BRM-Statistics in Research

GOOD MORNING
ALL OF YOU
STATISTICS
IN
RESEARCH
CONCEPT
The role of statistics in research is to
Function as a tool in designing research, analyzing
its data & drawing conclusions therefrom.


Classification & tabulation achieve this objective


to some extent but a researcher have to go step
further & develop certain indices or measures to
summarize & analyze collected & classified data…
 After this we adopt the process of generalization

from small groups to population.


Two major areas of
statistics..
Descriptive statistics is concerned with


development of certain indices from raw data


Inferential statistics is mainly concerned


with two major problems:-

 Estimation of population parameters..
 Testing of statistical hypothesis..
Statistical measures
Measures of central
tendency
 Also known as Statistical average, it tells us
the point about which items have tendency
to cluster. It is considered as the most
representative figure for entire mass of data.


Mean

 Mean is also known as Arithmetic average which may

be defined as the value which we get by dividing the
total of the values of various given items in a series by
the total no. of items .


CALCULATION OF MEAN

 INDIVIDUAL DISTRIBUTION

 MEAN or X= ΣXi/n = X1+X2+X3+…….+Xn/n


 FREQUENCY DISTRIBUTION

 X =ΣfiXi/Σfi = f1X1+ f2 X2+………………..fnXn

 f1+f2+f3….+fn
 WEIGHTED MEAN
 X = ΣWiXi / Σwi

 ADVANTAGES OF MEAN
 It is simple to understand & easy to calculate.
 It is based on all observations
 It is capable of further algebraic treatment.
 It is rigidly defined.

 DISADVANTAGES
 It is highly affected by extreme values
 It can’t be calculated in open-ended series.
 It can’t be ascertained graphically.
 It can’t be determined in situation when one value is
 missing.


 MEDIAN

It is defined as the middle value of the series


when arranged in ascending or descending

orders. It is the value which divides the series
into two equal parts. It is thus a positional
average & is used mostly in context of
qualitative phenomena.

 CALCULATION OF MEDIAN

 M = size of n + 1 th item
 2

 ADVANTAGES OF MEDIAN
 It is easy to understand.
 It is easy to locate or compute.
 It is not affected by extreme values.
 It is most appropriate average in case of open-ended
classes.
 It is the most suitable average in dealing with
qualitative facts such as beauty, honesty etc.

 DISADVANTAGES
 It requires arranging of data in ascending or descending
order.
 It is not based on all observations.
 It is not capable of further algebraic treatment.
 It is difficult to calculate if the no of items is very small
or
 large.
MODE

 It is the most commonly or frequently occurring

value in the series. Or it is the size of the item
which has the maximum frequency.

CALCULATION OF MODE
1. Inspection method
2. Grouping method
 Calculation in continuous series

 Z = L1 + f1-f0 *i
 2f1-f0-f2
ADVANTAGES OF MODE

 Itis easy to understand & simple to calculate.

 Itis not affected by extreme values.
 Itcan be located graphically.
 Itcan be easily calculated in case of open ended
classes.
 All frequencies are not needed for its calculation.

DISADVANTAGES

 It is not suited to algebraic treatment.

 There can be bimodal frequency series.
 It is not based on all items of series.
 It is not rigidly defined.
Geometric mean

 It is defined as the nth root of the product of the

values of n items in a given series .

 Symbolically, we can put it thus:


 Geometric mean= ⁿ√X1 * X2 * X3….* Xn


HARMONIC MEAN
 It is defined as the reciprocal of the average of the
reciprocal of the values of items of a series.

 Symbolically, we can express it as under:


 H.M= Rec. Σ rec Xi

 n
 =Rec. rec X1 + rec X2 + rec X3…
+Xn
 n

MEASURES OF DISPERSION
 Dispersion is the measure of the variations of the
items. It defined as scatterness or spreadness of
the individual items in a given series.


RANGE

 RANGE is the biggest possible measure of

dispersion & is defined as the difference between
the values of the extreme items of a series.

 RANGE= highest value of an - lowest value of

 Item in a series) the item in
series

 MEAN DEVIATION
 It is the average of difference of the value of items
from some average of the series.

 CALCULATION OF MEAN
DEVIATION

MEAN DEVIATION FROM MEAN (δx ) = Σ Xi – X

 n

MEAN DEVIATION FROM MEDIAN (δm) = Σ Xi – M

 n

 COEFFICIENT OF MEAN DEVIATION

When mean deviation is divided by the average used in

finding out the mean deviation itself.


 for eg. – Mean deviation

 Mean or median

STANDARD DEVIATION

 It is defined as the square root of the average of

squares of deviations, when such deviations for
the values of individual items in a series are
obtained from the arithmetic average. It is
denoted by symbol σ .

 CALCULATION
 Standard deviation (σ) = Σ(X – X)²
 n


 COEFFICIENT OF STANDARD DEVIATION

When we divide standard deviation by arithmetic average.

Thus the relative measure of standard deviation is called
coefficient of S.D.

 COEFFICIENT OF S.D = σ
 X

 VARIANCE
Variance is the square of the standard deviation.

 Variance= (S.D.)² = σ²


 COEFFICIENT OF VARIATION
 = S.D. * 100
 X

 ADVANTAGES OF STANDARD DEVIATION

 It is rigidly defined.
 It is based on all observations.
 It is capable of being treated mathematically.
 It is not very much affected by the fluctuations of
sampling.

 DISADVANTAGES
 It is difficult to understand & difficult to calculate.
 It gives more importance to extreme observations.
MEASURES OF SKEWNESS

Skewness is degree of asymmetry or departure from


symmetry of a distribution....It means lack of symmetry

in a frequency distribution..the significance of skewness
lies in the fact that we can study the formation of series
& can have an idea about shape of curve, whether
normal or otherwise, when items of series are plotted on
graph.

The frequency distribution is skewed when

 X=M=Z

It is either positively skewed when X > M > Z or it is

 negatively skewed when X < M < Z...

Measure of skewness

 KARL PEARSON’S METHOD


 Skewness = X – Z
When mode is ill-defined , we calculate skewness
as:

 skewness = 3( X – M )

 COEFFICIENT OF SKEWNESS

 =X–Z OR 3( X – M )
 σ σ
MEASURES OF
RELATIONSHIP
 Under this we study :-
qBivariate population-
A.Correlation –it is studied through
2.Spearman’s rank correlation.
3.Karl Pearson's coefficient of correlation.
D.Regression analysis
qMultivariate population-
A.Correlation – it can be studied through
b)Coefficient of multiple correlation.
c)Coefficient of partial correlation
D.Multiple regression

 KARL PEARSON’S COEFFICIENT OF

CORRELATION

 r= Σxy
 √ Σx² * Σy²

x=X–X,
 y=Y-Y

 SIMPLE REGRESSION ANALYSIS


 Y = a + bX
 ΣY = Na + bΣX
 ΣXY = aΣX + bΣX²


qMultiple correlation

 R₁.₂₃ = √r²₁₂ + r²₁₃ - 2r₁₂.r₁₃.r₂₃

 1- r²₂₃
qPartial correlation

 r₁₂.₃ = r₁₂ - r₁₃. r₂₃

 √1-r²₁₃ √1- r²₂₃

qMultiple regression

 Y = a + b₁X₁ + b₂X₂
 ΣY = na + b₁ΣX₁ + b₂ΣX₂
 ΣX₁Y=aΣX₁ + b₁ΣX₁² + b₂ΣX₁X₂
 ΣX₂Y=aΣX₂ + b₁ΣX₁X₂ + b₂ΣX₂²
OTHER MEASURES

 INDEX NUMBERS

An index number is a statistical measure designed to show


changes in a variable or group of related variables with

respect to time, geographic location or other characteristics.

 They are helpful in making predictions.

 Index numbers also measures changes taking place in
economic & social phenomena, in business & provide for
comparison of these changes.

 Thus index numbers can be defined as a specialized type of
averages which measures the relative changes in diff variables at
diff point of time.
 Index numbers measure only relative changes.
 It measures cost of living of diff class of people.

 TIME SERIES ANALYSIS


In context of economic & business researches, we may

obtain often data relating to some time period
concerning some phenomenon..Such data is labeled as
TIME SERIES.
Such series are usually the effects of one or more of the
following factors:
1.Secular trend or long term trend
2.Short time oscillations.
c)Cyclical fluctuations(C)
d)Seasonal fluctuations(S)
e)Irregular fluctuations( I )
f)
 For analyzing time series we usually have two
models:-
A). Multiplicative model
 Y=T*C*S*I

 B). ADDITIVE MODEL

 Y=T+S+C+I

 Methods of time series analysis


 IMPORTANCE OF TIME SERIES ANALYSIS

 For Understanding the dynamic conditions.

 Evaluating success or failure of business policies
by study of past trends
 Formulating future policies on basis of past
trends

Thus , analysis of time series is important in


context of long term & short term forecasting & is

therefore considered a powerful tool in hand of
researchers.
THANK
YOU

BRM-Statistics in Research

Uploaded by

Copyright:

Available Formats

BRM-Statistics in Research

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

BRM-Statistics in Research

Uploaded by

Copyright:

Available Formats

GOOD MORNING

its data & drawing conclusions therefrom.

Classification & tabulation achieve this objective

 After this we adopt the process of generalization

Descriptive statistics is concerned with

development of certain indices from raw data

Inferential statistics is mainly concerned

with two major problems:-

 Mean is also known as Arithmetic average which may

 MEAN or X= ΣXi/n = X1+X2+X3+…….+Xn/n

 X =ΣfiXi/Σfi = f1X1+ f2 X2+………………..fnXn

It is defined as the middle value of the series

when arranged in ascending or descending

 It is the most commonly or frequently occurring

2. Grouping method

 Calculation in continuous series

 Itis easy to understand & simple to calculate.

 It is not suited to algebraic treatment.

 It is defined as the nth root of the product of the

 Symbolically, we can put it thus:

 Geometric mean= ⁿ√X1 * X2 * X3….* Xn

 Symbolically, we can express it as under:

 H.M= Rec. Σ rec Xi

 RANGE is the biggest possible measure of

 RANGE= highest value of an - lowest value of

MEAN DEVIATION FROM MEAN (δx ) = Σ Xi – X

MEAN DEVIATION FROM MEDIAN (δm) = Σ Xi – M

 COEFFICIENT OF MEAN DEVIATION

finding out the mean deviation itself.

 for eg. – Mean deviation

 It is defined as the square root of the average of

When we divide standard deviation by arithmetic average.

 ADVANTAGES OF STANDARD DEVIATION

Skewness is degree of asymmetry or departure from

symmetry of a distribution....It means lack of symmetry

The frequency distribution is skewed when

It is either positively skewed when X > M > Z or it is

 KARL PEARSON’S METHOD

 KARL PEARSON’S COEFFICIENT OF

 SIMPLE REGRESSION ANALYSIS

 R₁.₂₃ = √r²₁₂ + r²₁₃ - 2r₁₂.r₁₃.r₂₃

 r₁₂.₃ = r₁₂ - r₁₃. r₂₃

An index number is a statistical measure designed to show

changes in a variable or group of related variables with

 TIME SERIES ANALYSIS

In context of economic & business researches, we may

 B). ADDITIVE MODEL

 Methods of time series analysis

 For Understanding the dynamic conditions.

Thus , analysis of time series is important in

context of long term & short term forecasting & is

You might also like