The Central Limit Theorem

1 The Central Limit TheoremSuppose that a sample of sizenis selected from a population that has mean and standarddeviation . LetX1,X2, ,Xnbe thenobservations that are independent and identicallydistributed ( ). Define now the sample mean and the total of thesenobservations asfollows: X= ni=1 XinT=n i=1 XiThecentral Limit theoremstates that the sample mean Xfollows approximately the normaldistribution with mean and standard deviation n, where and are the mean and stan-dard deviation of the population from where the sample was selected. The sample sizenhasto be large (usuallyn 30) if the population from where the sample is taken is the population follows the normal distribution then the sample sizencan be either smallor summarize: X N( , n).To transform Xintozwe use:z= x nExample: LetXbe a random variable with = 10 and = 4. A sample of size 100 is takenfrom this population. Find the probability that the sample mean of these 100 observations isless than 9.

2 We writeP( X <9) =P(z <9 104 100) =P(z < ) = (from the standardnormal probabilities table).Similarly the Central Limit Theorem states that sumTfollows approximately the normaldistribution,T N(n , n ), where and are the mean and standard deviation of thepopulation from where the sample was transformTintozwe use:z=T n n Example: LetXbe a random variable with = 10 and = 4. A sample of size 100 istaken from this population. Find the probability that the sum of these 100 observations isless than 900. We writeP(T <900) =P(z <900 100(10) 100(4)) =P(z < ) = (fromthe standard normal probabilities table).Below you can find some applications of the Central Limit 1A large freight elevator can transport a maximum of 9800 pounds. Suppose a load of cargo containing 49 boxes must betransported via the elevator. Experience has shown that the weight of boxes of this type of cargo follows a distribution withmean = 205 pounds and standard deviation = 15 pounds.

3 Based on this information, what is the probability that all 49boxes can be safely loaded onto the freight elevator and transported?EXAMPLE 2 From past experience, it is known that the number of tickets purchased by a student standing in line at the ticket windowfor the football match ofUCLA againstUSCfollows a distribution that has mean = and standard deviation = that few hours before the start of one of these matches there are 100 eager students standing in line to purchase only 250 tickets remain, what is the probability that all 100 students will be able to purchase the tickets they desire?EXAMPLE 3 Suppose that you have a sample of 100 values from a population with mean = 500 and with standard deviation = What is the probability that the sample mean will be in the interval (490,510)?b. Give an interval that covers the middle 95% of the distribution of the sample 4 The amount of regular unleaded gasoline purchased every week at a gas station nearUCLA follows the normal distributionwith mean 50000 gallons and standard deviation 10000 gallons.

4 The starting supply of gasoline is 74000 gallons, and there is ascheduled weekly delivery of 47000 Find the probability that, after 11 weeks, the supply of gasoline will be below 20000 How much should the weekly delivery be so that after 11 weeks the probability that the supply is below 20000 gallonsis only :EXAMPLE 1We are givenn= 49, = 205, = 15. The elevator can transport up to 9800 pounds. Therefore these 49 boxes will be safelytransported if they weigh in total less than 9800 pounds. The probability that the total weight of these 49 boxes is less than9800 pounds isP(T <9800) =P(z <9800 49(205) 4915) =P(z < ) = 1 = 2We are given that = , = 2,n= 100. There are 250 tickets available, so the 100 students will be able to purchase thetickets they want if all together ask for less than 250 tickets. The probability for that isP(T <250) =P(z <250 100( ) 1002) =P(z < ) = 3We are given = 500, = 80,n= (490< x <510) =P(490 50080 100< z <490 50080 100) =P( < z < ) = (1 ) = = x 50080 100 x= , x= ThereforeP( < x < ) = 4We are given that = 50000, = 10000,n= 11.

5 The starting supply is 74000 gallons and the weekly delivery is 47000 the total supply for the 11-week period is 74000 + 11 47000 = 591000 The supply will be below 20000 gallons if the total gasoline purchased in these 11 weeks is more than 591000 20000 =571000 gallons. Therefore we need to findP(T >571000) =P(z >571000 11(50000) 1110000) =P(z > ) = 1 = LetAbe the unknown schedule delivery. Now the total gasoline purchased must be more than 74000 + 11 A want this with probability , orP(T >74000 + 11A 20000) = Thezvalue that corresponds to thisprobability is So, =74000+11A 20000 11(50000) 1110000 A= The weekly delivery must be Limit Theorem - proofFor the proof below we will use the following :LetXnbe a random variable with moment generating functionMXn(t) andXbe a random variablewith moment generating functionMX(t). Iflimn MXn(t) =MX(t)then the distribution function (cdf) ofXnconverges to the distribution function ofXasn.

6 Central Limit Theorem :IfX1,X2, ,Xnare (independent and identically distributed) random variables having thesame distribution with mean , variance 2, and moment generating functionMX(t), then ifn the limiting distribution of the random variableZ=T n n(whereT=X1+X2+ +Xn) is thestandard normal distributionN(0,1).Proof:MZ(t) =MT n n(t) =EeT n nt=e n ntMT(t n)ButT=X1+X2+ +Xn. From earlier discussion the mgf of the sum is equal to the productof the individual mgf. Here eachXihas mgfMX(t). Therefore,MT(t n) =[MX(t n)]nand soMZ(t) is equal toMZ(t) =e n nt[MX(t n)]nOne way to find the Limit ofMZ(t) asn is to consider the logarithm ofMZ(t):ln MZ(t) = n t+n ln MX(t n)ExpandingMX(t n), using the following (also see handout on mgf)MX(t) = xP(x) +t1! xxP(x) +t22! xx2P(x) +t33! xx3P(x) + we getln MZ(t) = n t+n ln 1 +t n1!EX+(t n)22!EX2+(t n)33!EX3+ 3 Now using the series expansion ofln(1 +y) =y y22+y33 y44+ wherey=t n1!

7 EX+(t n)22!EX2+(t n)33!EX3+ we get:ln MZ(t) = n t+n t n1!EX+(t n)22!EX2+(t n)33!EX3+ 12 t n1!EX+(t n)22!EX2+(t n)33!EX3+ 2+13 t n1!EX+(t n)22!EX2+(t n)33!EX3+ 3 Factoring out the powers oftwe obtain:ln MZ(t) =( n + n EX )t+(EX22 2 (EX)22 2)t2+(EX36 3 n EX EX22 3 n+(EX)33 3 n)t3+ BecauseEX= andEX2 (EX)2= 2the last expression becomesln MZ(t) =12t2+(EX36 EX EX22+(EX)33)t3 3 n+ We observe that asn the Limit of the previous expression islimn ln MZ(t) =12t2and thereforelimn MZ(t) = this is the mgf of the standard normal distribution. Therefore the limiting distribution ofT n nis the standard normal distributionN(0,1). 4 Central Limit Theorem - ExamplesExample 1A large freight elevator can transport a maximum of 9800 pounds. Suppose a load of cargo con-taining 49 boxes must be transported via the elevator. Experience has shown that the weight ofboxes of this type of cargo follows a distribution with mean = 205 pounds and standard deviation = 15 pounds.

8 Based on this information, what is the probability that all 49 boxes can be safelyloaded onto the freight elevator and transported?Example 2 From past experience, it is known that the number of tickets purchased by a student standing inline at the ticket window for the football match ofUCLA againstUSCfollows a distribution thathas mean = and standard deviation = Suppose that few hours before the start of one ofthese matches there are 100 eager students standing in line to purchase tickets. If only 250 ticketsremain, what is the probability that all 100 students will be able to purchase the tickets they desire?Example 3 Suppose that you have a sample of 100 values from a population with mean = 500 and withstandard deviation = What is the probability that the sample mean will be in the interval (490,510)?b. Give an interval that covers the middle 95% of the distribution of the sample 4 The amount of mineral water consumed by a person per day on the job is normally distributedwith mean 19 ounces and standard deviation 5 ounces.

9 A company supplies its employees with2000 ounces of mineral water daily. The company has 100 Find the probability that the mineral water supplied by the company will not satisfy thewater demanded by its Find the probability that in the next 4 days the company will not satisfy the water demandedby its employees on at least 1 of these 4 days. Assume that the amount of mineral waterconsumed by the employees of the company is independent from day to Find the probability that during the next year (365 days) the company will not satisfy thewater demanded by its employees on more than 15 5 Supply responsestrueorfalsewith an explanation to each of the following:a. The probability that the average of 20 values will be within standard deviations of thepopulation mean exceeds the probability that the average of 40 values will be within deviations of the population ( X >4) is larger thanP(X >4) ifX N(8, ).

10 C. If Xis the average ofnvalues sampled from a normal distribution with mean and ifcisany positive number, thenP( c X +c) decreases asngets 6An insurance company wants to audit health insurance claims in its very large database of trans-actions. In a quick attempt to assess the level of overstatement of this database, the insurancecompany selects at random 400 items from the database (each item represents a dollar amount).Suppose that the population mean overstatement of the entire database is $8, with populationstandard deviation $ Find the probability that the sample mean of the 400 would be less than $ The population from where the sample of 400 was selected does not follow the normal dis-tribution. Why?c. Why can we use the normal distribution in obtaining an answer to part (a)?d. For what value of can we say thatP( < X < + ) is equal to 80%?e. LetTbe the total overstatement for the 400 randomly selected items.