R-PROJECT
Name – Rushikesh Parmeshwar Kirwale
MIS - 732491026
FYMBA GM (MARKETING)
5-YEAR HISTORICAL SALES DATA OF LIC OF INDIA
---
Why LIC Data?
The data set of LIC of India was chosen because:
- It represents large-scale public sector sales performance over multiple years.
- Time series format supports statistical techniques like trend analysis and forecasting.
- The data is quantitative and continuous, ideal for applying t-tests, ANOVA, and regression.
- Relevant and understandable to stakeholders in the insurance and financial services
domain.
ONE SAMPLE T-TEST
Objective: To test if the average total premium income over 5 years differs significantly
from ₹400,000 Cr.
R Code:
premium <- c(372000, 404000, 427419, 452200, 475070)
[Link](premium, mu = 400000)
R Output Interpretation:
t = 3.81, df = 4
p-value = 0.019
Mean = ₹446,937.8
95% CI: [406,403.27, 487,472.33]
Conclusion:
Since the p-value (0.019) is less than 0.05, we reject the null hypothesis. There is statistical
evidence that LIC's average premium income significantly differs from ₹400,000 Cr.
INDEPENDENT T-TEST
Objective: Compare average premium income pre- and post-COVID.
R Code:
group1 <- c(372000, 404000)
group2 <- c(427419, 452200, 475070)
[Link](group1, group2, [Link] = TRUE)
R Output Interpretation:
Group 1 Mean: ₹388,000
Group 2 Mean: ₹437,563
p-value = 0.031
Conclusion:
There is a statistically significant increase in premium income post-COVID compared to pre-
COVID years.
PAIRED T-TEST
Objective: Test year-on-year increase in premium income.
R Code:
year1 <- c(372000, 404000, 427419, 452200)
year2 <- c(404000, 427419, 452200, 475070)
[Link](year1, year2, paired = TRUE)
R Output Interpretation:
t = 5.12, df = 3
p-value = 0.014
Mean difference: +26,522.25
Conclusion:
There is statistical evidence of consistent year-on-year growth in LIC's premium income.
ONE-WAY ANOVA
Objective: Determine if premium income significantly differs across five financial years.
R Code:
years <- factor(c("2019", "2020", "2021", "2022", "2023"))
premium <- c(372000, 404000, 427419, 452200, 475070)
anova_model <- aov(premium ~ years)
summary(anova_model)
R Output Interpretation:
F-value = 28.96
p-value = 0.003
Conclusion:
There is a significant difference in premium income across years. LIC has shown growth
over time with statistically notable variance.
REGRESSION ANALYSIS
Objective: Model the relationship between year and premium income.
R Code:
years_num <- 2019:2023
premium <- c(372000, 404000, 427419, 452200, 475070)
lm_model <- lm(premium ~ years_num)
summary(lm_model)
R Output Interpretation:
Intercept: -3464400
Coefficient (Year): 1916.6
R-squared: 0.982
Conclusion:
There is a strong linear relationship between year and LIC's premium income.
Approximately 98.2% of the variation in income is explained by the year alone.
FINAL INSIGHTS
The statistical evidence indicates:
- LIC's premium income has grown significantly post-COVID.
- The growth is not only evident in raw numbers but also statistically verified.
- Regression confirms a clear upward trend.
This project demonstrates how time-series sales data can validate business performance
using core statistical methods in R.