R Square

3.4.
2 Inferential statistics technique
Inferential statistics is a branch of statistics which helps in analysing the data based
on the results to make valid conclusions. They are helpful in making inferences and
judgements about the nature of sample data being used. The conclusions here are
based on the concept of hypothesis testing. A hypothesis is nothing but a kind of
proposition based on past evidences and experiences which are formed for the
purpose of further investigation. There are two hypotheses: Null Hypothesis (H0) and
Alternate Hypothesis (H1). Null hypothesis states that the results are due to pure
chance or random errors whereas alternate hypothesis frames that the results a re
due the fluctuations or variations in independent (explanatory variables). In the study,
null hypothesis states that there is no significant relationship between Nifty50 and
selected macroeconomic variables while alternate hypothesis states that there i s a
significant relationship between Nifty50 and selected economic variables. Here we
have used correlation analysis and multivariate regression analysis using measures
such as R-square, t-ratio, F-test, p-value. Significance level or alpha level used is
5%. Here the analysis is being done using SPSS software.
Correlation matrix analysis
Correlation shows that a change in one variable is accompanied by a change in other

variable. It only shows the strength and direction of relationship and not the causality .
Coefficient of correlation has value ranges from -1 to +1. The value +1 shows perfect
positive relationship between the variables and -1 shows a perfect negative
relationship. The absolute value shows the magnitude of change and sign shows the
direction. A + sign means an increase in one variable leads to increase in other
variable whereas a – sign shows that an increase in one variable leads to decrease in
another variable. A correlation coefficient of zero shows that there is no linear
relationship between two variables however a non-linear relationship can exist in
such situations. Here partial correlation coefficient is used for study. This means
studying the relationship between two variables keeping all the other variables as
constant. The correlation is Karl Pearson correlation coefficient also known as
product moment correlation. The formula for correlation coefficient is:
19
where Cov (x,y) is the covariance between the two variables and denominator shows
the product of standard deviations of respective variables. Here it is used to measure
the association between Nifty50 and macroeconomic variables.
Econometric Regression Model
“Francis Galton proposed the term regression. Regression analysis is concerned with
the study of the dependence of one variable, the dependent variable, on one or more
other variables, the explanatory variables, with a view to estimating and/or predicting the
(population) mean or average value of the former in terms of the known or fixed (in
repeated sampling) values of the latter. When only one explanatory variable is considered
then the analysis is called as bivariate regression analysis or simple regression. The
regression equation is as follows:
Yi = β0 + β1 X1 + β2 X2+…..+ βn Xn + ui”
where Yi is dependent variable and variable X represents explanatory variables, β0 is

the interept or onstant term and β1 ( or β2 or βn) represents slope oeffiient of the
regression line with of respective explanatory variable. The slope coefficient
represents the direction and strength of relation between independent and dependent
variables. ui is a random error term that is the error which is not explained by the
explanatory variables. In our study the dependent variable is the stock market index
and macroeconomic variables are the independent or explanatory variables.
Statistic test
R-square: It is also known as the coefficient of determination which tells how the
regression line best fits the data. It measures the %age change in dependent variable
that is explained by the explanatory variables.
Sign-F: It tells whether the model as a whole is significant. It shows the combined
impact of all the explanatory variables on the dependent variable.
T-ratios: It measures the reliability or the impact of individual variable on the

dependent variable. The decision to accept or reject the null hypothesis is based on
the corresponding p-value. When p value is less than the alpha value we reject null
hypothesis. In case of rejection of null hypothesis we say that the findings are
statistically significant.
20

R Square

Uploaded by

Copyright:

Available Formats

R Square

Uploaded by

Document Information

Original Description:

Original Title

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

R Square

Uploaded by

Copyright:

Available Formats

3.4.

2 Inferential statistics technique

Correlation matrix analysis

Correlation shows that a change in one variable is accompanied by a change in other

Econometric Regression Model

where Yi is dependent variable and variable X represents explanatory variables, β0 is

T-ratios: It measures the reliability or the impact of individual variable on the

You might also like