1 Arithmetic mean: (i) For ungrouped data (individual series) x =

(ii) For grouped data (continuous series)

(a) Direct method x = where xi , I = 1 .. n be n observations and fi be their corresponding frequencies (b) short cut method : x = A + fidi / fi) where A = assumed mean, di = xi - A = deviation for each term 2 Properties of A.M. (i) In a statistical data the sum of the deviation of items form A.M. is alwalys zero. (ii) If each of the n given observation be doubled, then their mean is doubled (iii) If x is the mean of x1, x2, , xn . the mean of ax1, x2, .. , axn is a x where a is any number different form zero (iv) Arithmetic mean is independent of origin i.e. it is x effected by any change in origin. 3 Geometric mean: (i) For ungrouped data G.M. = (x1 x2 x3 .. xn)1/n or

G.M. = antilog (ii) For grouped data G.M. = (xf11 xf22 .. xfnn)1/N , where N = i=1 n fi

4 Harmonic mean Harmonic mean is reciprocal of arithmetic mean of reciprocals.

(i) For ungrouped data H.M. =

(ii) For grouped data H.M. = 5 Relation between A.M., G.M and H.M. A.M. G.M. H.M. Equation holds only when all the observations in the series are same 6 Msdian: (a) Individual series (ungrouped data) : If data is raw, arrange in ascending or descending order and n be the no. of observations . If n is odd, Median = value of ((n+1) / 2))th observation If n is even, median = (1/2) [value of (n/2)th + value of ((n/2) + 1)th] observation.

(b) Discrete series: First find cumulative frequencies of the variables arranged in ascending or descending order and Mediain = {(n+1) / 2}th observation, where n is cumulative frequency. (c) Continuous distribution (grouped data) (i) For series in ascending order

Median = e + Where e = Lower limit of the median class. f = Frequency of the median class. N = Sum of the all frequencies. i = The width of the median class. C = Cumulative frequency of the class preceding to median class.

(ii) For series in descending order Median = u Where u = upper limit of median class. 7 Mode: (i) For individual series: In the case of individual series, the value which is repeated maximum number of times is the mode of the series. (ii) For discrete frequency distribution series: In the case of discrete frequency distribution, mode is the value of the variate corresponding to the maximum frequency. (iii) For continuous frequency distribution : first find the model class i.e. the class which has maximum frequency for continuous series

Where e1 = Lower limit of the model class. f1 = Frequency of the model class. f0 = Frequency of the class preceding mode class. f2 = Frequency of the class succeeding model class. i= Size of the model class. 8 Relation between mean, mode & median: (i) In symmetrical distribution : mean = mode = median (ii) In Moderately symmetrical distribution : mode = 3 median 2 mean Measure of Dispersion: The degree to which numerical data tend to spread about an average value is called variation or dispersion popular methods of measure of dispersion. (a) Individual series (ungrouped data) 1 Mean deviationMean deviation = (|x-S| / n) Where n = number of terms, S = deviation of variety form mean mode , median

(b) Continuous series (grouped data)

Note: Mean deviation is the least when measured from the median. 2 Standerd Deviation : S.D. () is the squere root of the arithmetic mean of the squares of the deviations of the terms from their A.M. (a) for individual series (ungrouped data) where x = Arithmetic mean of the series N = Total frequency (b) For continuous series (grouped data) (i) Direct method = Where x = Arithmetic mean of series X1 = mid value of the class f1 = Frequency of the corresponding x1 N = f = Total frequency (ii) Short cut method

Where d = x - A = Derivation from assumed mean A f = Frequency of item (term) N = f = Total frequency. Variance Square of standard direction i.e. variance = (S.D.)2 = ()2 Coefficient of variance = Coefficient of S.D. x 100 = ( / x) x 100