Title: Relationship between Nifty 50 and Star Health.
Author: Shubheecha Nakhawa
Introduction:
Star Health Ltd is India’s first standalone health insurance provider, established in 2006. It dominates the retail health market with a wide network of hospitals and diverse insurance products. The company focuses on digital innovation and specialized health plans to maintain its market leadership. In this report, we analyze its stock performance in relation to the Nifty 50 index.
Objective: Calculation of Beta and observe its significance.
Literature Review:
Ghosh (2019) studied beta regression in healthcare data and found that it is suitable for modeling proportions like claim ratios and health rates (0–1 values). The study also introduced a robust beta regression model to handle outliers, which are common in insurance claims.
Gan and Valdez (2021) used beta regression to analyze prescription drug utilization rates in health insurance. The study showed that beta regression effectively models claim proportions and healthcare usage, improving risk prediction in insurance models.
Data Collection:
Data for Nifty 50 and Star Health was downloaded from NSE India.com. For the Period 1-Jan-25 to 31-Dec-25, Friday closing prices for Nifty 50 and Star Health were segregated, weekly returns of Nifty 50 and Star Health were calculated weekly return of Nifty 50 were (X) and weekly return of Star Health were taken as (y). ‘y’ was regressed on ‘X’.
Data Analysis:
Y = 0.28 + (-2.92) X
N= 48, R²= 0.21, F= 12.45, t start= -3.53, P- value= 0.00
The above equation shows the relationship between Nifty 50 and Star Health there is an inverse relationship which means Nifty 50 rises so will the Star Health and vice versa. If Nifty 50 rises by 1 unit the Star Health will fall by -2.92. Number of observation are 48, t-stat for B is -3.53 the P-value for which is 0.00 which is less than 0.05, B is statistically significant at 5% level, r² = 0.21 meaning 21% of change in stock of Star Health is explained by Nifty 50 and 79% is error due to the variables not included in the model now F is 12.45 and P-value is 0.00 which is less than 0.05 it means overall model is statistically significant at 5% level.
Conclusion:
The beta here is -2.92 as it is less than 1 (negative), ignore this company.
Reference:
1.Ghosh, A. (2019). Robust inference under the beta regression model with application to health care studies. Statistical Methods in Medical Research, 28(3), 871–8.
2. Gan, G., & Valdez, E. A. (2021). Analysis of prescription drug utilization with beta regression models. North American Actuarial Journal, 26(2), 205–226.