3 e 6 | Measures of Central Tendency and Location i One of the most common quantities used to summarize @ set of data is its center. The center is a single value, chosen in such a way that it gives a reasonable approximation of the concentration of data. There are many ways te approximate the center of a set of data. This chapter defines the three most common measures of central tendency: the mean, the median, and the mode. uantify what we mean when Measures of Central Tendency attempts to q t ed be ‘a data set. The concept is we think of as the "typical" or "average" score in important and we encounter it in daily ite. For example, we often want to know before purchasing a machine or an electronics equipment its average enery consumption per kilowatt-hour. Or, if you are a basketball player, you might often think about your “average points per game”. This chapter gives the answer to such a question using the mean, median and mode. The Arithmetic Mean is the most widely used measure of central ed set of data as the sum scores in the distribution, le being measured, The mean, or “arithmetic average", tendency. The mean is defined technically for ungroups of all the data scores divided by the total number of denoted byz. If we use the letter x; to represent the variabl then symbolically, the mean is defined as; x Illustrative Example: bs The data provided below in minutes shows the amount of time each 11 secretarial applicants spent encoding a certain annual report of the company assigned to them as one of the basic requirements for the secretarial position in a certain multi-national ‘company in Makati City. [18, 25,30, 27,28, 24,19, 18,27, 23,15] Compute the mean Solutior Dhix ta t%2t + An n n z= Scanned with CamScannerMeasures of Central Tendency and Location | 37 ga 18 +25 +304 27 +28 +24 +19 418427423415 He. & = 23.09 minutes The Median 4, rechnically, the median of a distribution is the value that cuts the distribution exactly in half. The median is by definition what we call the middle value of the ungrouped data, It can easily be computed by sorting the data from smallest to largest and look for the "middle" score in the distribution. The median place can be determined after arranging the data in ascending order using the following equation: "Median place = "t+ The median is simply the middle value of the ungrouped data when (n+1)/2 is an integer, but if (n+1)/2 is not an integer, median is the average of two middle values in the data set. Illustrative Example: Now, let us try to find the median of theamount of time that the 11 secretarial applicants spent encoding a certain annual reportassigned to them which was discussed beforehand. (18, 25,30, 27,28, 24,19, 18, 27, 23, 15] Solution: First, let us arrange the data in an array as follows: 15,18, 18, 19,23, 24, 25, 27,27,28, 30 Next, we must compute for the place (n+1)/2, wheren is the number of data points. Here, there are 11 data, so n = 11. Hence, Median place = y 4141" 2 =6" Scanned with CamScanner3B [Measures of Central Tendency and Location Finally, since the number of entries is an odd, we have one middle value that is 24. Therefore, the median is 24. 15, 18, 18, 19, 23, 24, 25, 27, 27, 28, 30 The Mode The mode of a data set illustrates which value occurs very often or most frequently. It is the simplest, but the least widely used measure of central tendency because obviously it cannot be subjected to further. statistical analysis, A distribution with a single mode is said to be unimodal. A distribution with two modesis said to be bimodal, trimodal if there are three modes, and multimodal for more than three modes. The data set does not have the mode when each number in the set occur the same number of times. Illustrative Example: 4 Find the mode for the following observations; [18, 25, 30,27, 28, 24, 19, 18 , 27, 23, 15] Solution: e two observations that occurred most. These are 18 Inthe given data, there ar ice. Therefore, the modes are 18 and 27 and and 27 wherein they occurred twit this is a bimodal distribution. Additionallllustrative Example: Find the mean, median and mode for’ the following ‘£5. observations; [5, 15, 9, 16, 5, 11, 10, 20, 25; 18] Solution: a) Mean R= Zhi t 7 got +15 +9+ 16 +5 +11 +10 +20+25+18 10 A 13.3 Scanned with CamScannerMeasares of Central Tendency and Location | 39 b) Median Arrange the data in an array[4, 5, 9, 10, 11; 15, 16, 18,20,25] Median place = 4-101. 2 5.5 Since the median place is 5.5 we locate the 5 and the 6” values and divide it by two as shown below: ©) Mode In this distribution, each data the mode does not exist. median = ——_ = edian 2 sth 4 6th 2 Characteristics of Mode, Median and Mean 11+15 Occur the same number of times, therefore Median Mode It is the value in a given aggregate which can be obtained if all the values are equal. It is the middle value of the data set. Tt is the most frequent value in the distribution. Thus, it is the point of greatest density. If the sum of the deviations on either side of the mean is equal, then the sum of the deviation is equal to zero. The value of the median is fixed by its position in the data set and does not reflect the individual value. The value of the mode is established by the dominant frequency. f Tt reflects the magnitude of every value. The distance between the median point and all the value in the data set is less than from any other point. It is the most probable value, hence the most typical. A data set has only one Mean. Every data set has only ‘one median. A distribution may have 2 or more modes. On the other hand, there is no mode in a_ rectangular distribution or if each data occurs the same number of times. Scanned with CamScanner40 | Measures of Central lendency and Location Means: may be manipulated algebraically: like the weighted mean of subgroups may be combined when properly weighted. Tt cannot be manipulated algebraically hence medians of subgroups cannot be weighted and combined. It cannot be manipulated algebraically: modes of subgroups cannot be combined Tt may be calculated even when __ individual values are unknown provided that the sum of the values and the sample size are known. It is stable since it is not | . affected by grouping procedures. The mode does not reflect the degree of modality. 4 Values need not be ordered or grouped in the computation of the mean. Values must be ordered, and may be grouped, for computation. It is unstable that it is influenced by grouping procedures. Measures of Central Tendency for Grouped Interval Data In an interval data, the mean, median and mode can be computed since the classes are given in numerical intervals. Mean In this chapter, Long Method formula (Mid- : Formula). to find the mean, we will use two formulas namely;the point Formula)and the Short Method formula (Coded The Long Method uses frequency and class mark of a particular class interval. By taking the sum of the product of the frequency and the class’mark for all class intervals divided by the sum of the frequencies for all class intervals, we have computed the mean. Using summation notation this is given as follows: where fjis the frequency of Dh fii the,i'*class interval, Mjis the class mark of the i**class interval and nis the sum of the frequencies for all class intervals. Scanned with CamScanner» Measures of Central Tendency and Location [41 Illustrative Example: iB The following is a frequency distribution of the number of / sports activities that students want to engage with during Gl og their teenage years. Using the long method formula, find * ¥ the mean for the distribution. Table 3.1 Distribution of the Number of Sport Activities of Students [Number ofSportsActivities [Frequency 0-4 5 i 5-9 8 10-14 2 15-19 13 20-24 7 25-29 30-34 Solution: Class Class Frequency Mark fiM: Interval (fi (m) 5(2) = 10 0-4 5 2 8(7) = 56 5-9 8 7 2(12) = 24 10-14 2 12 13(17) = 15-19 13 17 221 20 - 24 7 22 7(22) = 154 25-29 11 27 11(27) = 30 - 34 4 32 297 4(32) = 128 n=50 ZL fiMi= 890 Zi fim Scanned with CamScanner« A2 [Measures of central Tendency and Location The short method uses frequency, assumed mean and deviation from the assumed mean. Assumed mean, like the name suggests, is a guess or an assumption of the mean. Assumed mean is commonly denoted by the letter 4. M.. It doesn't need to be correct or even close to the actual mean and choice of the assumed mean is at your discretion. To obtain the mean,'we must follow the formula : : a zeus (Hah), . n Where A.M. is the assumed mean, fris the frequency of the class interval, dis the deviation from where we assumed our mean and cis the class size. . Illustrative Example: Let us use the data presented in table 3.1 and calculate the mean of the number of sports activities of the students using the short method, Solution: Class Frequenc | Differenc nen Marks y e . fid A) a) 3 5¢3)=- 0-4 5 3 ie 5-9 12 8 2 a(-2) = - 10-14 2 1 16 . 4-1) =- x 15-19 17 13 0 13@=0 20-24 2 7 1 70) = 25-29 2 1 2 11(2) = 30 - 34 4 3 22, 4(3)_= 12 n=50 > Te Scanned with CamScannerMeasures of Central Tendency and Location | 43 Note that the assumed mean A.M. = 17, which is the class mark of the coe interval 15 - 19 and c = 5, which is the class size. The deviations dare obtain as follows: a) Set the deviation of the class interval containing the assumed mean to be zero (0), because it is the deviation of the assumed mean itself. b) The deviations of the class intervals smaller than the class interval containing the assumed mean are -1, -2, -3, -4 and so on. c) Similarly, the deviations of the class intervals larger than the class interval containing the assumed mean are 1, 2, 3 and so on. By applying the coded formula, we obtain the following: “1k xeau.s (Bafid) n #174 (35 #=178 Median To determine the median for grouped data, we just follow the following steps: Step 1: We write the < CF (less than cumulative frequencies) for each class intervals . Step 2: We need to compute for the value of +. Step 3: Determine the median class which is the class interval whose < CFis equal to or greater than? . Step 4: Substitute the needed value in the formula given below to compute for the mediari, . mn < CFnén~ Mdn.= LCBan + (: a *) c Sman* WhereLCBnarclass is the lower class boundary of the median class; finan 1S the frequency of the median class; . Since 3 is 25, then the median class is found to be in the fourth class interval, 15 — 19. Next is to compute for LCBmdn, the lower class boundary of the median class, that is; Also note that fran = 13; < CFn= 15, = 50andc=5 i Step 4: Substituting these values to the formula gives us; i BC tn Mdn.= LCBman of ° Sman Mdn=145 + (238 )5 | | =14543.85 \ Mdn = 18,35, Scanned with CamScannerMeosures of Central Tendency and tocation 145 Mode : The mode is simply, the midpoint of the class interval containing the highest number of class frequencies. To determine the tnode for grouped data , we use the following formula; a . fue — fi Mo = LCByo + (te i z)é wherein LCBro is the lower class boundary of the modal class or the class having the highest frequency; fu. is the frequency of the modal class , f; is the frequency of the class before the modal class; f, is the frequency of the class after the modal class and c is the class size. Illustrative Example: For the past 40 days, the temperature in the city of Baguio were recorded and tabulated in a frequency distribution as follows: Table 3.2; Distribution of the Temperature In The City Of Baguio [Temperature in Degree Centigrade |Number of Days. 15-17 2 18-20 8 21-23 7 24-26 10 A 27-29 3 30-32 7 33-35 3 Solution: Class Frequency Interval (A 15-17 2 . 18-20 8 21-23 7 24-26 10 model dass Scanned with CamScanner46 a [Measures of Central Tendency and Location 27-29 + 3 30-32 7 33-35 3 Note hat the value of LCByo which is the lower boundary of the class interval 24 s ing the highest frequency is 23.5 , fro = 10, fi= 7, fe =3 and c= 3. ubstituting in the formula, we have * fo —f Mo = gas LCBuo + Ge == aye Mo = .23.5'+ qa) Mo = 24.4 Note: Sometimes we may want to get the average of k quantities with a particular weight for each quantity pertaining to their ralative importance. If we are going to compute for the mean in this case, we have the weighted average or weighted mean given as — Lh Wixi we Tew where: kis the number of quantities w; are the relative weight x; are the corresponding quantities If all the weights are the same, then we go back to the usual arithmetic mean. Illustrative Example: Determine the average of a student having a preliminary period grade of 85, a midterm period grade of 84 and a final period grade of 87 if the final is counted twice as the other periods. Solution: * Weg = 1 Wu =1 Weg =2 Scanned with CamScannerMeasures of Central Tendency and Location |47 3 Sim a14142=4 t=1 _ _ PG+MG + 2FG z= . 4 _ 85 + 84+ 2(87) I< ——. Fractiles Aside from the mean, the median and the mode , there are still other ways of describing a given set of data .These values are called quantiles like quartiles, deciles and percentiles. These are the extension of the median concept that divide a set into equal parts. The diagram below shows how these different measures are related. Quartiles ‘As the median divides a data set in half, the quartiles divide the data set into fourths. Hence the second quartile, denoted Q2, is the median. Quartiles are the three values of the variable that divide an ordered data set into four equal parts namely Q;, Q2 and Qs. It means that the value Qiseparates the distribution below it from the 75% of the distribution above it. While Q;, separates the distribution below it from the’25% of the distribution above it. - Mdn. Qa 2a q Scanned with CamScanner