Lecture 12 ON MATH-208 (Probability and Statistics) BY Kiran Kumar Shrestha Department of Mathematics School of Science Kathmandu University TO CE - II – I Group Students Topics Covered Normal Distribution Date: Thursday, June 3, 2021 Normal Distribution (Notes Continued...) #.9 Probability properties If ( ), then ( ) ( ) ( ) For a normal distribution 68.26% of data lie between the points of inflection, i.e., In the same way, 99.73% of data lie between 0.0027 lie outside . and only 100%-99.73% = 0.27% = Example, If X ~ N(24, 32) , then (a) ( ) ( ) ( ) (b) ( ) ( ) (c) ( ) ( ) #.10 The kurtosis of a normal distribution is 3, i.e., or it is mesokurtic. #.11 The linear combination of normal random variables also follow normal distribution. For example- If ( ) . ( Since ) ( ) ( ) #.(i) Let Y1 = 2X, then ( ) ( Hence ( ) ( ) ( ) #.12 Let ( ( ) and ( ) ( ) ( ) ( ) ( ) ( Hence ( ) ) #.(ii) Let Y2 = 2X+3, then ( ) ( ) ( ) ( ) ( ) . ) ), then #.(a) ( ) #.(b) ( ) #.(c) ( ) A normal distribution having mean 0 and variance 1 is called standard normal distribution. Proofs: Since ( Let Next, ( ) Let Next, ( ) ) ( ) , then ( ) ( ) , then ( ) ( ) ( ) ( ( ) ( ) ( ) ) ( ) ( ) ( ) ( ) . Let, ( ) ( ) ( ( * ( ) ) ( ) ( ) * ( ) ) ( )+ ( )+ ( ( ) ) Thus, ( ) Standard Normal Distribution A standard normal distribution is that type of normal distribution which has mean 0 and variance 1. ( A normal distribution following transformation: ), then it can be converted into standard normal distribution by ( Standard normal distribution is usually denoted as ) The probability density function of standard normal distribution is ( ) √ For a standard normal distribution ( ) ( ) ( ) The cumulative distribution function (cdf) of standard normal distribution is given by ( ) ( ) ( ) ∫ ( ) ∫ √ The value of above integral for different levels of 'z' are given in a table called normal probability table as shown below- For example, from table we see that P(Z< = 1.22) = P(Z < 1.22) = 0.8888 Using Z-table #.1 Find following probabilities#.(a) P(Z<=1.25) = 0.8944 #.(b) P(Z < = 2.61) = 0.9955 #.(c) P(Z >1.12) = 1 – P(Z < 1.12) = 1 – 0.8686 = 0.1314 #.(d) P(Z < - 2.11) = P(Z > 2.11) (due to symmetry) = 1- P(Z < 2.11) = 1 – 0.9826=0.0174 Note: ( ) ( ) ( ) ( ) #.(d) P(Z > -1.72) P(Z>-1.72) = 1 – P(Z< -1.72) = 1 – (1 – P(Z < 1.72)) = P(Z < 1.72) = 0.9573 #.(e) P(0.75 < Z< 2.41) P(0.75 < Z < 2.41) = P(Z < 2.41) – P(Z < 0.75) = 0.9920 – 0.7734 = 0.2186 #.(f) P(-1.96 < Z < 1.96) ( ) ( ) ( * ) ( )+ ( ) #.2 Find 'c' if #.(a) P(Z < c) = 0.9793 From Z-table, P(Z < c)= P(Z < 2.04) So, c = 2.04 #.(b) P(Z < c) = 0.3594 Or, P(Z < c) = 1 – 0.6406 Or, 1 – P(Z < c) = 0.6406 Or, P(Z < - c) = 0.6406 Or, P(Z < -c) = P(Z < 0.36) So, - c = 0.36 Or, c = - 0.36 #.(c) P(Z > c) = 0.1093 Or, 1 – P(Z < c) = 0.1093 Or, P(Z < c) = 1 – 0.1093 Or, P(Z < c) = 0.8907 Or, P(Z < c) = P(Z < 1.23) So, c = 1.23 #.(d) P(Z > c) = 0.9920 Or, 1 – P(Z < c) = 0.9920 Or, P(Z < -c) = 0.9920 Or, P(Z < -c) = P(Z < 2.41) c = -2.41 #.(e) P(-c < Z < c) = 0.95 Or, P(Z < c) – P(Z < -c) = 0.95 Or, P(Z < c) – {1 – P(Z < c)}=0.95 Or, 2. P(Z < c) -1 = 0.95 Or, 2.P(Z < c) = 1.95 Or, P(Z < c) = 1.95/2 = 0.975 = P(Z < 1.96) So, c = 1.96 #.3 Given X ~ N(12 , 9), find P(X > 16). SolutionGiven X ~ N(12, 9). So Now, ( ) ( ) ( ) ( ) ( )