Measures of Central Tendency Contents ... 2.1 Inrodvetor 22 23. Arithmetic Mean (AM) 24 2.5 Meon of Combined Groups Objectives oF Requisites of Ideal Average ts ond Demerits of Avith 2.6 Medion 27 2.8 Merits ond Demerits of Median Median by Groph 2.9_Mode Key Words : Central Tendency, Average, Arithmetic Mean, Deviation, Combined Mean, Medi Deciles, Percentiles, Box Plot, Cumulative Frequency, Mode, Empirical Relation Objectives Averages are tools of summarizing data, finding representative. It also facilitates the ‘comparison. The methods of determining averages are illustrated in this chapter. The third ‘and fourth aspects of statisties are analysis and interpretation. Averages help in both analysis and interpretation. Introduction ‘We have studied in the previous chapters the various methods of summarizing date and its graphical representation, However it becomes essential to condense the data into a single ‘value, Such a single value is treated as a representative of data and it is referred to an ‘average or central value or measure of central tendency. It is desired that all the important [properties of the observations in the data should be represented in the average, The word average is very commonly used in day-to-day life, ‘Average marks, average profit, average run-rate of a team in one day. A For example ‘ingle value is suitable for comparison. Therefore, average is essential quantity. Average is & Wvalue around which most ofthe observations are clustered, hence this single value itself gives lear idea regarding phenomenon under study. an—s There are several types of averages used in practice according to the type of data ang purpose. In this chapter we study three important averages viz. mean, median and mode, 2.2 Objectives or Requisites of Ideal Average The following are the objecti 1. To obtain a single representative quantity for the entire data. 2. To facilitate comparison. There are several averages in use, hence it is necessary to discuss the requisites of 800d or.ideal average. The following are requisites of good average : (April 2015) 1. It should be simple to understand and easy to calculate. 2. It should be rigidly defined. 4. It should be based on all observations in the data. 4. It should be capable of further mathematical treatment. 5. _It should be least affected by extreme observations. 2.3 Arithmetic Mean (A.M.) eee This is very commonly used and widely applicable average. Definition : Arithmetic mean (A.M.) or mean is a sum of observations’ divided by number of observations i.e. AM, oi of observations According to the different types of data calculation of A.M. differs slightly. We consider these cases as given below : Case (i) Individual Observations or Ungrouped Data : Suppose x}, X>, ... , Xp is a set of n observations by definition, arithmetic mean will be Xp+X2+...+ AM, = 228th. (21) Numerator of right side of (2.1) can be symbolically written as Y x i.e, Xp + Xyt 2. + Xp. Symbol ¥ (sigma) represents the sum. Further it is a customary to denote A.M. by X. Hence AMS = 2 Case (ii) Discrete Frequency Distribution : Suppose x,, X3, ..., Xn are values with f), f), ... , fy as the corresponding frequencies. Clearly to find the sum of observations we need to add observation X,, f, times, observationXp, f times and so on, Hence sum of observations will be fx; + Gx) +... + fyxy and total er of observation vi e t, = es . number of observations will be f) + f+... + fy. Hence, rth... + fh Using © notation we get Case (iii) Continuous Frequency Distribution : In this case, frequency is associated to the entire class and not to any specific single value. This creates difficulty in choosing x, X3, ..., Xn For calculation purpose we make a reasonable assumption that the frequency is associated with mid-point of class or equivalently the frequency is distributed over the respective class uniformly. Thus, taking X,, X2, ..., Xn as the mid-values of class intervals we ~ calculate mean by the same formula discussed in case (ii), i-e. = 2x Dix Illustration 1 : Calculate the arithmetic mean of marks scored by a student in 7 subjects _ given below 261, 68, 69, 63, 70, 60, 78. : Solution : = _ Total marks scored x = Number of subjects — _ 614+68+69+63+70460+78 469 ae 7 SoS Ce ©—© _4 OO +—@- 58 60 62 64 66 68 70 72 74 76 78 80 Mean Fig. 2.1 It can be noticed, in the above illustration that the observations are nearer to 60, so for convenience we assume the mean to be 60 and obtain the sum of excess of marks. It will be (14+84+943+10+10+ 18 =49. We find the average of excess and add in the assumed mean. Thus mean will be 60+ = 67. The above discussion leads to a short-cut method of finding arithmetic mean. Short-cut Method or Derivation Method or Assumed Mean Method : This method reduces the calculations involved in finding mean. Following are the steps in the computational procedure of mean, (1) Decide a suitable figure ‘a’ which is referred as assumed mean. (2) Subtract ‘a’ from each observation, the difference so calculated is called deviation 'a!, we denote deviation by 'd’.(3) Find sum of d Yd_ in case of individual observations. ¥ fd in case of frequency distribution. (4) Use the following formula and find the mean : “x = a4 ~4 in case of individual observations n and Fe ce of frequency distribution. n Illustration 2 : Calculate arithmetic mean for the following frequency distribution : Observation (x) | 103 110 112 118 95 Frequency (f) | 4 6 10 72 3 Solution : We solve the problem by both the methods. 1. Direct method : x f fx 103 4 103 x 4=412 110 6 110 x 6 = 660 112 10 112 x 10=1120 118 12 118 x 12= 1416 95 3 95 x 3 = 285 Total | Nz=35 Six = 3893 *I fx _ 3893 = pees = "35" = 111.2286 2. Deviation method : Taking assumed mean a = 100, we prepare the following table and use deviation method. Deviations x d=x-a f fd d=x-100 103 3 4 D 110 10 6 60 a V2 10 120 118 18 2 OG a ES 3 -15 Lota N=35 Yfa = 393—_—_._ See -_ 393 Thus x sat N = 100 +35 = 100 + 11.2286 = 111.2286 Step-deviation method : We have seen that deviation method reduces the calculations when the observations are large in magnitude. Sometimes the observations or deviations are multiples of some number. Especially when we deal with frequency distribution of ‘continuous variables, deviations are found to be multiple of class width. In this situation step-deviation method is advisable. __ Steps in the computational procedure are given below : _ (1) Decide a suitable figure ‘a’. (assumed mean a). _ (2) Subtract ‘a’ from each observation and find deviation d (or class-mark) i.e. ‘ d =x-a, _ (3) Divide d, obtained in (2) by convenient figure 'h' (or by class width). - This figure is called as step-deviation. 3 d = hi Xd in case of individual observations Yfd' —_in case of frequency distribution. Salaries in&_| No. of employees O- 500 2 500 - 1000 8 1000 — 1500 12 1500 - 2000 23 2000 - 2500 25 2500 — 3000 20 3000 - 3500 9 3500 — 4000 1Solution : We use step-deviation method to find the mean 4 J | Class | Mid-values | d= 1750 | a | | | 0 7 i | 8 | 2 -6 | 500-1000 | = 750 - 1000 | -2 8 | -16 1000-1500 | 250 | -soo | -1 | 2] -2 | 1500-2000 | 1750 | o. | 0] | 23 0 | 2000 - 2500 2250 soo | i | os | os | 2500 - 3000 pe || 1000 2 20 40 | | 3000 ~ 3500 3250 1500 3 | 9 27 | 3500 - 4000 3750 2000 4 1 4 Total | - eo | eae) fd’ >a En) Note that a = 1750, 5 fd' = 62, N = 100 and h = 500. 6. 1750 + 799 x 500 Hence, x . X = 1750 +310 = 2060 Thus average salary is % 2,060. Effect of change of origin and Scale on Arithmetic mean : Change of origin means to add or to subtract a constant from each observation. Thus, if the original variable is denoted by x than x — a or x +a is a variable obtained by shifting the origin (where a is a constant). The new variable x ~ a is also referred as deviation, In this situation arithmetic mean need not be obtained again however from the earlier mean we can determine the mean after the change of origin. (1) If y =x-a then y = QQ) If y=x+a then JaXta Similarly, changing of scale means to multiply or to divide the observations by a constant. Thus, if x is the variable > or cx is a variable obtained by changing the scale, c being constant. In this case also we need not find the arithmetic mean once again due to change in scale. The change of scale is similar to step deviation. However the same relation is observed between old variable and the variable after changing the scale. We summarize the rules below : on (3) Ity=2 then ¥ =a ves ut ventral fenaency (4 If y =cx then F sex, (5) If y=ax+b then y sax +b. x=a a xXoa = (6) y= *S* then ¥ Illustration 4 : Suppose the arithmetic mean of arithmetic mean if each observation is (i) increased by 10 (ii) decreased by 5 (iii) doubled (iv) reduced to one third (v) doubled and then increased by 5 (vi) increased by 5 and then doubled. 50 observations is 120. Find the Solution : This illustration explains the change of origin and scale (or linear transformations). Let x = Original variable = y = New variable, @) y=x+10, y =X +10 =120+10 =130 (i) y=x -5, y =X-5 = 120-5 =115 (iii) y = 2x, y = 2 = 2x 120 = 240 : x = | x 1120 (iv) y=3, Yo ae 0 y = 2% +5 = 2x120+5 = 245 2% +5)= 2(120+5 25 Arithmetic mean possesses most of the requisites of good average. Hence it is widely used. We state below its merits and demerits : Merits : (April 2015) 1. _Itis easy to calculate and simple to follow. 2. It is based on all observations. 4. It is rigidly defined. 4. It possesses sampling stability. 5. It is capable of further mathematical treatment. Given the means and sizes of two or More groups we can find mean of combined group. We can find the total given the mean and lumber of observations.(April 2015, Demerits : 1. Itis applicable only for quantitative data 2. Itis unduly affected by extreme observations. 3. Iteannot be computed for frequency distribution with open end class. It cannot be determined graphically. Sometimes arithmetic mean may not be an observation in a data. For example, arithmetic mean of number of T.V. sets sold daily is 5.25. ok 2.5 Mean of Combined Groups % Many times it is required to compute mean of two groups combined together. If Means and sizes of groups are known we can determine the combined mean i.e. mean of combine group. Let x; be the arithmetic mean of first group of size n,. Similarly x, be mean of secong group of size n,, then the combined mean is derived as follows : = _ (Sum of observations in first group) x= a hence, n, xX; = Sum of observations in first group. Similarly, _n, X;_= Sum of observations in second group. Thus, the combined mean x, is ‘Sum of the observations in) _ (Sum on) Xe = (Size of first group) + (Size of second group) we Illustration 5 : Arithmetic mean of weight of 100 boys is 50 kg and the arithmetic mean of 50 girls is 45 kg. Calculate the arithmetic mean of combined group of boys and girls. Solution : Let x, and n, be the mean and size of group of boys and x, and n, be the mean and size of group of girls. So that n, = 100, x, = 50, n, = 50, X = 45. Hence, combined BX +M x, (100x 50) + (50x45) m+n, 7” 100+ 50 2250 = Tap = 48.3333 mean isMlustration 6 : The mean weekly salary paid to 300 employees of a firm is % 1,470 There are 200 male employees and the remaining are females. If mean salary of males is 1,505 Obtain the mean salary of females. Solution : Suppose x, and n, are mean and group size of males. x; and n, are mean and size of group of females, Xe is mean of all the employees considered together. _ BX $M X> Now, So aneta (200 x 1505) + (100 IL 200 + 100 301000 + 100 x: wn = or 441000 = 301000+ 100 x 4410 = 3010+ x, % 1,400 We have seen that arithmetic mean cannot be calculated for qualitative observations like ty, debating skill, honesty, blindness. Moreover if a frequency distribution includes open end class, mean does not exist and it is unduly affected by extreme observations. In order to vercome these drawbacks, other measures of central tendency, median or mode are used. Illustration : The arithmetic mean of 38, 43, 41, 39, 52, 48, 60, 167 is 61. This cannot be representative value of the data, because among 8 observations, 7 are smaller than arithmetic mean. Thus incase extreme observations are widely separated from most of the servations, arithmetic mean does not remain suitable, whereas median is suitable. Definition : Median is the value of middle most observation in the data when the observations are arranged in increasing (or decreasing) order of their values. Thus, median is the central observation. It divides the data into two equal parts. There are ual number of observation above as well as below the median. It is also called as jositional average. Frequency curve Fig. 2.2() Computation of Median for Ungrouped data : It may be noticed that in case of individual observations or of median does not require any formula. It can be determined by Suppose n is the number of observations in the data. If n is odd then there is only one (neh a L! pservation. On the other hand if n is even they ungrouped data computati inspection. _ middle most observation which is th th n n A there are two middle most observations which are 6) and (+ 1) - In this case we take median to be mean of these two middle most observations. We follow the procedure described below for calculating median. Step 1: Arrange the observations in increasing (or decreasing) order. Step 2 : Compute the median by the following criteria : Median = ae 2 ifnis even Illustration 7 : Following are the temperatures recorded in a certain city, observed ina certain week. 35, 38, 40, 39, 35, 36, 37 Obtain the median temperature. Solution : The ordered arrangement of 7 observations is 35, 35, 36, Since, n = 7isodd we get, Median = The value of (n + 1)/2% observation = The value of 4" observation = 37. Jlustration 8 : The following are the sales in @ for 6 days ina certain week. 3020, 4120, 3600, 3250, 3830, 4000 Obtain the median sale. Solution : The ordered arrangement of 6 observations is 3020, 3250, [3600, 3830}, 4000, 4120 Since n= 6 is even we get two middle observations. Hence (% value of (0) Ce value of (n/2 + ys) observation observation Median = Ge value of 3 (Ge value of o Nine observation observation a 3600+ 3830 Sse(ii) Computation of Median for Continuous frequency distribution : Suppose N is the frequency Since the variable under consideration is continuous we can estimate the observation. Hence regardless of N whether it is even or odd in continuous NY" ency distribution we take median to be the value of (3) observation. omputational procedure : : Obtain the class boundaries. Obtain less than cumulative frequencies. Locate the median class. Where median class is the class in which median ice. 1 = Lower boundary (extended class limit) of the median class N = Total frequency c.f. = Less than cumulative frequency of the class just preceding to median class. f = Frequency of median class Class width Illustration 9 : Calculate median for the following frequency distribution : (April 2015) Marks below 20 | 21-40 | 41-60 No. of students ad 32 Solution : Class boundaries Frequency | Less than cumulative frequency 0 - 20.5 1 1 < N22 20.5 - 40.5 9 cf.=10 < N/2 40.5 — 60.5] Median class I-32 42 > N2 16 58 60.5 — 80.5 “ a 80.5 - 100 Median = The value of N/2 i.e. 32.5" observation. M class : 40.5 — 60.5, because N/2 exceeds less than cumulative frequency for the time in this class. Therefore, / = 40.5, N/2 = 32.5, c.f. = 10, f= 32,h= 20.—y Hence, [2.7 Median — by Graphical Method Median can be obtained graphically by means of ogive curve. Plot less than cumulan frequency curve taking upper boundaries on x-axis, and less than cumulative frequency og . N : y-axis. Draw a line parallel to x-axis passing through point > on y-axis. From the point of intersection of the line and ogive curve, draw a perpendicular to x-axis. The value at the foot of perpendicular is the median. z Ni Cummulative frequency Class boundary Fig. 2.3 Illustration 10 : Obtain the median, from the following frequency distribution using Formula and also graphically. Monthly | 1400-1600 | 1600-1800 | 1800-2000 | 2000-2200 | 2200-2400 | 2400-2600 Salary (% | | Poeqeeney Mee Iaeea| OP 30 = | 35) =| ao |. as. pag Solution : Here the classes are continuous, hence they can be used as they are : Class Frequency | Less than type cumulative | frequency 1400 - 1600 12 2 1600 - 1800 30 | 42 | 1800 - 2000 55 97 | 2000 - 2200 40 137 | 2200 - 2400 35 172 | 2400 - 2600 28 200 = N |th Median = observation 200 _ | ym 7 = 100) observation Median lies in the (2000 — 2200) class, since 100 li : frequencies 97 and 137, since 100 lies between less than cumulative Median = [| + (==) xh . 100 - 97 = 2000 + ( 40 ) x 200 = 2015 To obtain median graphically we use less than type cumulative frequency curve. Y 200: Less than cumulative frequency curve Less tham cumulative frequencies 3 8 0! 1400 1600 1800 2000 2200 2400 2600 Upper Class-boundaries Fig. 2.4 3. Merits and Demerits of Median 1. Itis easy to understand and easy to calculate. 2. It is not affected due to extreme observations. 3. Itcan be computed for a distribution with open end classes. 4 3. It can be determined graphically. . It is applicable to qualitative data also. In this case observations are arranged in r according to the quality and the middle most observation can be obtained. The quality this item is taken to be average quality or median quality. erits : 1. _Itis not based on all the observations, hence it is not proper representative. 2. It is not capable of further mathematical treatment. 3, It is not as rigidly defined as the arithmetic mean.2.9 Mode It is yet another measure of central tendency developed to overcome the drawbacks arithmetic mean. Apart from this, in some situations mode is the proper average. Definition : The observation with maximum frequency or the most repeated observatio, is called as mode. Itis clear from earlier discussion that the general nature of frequency curve is bell shape in majority of situations. Thus initially frequency is small, it increases and reaches the maximum and then it declines, The value on x-axis at which the maxima or the peak of the frequency curve appears is a mode. Frequency curve Mode Fig. 2.5 In case of election results, a political party with largest votes (i.e. maximum frequency) is considered as representative. Thus, it is mode or modal opinion. In this situation, mode is the appropriate average. Similarly, to estimate the crop yield, too good quality or too poor quality crop is not considered. A quality of crop most commonly found is taken into account, which is nothing but mode. In titration experiment, out of three readings a repeated reading is taken to be final reading. It is mode and not the arithmetic mean. Thus in number of situations mode is appropriate. (i) Computation of mode for Individual observations and Discrete frequency distribution : In this case we can find the observation with the largest frequency just by inspection. If the largest frequency occurs twice (or more), then we say there are two (or many) modes. Illustration 11 : Find the mode of the following frequency distribution : x to {uu |e | [uw] | f iglesia | 10 a| aie 2 | 1s | Solution : Since maximum frequency is associated with observation 13, the mode is 13. (ii) Computation of mode for Continuous frequency distribution : Step 1: Obtain the class-boundaries. Step 2: Locate the modal class. Modal class is class in which mode lies or a class with the largest frequency. Step 3: Apply the formula and find the mode.where, modal class Illustration 12 : Calculate modal income from the following income distribution : | Daily income (8 | 20.and betow 31-60 | 61-90| 91-120 | 121-150 | above 150 | No. of Persons 22 198 | 110 95 42 | 33 Solution : | Class boundaries Frequency | below 30.5 f= 22 | 30.5 -60.5 fm = 198 Modal class | 60.5 - 90.5 f,= 110 90.5 - 120.5 95 120.5 - 150.5 42 above 150.5 33 Modal class is 31-60. Since the corresponding frequency is the highest. Here we get ! = 30.5, fm= 198, f= 22, f,= 110, h=30 Mode 198 ~ 22 "2x 198- 22-110 30.5 + «30 = 50.5 - If the maximum frequency is repeated, to find the mode uniquely, a method| grouping is adopted and a modal class is determined. The method of grouping beyond the scope of book. . Mode cannot be determined if modal class is at the extreme. (i.e, the maxim| frequency occurs at the beginning or at the end of the frequency distribution.) . Modal, pre-modal and post-modal classes should be of the same width. 4. If f, =f, then mode is the class-mark of modal class.es ss Computation of mode - by Empirical relation Arithmetic mean, mode ang ig are averages, hence we expect that those should be identical in value. However, this ist only in ideal situation, It is true whenever the frequency curve is Perfectly Symmetric bell-shaped. For a moderately asymmetric unimodal frequency distribution the followin, empirical relationship holds approximately. : Mean ~ Mode = 3 (Mean - Median) (23 In some situations mode is ill-defined (see notes 1, 2 stated above). To overco; this difficulty in computing mode, the empirical relation (1) is used. If any two averages includes in (2.2) are known, the remaining third can be computed. Therefore, if mean and Median ae known, then mode can be determined. The empirical relation cannot be theoretically proved. Karl Pearson has stated it ON the basis of vast experience. This relationship is observed to be valid for number of data Sets after actual computations. (iv) Computation of mode - by graphical method : Mode can be obtained graphically with the help of histogram. Mode is the x-co-ordinate of point P or the value at foot of Perpendicular from P to x-axis, shown in Fig. 2.6. Historgam 336 z yale s is s Bg E be Zole Mode class boundries Fig. 2.6 : Histogram [> lerits and Demerits of mode : i its = C 1. Itis simple to understand and easy to compute. : 2. Itis applicable for qualitative and quantitative data, 3. It is not affected by extreme observations. 4. Itcan be computed for distribution with open end classes. 5. Itcan be determined graphically. Demerits : 1. Itis not based on all the observations. 2. Itis not capable of further mathematical treatment. 3. Itis not rigidly defined like arithmetic mean. 4, Itis indeterminate if the modal class is at the extreme of the distribution.cequency distribution, Sometimes bimodal frequency distribution is an indication of mixture frwo frequency distributions. For example, operator or machine is changed in manufacturing process. In medical ciences, two types of anaemia viz. microcytic and macrocytic are found in same population vhich give bimodal frequency curve. > 5 2 2 & Small red Normal red Largel red cell cell cell Fig. 2.7 Tlustration 13 : Calculate arithmetic mean and mode for the following data : Monthly salary(3 | __Number of workers | Below 400 0 | Below 600 4 | Below 800 14 Below 1000 33 Below 1200 45 Below 1400 49 Below 1600 50- Solution : We need to prepare frequency distribution from the given cumulative frequency distribution. Frequency 400-600 | 4-0=4 600-800 | 14-4 = 10 800 - 1000 | 33-14 = 19 1000 - 1200 | 45-33 = 12 1200-1400] 49-45 = 4 1400 - 1600y Mean =a + at xh, where, a= 900, Sfu = 5,N=50,h = 299 5 900 + 3 x 200 =% 920 Modal class : 800 ~ 1000 Mode = Here / = 800, fm = 19, f, = 19-10 -. Mode = 200+ (ess) x 200 = 912.5 Solved Examples | Example 2.1 : From the following data find the missing frequencies, it is given that mean is 15.3818 and total frequency is 55, Class 9-M | 41-13 | 13-15 | 15-17 [17-19 | 19-21 | Frequency 8 7a ee 20) ey 5. | Solution : Let the missing frequencies be a and b Class Mid-value Frequency f-x x £ 9-11 10 3 30 11-13 12 7 84 13-15 14 a l4a 15-17 16 20 320 17-19 18 b 18b 19-21 20 3 100 Total - 35+a+b=N=55 534+ 14a+18b = 5 fx We get two equations from the given information ie. 35+a+b = 55 (-,* Total frequency N = 55) a+b = 20 wo (l) X = oh gives 15.3818 = S4tl4a+18b 55 845,999 = 534+14a+18b 14a+18b = 311.999 we Q)solving (1) and (2) we get, a = 12,0002, b = 7,998, After rounding-off the values, a= 12 and b=8, Thus, frequency of the class 11-13 is 12 and that of 17-19 is 8. Example 2.2: Find the arithmetic mean given that 5. (x ~ 10) = 230 and n = 50. Solution: Letd =x-10, a = 10, hence Xd = 230 ed 0 Mean = a + = 10+%9 = 14.6 : : Example 2.3 : Arithmetic mean of 50 items is 104. While checking, it was noticed that pbservation 98 was misread as 89. Find the correct value of mean. Solution : Incorrect sum n Incorrect sum = 104x50 = 5200 Correct sum = Incorrect sum + Correct observation ~ Incorrect observation 5200 + 98-89 = 5209 Correct sum n Incorrect mean = 104 = Correct mean = 5209 “So = 104.18. Example 2.4 : The number of washing machines sold in a shop per day are distributed lows. Find median No. of machines sold wYT 1 4 sie No. of days 6.| 10 |74:).3°|°3 | 2 Solution : Let X = No. of machines sold, f = No. of days. x f y Less than type cumulative frequency | 0 6 6 1 10 16 2) 4 20 3: 3 23 4 3 26 5 1 27 =n i 27+1 th See Median = The value of (om = : = 14) observation in the ordered arrangement =1my Example 2.5 : A salesman has given a target to complete average daily sales of F 1009 In a particular week, average sales of first 6 days is € 980. What should be his sales on seventh day in order to make-up the target ? Solution : Here we use average as arithmetic mean % = 28. 58. 1000 Total sales for 7 days = Yx = nX = 7x 1000= % 7000 The average of first 6 days = i = 980. Total sales for 6 days = 6 x 980 = & 5880 Sales required on 7 day = 7000-5880 = % 1120 Example 2.6 : The median of a group of 100 observations is computed to be 70. While verifying, it was found that the observation 13 was misread as 31. Find the correct median, Solution : Note that the median is 70. The observation 31 is to be replaced by correct observation as 13. This change does not affect the middle most observation in the ordered arrangement, hence median will remain same. Thus the median after correction is 70. Note : However, arithmetic mean will change. Example 2.7 : Calculate mode of the following frequency distribution class | 50-100 | 100-150 | 150-200 | 200-250 | 250-300 | 300-350 350-400 | Frequency| —§ I 15 25 18 | 12 3 2 Solution : Modal class = (150-200) ‘ 25-18 -} xh= 150+ (sizes) x 50 7 150+(F) x50 = 170.5882 Example 2.8 : Following is a frequency distribution regarding the number of family members, number of earning members in a certain locality. Mode = Income No. of No. of family members per month families Earners Non-earners _| 0 - 2000 |= 22 25 40 2000 - 3000 59 rb] 143 3000 - 4000 70 91 179 4000 - 6000 25 57 136 6000 - 10000 15 A 42 85 10000 - 14000 9; 30 I7 Total 200 320 600Calculate = 1. Average monthly income per family Average monthly income per earning member |. Per capita income |. Average family size yRwD . The median family income. Solution : Income | Mid-point |No. of families (f)| fx | Less than cumulative oe | | frequency 0- 2000 1000 | 2 | 22000 | 2 2000 - 3000 2500 59 147500 | 81 3000 - 4000 3500 70 245000 Is 4900 - 6000 5000 25 | 125000 | 176 6000-10000 | 8000 15 | 120000 191 10000-14000 | _ 12000 9 | 108000 | 200 Total 200 | 767500 | 7 7: . Average monthly income per family 8 . “oe = 3837.5 : Pi Total income Average monthly income per earning member = No. of earning members 767500 = 390 = % 2398.44 a. Total income _ 7675000. _ Per capita income = Fora! population = 320+ 600 = * 834.24 (Total population = No. of earners + No. of non-earners.) ee Total number of earners and non-e: erase family size = Total number of families The median of family income. Median = The value ofae Example 2.9 : The monthly income (2) of 10 families in a village is as follows ; 1200, 1000, 1100, 1250, 950, 1300, 1350, 1150, 1200, 1050. Find Mean, Median and Mode of this Income Distribution. yx 11550 10 x. = 1155 n Solution : Mean = The ordered arrangement to find the median is as follows : 950, 1000, 1050, 1100, [1150. 1200] , 1200, 1250, 1300, 1350. ie th Median = The value of(* Fee ss) observation _ Sthobservation + 6M observation = 2 _ 1150+ 1200 = 2 ©1175 Observation with maximum frequency = 1200 Thus, Mean = % 1155, Median = % 1175, mode = % 1200 Example 2.10 : The following data relates to age distribution of 50 persons : Mode Age (years) Frequency 20-30 J 30-40 Zz 40-50 14 50-60 16 60-70 | 70-80 2 Find mode of above distribution Solution : Modal class : 50-60 fm fo Mode = 1+ f,-h-f, xh 1= 50, fm = 16, fo = 14, f, = 8 h= 10. 16-14 Mode = 50+(s27¢45) x10 = 52 yearsShriram Oxygen Ltd. is a company in a manufacturing of industrial oxygen based in a dustrial area of Washi, Navi Mumbai. There are in all about 1000 employees in this ompany. They are of various grades. For example, there is a managing director, about 10 directors, 30 senior general anagers, about 200 managers, 150 officers and rest are workers of different grades ‘Company's monthly salary budget is about & 30 lac. Management of this company is of the opinion to increase the productivity by not increasing the man power but through increasing the salary of existing employees. Existing salary of managing director is approximately % 1 lacs per month, directors get ‘around % 75,000/- per month, general manager gets around % 50,000. Whereas workers salary aries from ¥ 20,000 to & 50,000 as per their grades. Company has a revised budget of % 40 lac per month. Company would like to know bout what is the average salary per month. Whether to find mean would be appropriate or uld median be used. What would be average revised salary per month ? Points to Remember Arithmetic mean (X) = Ex for ungrouped data i 7 Es for frequency distribution. 5-Cf Median =/+|—F—) xh. _). (fanfi ) Mose = 1+ (592245 xh If y=ax+btheny=ax+b, y= 7 ; : myx+my Combined arithmetic mean =") yy, Median can be obtained graphical using ogive curves. Mode can be obtained graphically using histogram. Arithmetic mean is the best average. Arithmetic mean cannot be determined by graph.Exercise [A] Theory Questions : Vv What do you mean by central tendency ? Explain the purpose of measures of Central tendency. State the requisites of an ideal average. 3. Define mean, median, mode and state the formula for each, in case of (i) individuay observations (ii) frequency distributions. 4. Discuss merits and demerits of (i) mean, (ii) median, (iii) mode. 5.__Explain graphical method of determination of (i) median (ii) mode. [B] Discrete Series : 6. Monthly consumption of electricity in units of a certain family in a year is given below : 210, 207, 315, 250, 240, 232, 216, 208, 209, 215, 300, 290. Compute the mean, median and modal consumption of electricity. 7. The marks obtained by 12 students are given below : 30, 55, 50, 40, 50, 60, 55, 62, 55, 45, 61, 65 Calculate mean, median and mode for the above data. 8. Compute the mean, mode and median for the following data : (April 2011) 68, 49, 38, 41, 49, 54, 89, 99, 67 9. Find the mean, median and mode of the following observations : (Oct. 2014) 61, 62, 63, 62, 63, 62, 64, 64, 60, 65. : 10. In a set of 50 items, arranged in ascending order of magnitude the values of 24, 254 and 26" items are 40, 42 and 45 respectively. Find the median. Also find the median if the number of observations was 51. 11. Calculate mean and median weight of the group of students with weights (in kg) given below : 51, 52, 53, 51, 53, 54, 54, 50, 55, 53. If a new group of students with weights in kg as 50, 56, 58, 57, 60 is added to the original group, find mean and median of combined group. 12. Compute median of the following series 5, 20, 18, 12, 0, 21, 18, 26, 5, 15, 20. . The following figures represent the number of books issued at the counter of commerce college library on 8 different days. 96, 98, 75, 80, 102, 100, 94, 75, Calculate the median and mode of the data.