Relationship of weekly return between RELAXO with NIFTY50 (Regression Analysis)

Raspreet Kaur Bindra

Roll no


Relaxo Footwears Limited is engaged in the manufacturing and trading of footwear and related products. The principal activity of the Company is the manufacture of footwear made primarily of vulcanized or molded rubber and plastic. Its brands include Hawaii, Flite, Sparx, Schoolmate, Elena, Casualz and Bahamas. The company boasts of having 8 start-of-art manufacturing units spread in northern part of India with a production capacity of 6 lac pairs of footwear per day, catering to varied needs of consumers worldwide.

Since its inception, the company has gone on to become one of the largest producers of footwear in India with an estimated business value of 17 billion last year. A brand synonymous with quality products and affordable prices, Relaxo is adorning millions feet in more than 25 countries around the world. Relaxo brings a fine combination of comfort, style, and workmanship under its popular brands i.e. Flite, Bahamas, Sparx, Schoolmate, and Hawaii. The footwear products offered by the brand signify extreme stylishness and come in varied alluring colours and exquisite designs.

To calculate beta of RELAXO and find its significance using regression analysis with NIFTY50.

Data collection
The closing price data of Nifty50 and RELAXO was taken from www.nseindia.com for the time period 1st March 2019 to 28th Feb 2020. From the available data, the closing rates of all the Fridays in the year was sorted to find out weekly returns for both Nifty as well as PEL. Then the weekly returns was calculated for both by using formula – Weekly Return= (C3-C2)/(C2*100) where, C3 is present week closing price and C2 is the previous week closing price. Once the data is calculated, weekly return column for NIFTY50 is considered as “X” variable and the weekly returns column for RELAXO is considered as “Y” variable.

The Model and formulas used are:
Y = a +bX
X ̅ =∑X/N
Y ̅=∑Y/N
x = X – X ̅
y = Y – Y ̅
a= Y ̅- bX ̅
e = Y – Y ̅
Variance of error=(σe)^2 =∑e^2/N-K
S.E of b = √ ((σe)^2 /∑x^2)
t stat of b = b/ S.E of b
ESS = (b^2)*(∑x^2)
RSS = ∑e^2
F = Mean ESS/Mean RSS

Data analysis
Using the Regression Add-on in Microsoft Excel Data Analytics tool we get following values:
R Square= 0.032
a= 0.269
b = 0.723
N (Observations) = 50
F = 1.608
Therefore, formulating below question:
Y = 0.269- 0.723X

The above equation tells us the relationship between “Y” and “X”, that is Demand and Price. If price raises by unit, demand raises by 0.723 units. Positive sign says that, there is reverse relationship. Means if price rises demand rises, similarly if price falls then demand also falls. Figure In bracket is t-stat for “b”. b value for which is more than 0.05 so “b” is statistically significant at 5%. R2 = 0.032, which means 32% Y is explained by X. 68% error or other variables aren’t in the models. F is 1.608. The P value for which is more than 0.05, overall model is statistically significant at 5%.

Price is significant and overall model is significant but error will be 68%.