Methodology & Research Design

To achieve our objective of identifying factors which influence the capital structuring decision in firms we use regression method wherein we try to identify factors which significantly impact the debt-equity structure of a firm.
Regression refers to the estimation of the best possible value of one variable for a given particular another variable. hence the regression of variable y is also called the dependent variable on another variable x, which is the independent variable.

The regression equation is defined as follows :

y = a+b*x.

Here we find the best possible value of y for a given value of x by using the method of least squares. By the principal of least squares we minimize the with respect to a and b the sum of the square of the errors.

i.e. U = Y - y = (Y-a-b*x)

To see whether a factor x significantly impacts y we observe the p-value as well as R-square. For 5% significance level if the p-value is less than 0.05 we reject null hypothesis, that factor x does not significantly impact the dependent variable y. Also to see whether the model is effective or not we gauge the R-square value. A high R-square value signifies the percentage of variable y can be explained by x. An R-square value of close to 60% generally makes a good fit.

Independent variable	Definition	Relationship with leverage
Tangibility of asset	net FA/Total Asset	positive
Profitability	PBT/total asset	negative
Size of the firm	Natural log of sales	positive
RnD expense ratio	RnD expense/Sales	positive
Marketing expense ratio	Mktg expense/sales	negative

Dependent Variable : Leverage to be measured by the Debt to Asset Ratio

The results obtained from the regression analysis are compared with the theoretical results and suggestions have been made based on the inferences made.