MODULE 6 SAMPLING THEORY D SAMPLING THEORY SAMPLING the process of taking a part of a total population of living g things that would represent the outcome of the entire {group this is done to make statistical data easier to create rather than taking the account of all the population DEFINITIONS Population ~ This consists ofthe total participants or observationsSAMPLING THEORY SAMPLING This is the process of taking a part of a total population of ving fr non living things that would represent the outcome of the entire {group this is done to make statistical data easier to create rather than taking the account of all the population DEFINITIONS Population ~ This consists ofthe total participants or observations Noted that sampling is made to avoid biases on a certain target of population therefore itis always recommended that the sampling ust be randomized Let us review of the Simple Statistics THIS 1S FOR RAW DATA Median = The center point of the reading Mode = Most frequent appearing value Variane Tha 0?SAMPLING THEORY # A comparison of coffee prices at 4 randomly selected grocery stores in San Diego showed increases from the previous month of 12, 16, 17, and 20 cents for a I-pound bag. Find the variance of this random sample of price increases, Solution Mean = (12 +15 +17 + 20)/4 = 16 conte Variance Also note that in sampling theory of random the variance is equivalent to this formula SAMPLING THEORYSAMPLING THEORY # Find the variance of the data 3, 4,5, 6,6, and 7, representing the umber of trout caught by a random sample of 6 fishermen on June 19,1986, at Lake Muskoka, Solution Then Pein Dh we obs eet F eS Whit 234445464647 =31 Then a gam -@ny=2 SAMPLING THEORYSAMPLING THEORY SAMPLING DISTRIBUTION The probability distribution of a statistical data is called as this fone and this distribution can only be accessed after analyzing and Inferencing statistical data The Central timit Theorem IF x's the mean of the sample size n taken from a population with the mean and finite variance a then the limiting form of the distribution willbe aaXo als) This is only good it n > 30 provided that the population is not essentially randomized to the point of skewing or breaking the data # An electrical firm manufactures light bulbs that have a length of lite that is approximately normally distributed, with mean equal to 1800 hours and a standard deviation of 40 hours. Find the probability that a random sample of 16 bulbs will have an average life of lass than 775 hours Solution P(X<715) +z Then P (2-25) = 0.0062 SAMPLING THEORY 4 Traveling between two campuses of a university in city via shuttle bus takes, on average, 28 minutes with a standard deviation of 59.0062 SAMPLING THEORY # Traveling between two campuses of a university in city via shuttle bus takes, on average, 28 minutes with a standard deviation of 5 minutes, In a given week, a bus transported passengers 40 times What is the probability that the average transport time was mare than 20 minutes? Assume the mean time Is measured to the nearest minute Solution P (X>30) =1~P(X « 30) then getting Z Xow 30 nS Then -P(2 < 2530) 0.0008 # The heights of 1000 students are approximately normally Jistributed with a mean of 1745 centimeters and a standard oviation of 8.9 centimeters. Suppose 200 random samples of size 25 fare drawn from this population and the means recorded to the nearest tenth of a centimeter. Determine 1.) the number of sample means fall 1g below 172.0 centimeters. Solution: P (1720) ; Noted that this is a mean therefore 171.95 - 1745 , 2a MASSES 7 2-105 +P = 00322 ‘Then # of people = 200(0,0322) = 6.44 say 6 peopl SAMPLING THEORY # If the standard error of the mean for the sampling distribution of random samples of size 36 from a large or infinite population is 2,Then # of people = 200(0,0322) = 6.44 soy 6 people SAMPLING THEORY 4 If the standard error of the mean for the sampling distribution of random samples of size 36 from a large or infinite population is 2, how large must the size of the sample become if the standard error is tobe reduced to12? Solution o=2 )' = 100 n=36 a= 2N3B= 12 4# Given the population 10,10, 12,18, and 16, find the probability that a random sample size of 100, selected with replacement, will have a sample mean greater than {15 but less than 125, Assume the means to be measured to the nearest tenth. Solution (10#10 12 +13 +15)/5 2 Variance = 18/5; standard of deviation of the population = [= p(s «x 125); Then P= 0.9959 - 0.0042= 0.9916 Drag fronLess he Vi00 4 Then P= 0.9958 - 0.00425 0. SAMPLING THEORY SAMPLE OF 2MEANS There are times that we need to get a range of a sample therefore there is a need to get a sample of two means Unlike the other Z ~ score , in this case if itis random sampling we will need to get the actual probability using this method 4 =) = =, le) VW This would be a standard normal variable # The television picture tubes of manufacturer A have a mean lifetime of 6.5 years and a standard deviation of 0.8 year, while those fof manufacturer B have a mean lifetime of 60 years and a standard eviation of 0.8 year. What is the probability that a random sample of 36 tubes from manufacturer A will have @ mean lifetime that is at least 1 year more than the mean lifetime of a sample of 49 tubes from manufacturer B? Solution: Pxen) z= 10.9960 = 0.0040 SAMPLING THEORY # Two alloys A and 8 are being used to manufacture a certain stee! product. An experiment needs to be designed to compare the two InSAMPLING THEORY 4# Two alloys A and 8 are being used to manufacture a certain ste! product. An experiment needs to be designed to compare the two in terms of maximum load capacity in tons (the maximum weight that can be tolerated without breaking). Its known that the two standard deviations in load capacity are equal at § tons each. An experiment is conducted in which 30 specimens of each alloy (A and 8) are tested and the results recorded as follows: Xa =495; Xb = 455 The manufacturers of alloy A are convinced that this evidence shows conclusively that yA > uB and strongly supports the claim that their flley is superior. Manufacturers of alloy B'claim that the experiment Could easily have given Xa - xb = 4 even if the two population means {re equal. In other words, “the results are inconclusive!” (a) Make an fargument that manufacturers of alloy B are wrong. Do it by computing P(Xa - b> 41 y= 8). solution P (Xa - Xb > 4) 3.10 & Probability =1- 0.9990 = 0,001 DATA Is CORRECT SAMPLING THEORY T— DisTRIBUTION Drag fronSAMPLING THEORY ‘T~ DISTRIBUTION There are some scenarios in which that the standard of deviation is not known but can stil have its own distribution pattern thus alimit to the central limit theorem with that in mind. Considering that all other values are present therefore: Where 5 - variance of the population ; Noted that the t ~ distribution relies on the degrees of freedom Degrees of Freedom - is the number of values of a variable which are free to vary. It is equal to the number of observations minus the umber of parameters that ate being estimated from the sample data, (THIS IS FOR T ~ DISTRIBUTION) This isthe distribution pattern Drag fronSAMPLING THEORY # The final grades in English of first year high school students in a Certain university are normally distributed with a mean of 78. A sample of size 25 yielded standard deviation of 85. If random samples of the same size are drawn from the given population, what is the probability of obtaining a sample mean? 1a) Higher than 80 'b) Lower than 75 Solution: P (X> 80) ; Then converting to T Ta Sgt 7 = Se" T= 1818; freedom = 25 checking the diagram Par 2SAMPLING THEORY Upon checking the diagram the t value of 1818 is between 1701 and 2064 Then to get the probability we therefore need to interpolate 2.068 Laie 0025 Then by interpolating 2066-1918 0.025 2068 1.711 ~ 025 — 0.050 0.0428 Then for Lower than 75 w Then by checking and interpolating we get that = 0.0056 SAMPLING THEORY Penns) Timea!i aK} ao a= 0.0056 SAMPLING THEORY # A manufacturing firm claims that the batteries used in their electronic games will last an average of 30 hours. To maintain this ‘average, 6 batteries are tested each month. I the computed t value falls between t = -0.025 and t = 0,025, the firm is satisfied with its Claim. What conclusion should the firm draw from a sample that has ‘@ mean 275 hours and a standard deviation s = 5 hours? Assume the distribution of battery lives to be approximately normal Solution finding the part of the distribution: Getting the value of t Upon checking we can check that itis between those values therefore itis appropriate Drag fron