𝑗 )
𝑗=1

• For a continuous random variable 𝑋 which can take values in the interval
[𝑎, 𝑏] and has a probability density function 𝑝(𝑥)
𝑏
𝐸 𝑋 = න 𝑥𝑝 𝑥 𝑑𝑥
𝑎

19 August 2024 APL103, Experimental Methods 8


Probability basic concepts
• For a real valued function 𝒈(𝑿) of a discrete random variable 𝑿
which can take values from a discrete sequence 𝑥1 , 𝑥2 , …, 𝑥𝑁
𝑁

𝐸 𝑔(𝑋) = ෍ 𝑔(𝑥𝑗 )𝑃(𝑥𝑗 )


𝑗=1
• For a real valued function 𝒈(𝑿) of a continuous random variable 𝑿
which can take values in the interval [𝑎, 𝑏] and has a probability
density function 𝑝(𝑥)
𝑏
𝐸 𝑔(𝑋) = න 𝑔(𝑥)𝑝 𝑥 𝑑𝑥
𝑎

19 August 2024 APL103, Experimental Methods 9


Probability basic concepts
• For a real valued function 𝒈(𝑿, 𝒀) of discrete random variables 𝑿
and 𝒀
𝐸 𝑔(𝑋, 𝑌) = ෍ ෍ 𝑔(𝑥𝑗 , 𝑦𝑘 )𝑃(𝑥𝑗 , 𝑦𝑘 )
𝑗 𝑘
• For a real valued function 𝒈(𝑿, 𝒀) of continuous random variables 𝑿
and 𝒀 with values in the interval (−∞, ∞) and joint probability
density function 𝑝(𝑥, 𝑦)
∞ ∞
𝐸 𝑔(𝑋, 𝑌) = න න 𝑔(𝑥, 𝑦)𝑝 𝑥, 𝑦 𝑑𝑥𝑑𝑦
−∞ −∞

19 August 2024 APL103, Experimental Methods 10


Probability basic concepts
• If 𝑎 and 𝑏 are constants, then for any random variable 𝑋
𝐸 𝑎𝑋 + 𝑏 = 𝑎𝐸 𝑋 + 𝑏
• Consider a random variable 𝑋 as a linear combination of random
variables 𝑋𝑖 where coefficients 𝑎𝑖 are constants,
𝑁

𝑋 = ෍ 𝑎𝑖 𝑋𝑖
𝑖=1
Then
𝑁

𝐸 𝑋 = ෍ 𝑎𝑖 𝐸[𝑋𝑖 ]
𝑖=1

19 August 2024 APL103, Experimental Methods 11


Probability basic concepts
• Variance of a random variable 𝑋 is 𝐸[(𝑋 − 𝜇)2 ] where 𝜇 = 𝐸[𝑋]

19 August 2024 APL103, Experimental Methods 12


Probability basic concepts
• Covariance of random variables 𝑋 and 𝑌 is 𝐸[(𝑋 − 𝜇𝑋 )(𝑌 − 𝜇𝑌 )]
where 𝜇𝑋 = 𝐸[𝑋] and 𝜇𝑌 = 𝐸[𝑌]

19 August 2024 APL103, Experimental Methods 13


Probability basic concepts
• Covariance of independent random variables 𝑋 and 𝑌 is zero

19 August 2024 APL103, Experimental Methods 14


Probability basic concepts
• Correlation coefficient of random variables 𝑋 and 𝑌 is
𝐶𝑜𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 𝑋,𝑌
𝑟=
𝑉𝑎𝑟𝑖𝑎𝑛𝑐𝑒 𝑋 𝑉𝑎𝑟𝑖𝑎𝑛𝑐𝑒 𝑌

19 August 2024 APL103, Experimental Methods 15

You might also like