setwd("C:/Users/SwagD/Desktop/Data 101")
data <- read.csv("AllCountries.csv")
head(data)
## Country Code LandArea Population Density GDP Rural CO2 PumpPrice
## 1 Afghanistan AFG 652.86 37.172 56.9 521 74.5 0.29 0.70
## 2 Albania ALB 27.40 2.866 104.6 5254 39.7 1.98 1.36
## 3 Algeria DZA 2381.74 42.228 17.7 4279 27.4 3.74 0.28
## 4 American Samoa ASM 0.20 0.055 277.3 NA 12.8 NA NA
## 5 Andorra AND 0.47 0.077 163.8 42030 11.9 5.83 NA
## 6 Angola AGO 1246.70 30.810 24.7 3432 34.5 1.29 0.97
## Military Health ArmedForces Internet Cell HIV Hunger Diabetes BirthRate
## 1 3.72 2.01 323 11.4 67.4 NA 30.3 9.6 32.5
## 2 4.08 9.51 9 71.8 123.7 0.1 5.5 10.1 11.7
## 3 13.81 10.73 317 47.7 111.0 0.1 4.7 6.7 22.3
## 4 NA NA NA NA NA NA NA NA NA
## 5 NA 14.02 NA 98.9 104.4 NA NA 8.0 NA
## 6 9.40 5.43 117 14.3 44.7 1.9 23.9 3.9 41.3
## DeathRate ElderlyPop LifeExpectancy FemaleLabor Unemployment Energy
## 1 6.6 2.6 64.0 50.3 1.5 NA
## 2 7.5 13.6 78.5 55.9 13.9 808
## 3 4.8 6.4 76.3 16.4 12.1 1328
## 4 NA NA NA NA NA NA
## 5 NA NA NA NA NA NA
## 6 8.4 2.5 61.8 76.4 7.3 545
## Electricity Developed
## 1 NA NA
## 2 2309 1
## 3 1363 1
## 4 NA NA
## 5 NA NA
## 6 312 1
model1 <- lm(LifeExpectancy ~ GDP, data = data)
summary(model1)
##
## Call:
## lm(formula = LifeExpectancy ~ GDP, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -16.352 -3.882 1.550 4.458 9.330
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.842e+01 5.415e-01 126.36 <2e-16 ***
## GDP 2.476e-04 2.141e-05 11.56 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 5.901 on 177 degrees of freedom
## (38 observations deleted due to missingness)
## Multiple R-squared: 0.4304, Adjusted R-squared: 0.4272
## F-statistic: 133.7 on 1 and 177 DF, p-value: < 2.2e-16
The intercept is the predicted life expectancy when GDP = 0
The slope is the change in life expectancy for a 1-unit increase in GDP
R² is how much variation in life expectancy is explained by GDP
model2 <- lm(LifeExpectancy ~ GDP + Health + Internet, data = data)
summary(model2)
##
## Call:
## lm(formula = LifeExpectancy ~ GDP + Health + Internet, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -14.5662 -1.8227 0.4108 2.5422 9.4161
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.908e+01 8.149e-01 72.499 < 2e-16 ***
## GDP 2.367e-05 2.287e-05 1.035 0.302025
## Health 2.479e-01 6.619e-02 3.745 0.000247 ***
## Internet 1.903e-01 1.656e-02 11.490 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.104 on 169 degrees of freedom
## (44 observations deleted due to missingness)
## Multiple R-squared: 0.7213, Adjusted R-squared: 0.7164
## F-statistic: 145.8 on 3 and 169 DF, p-value: < 2.2e-16
Health coefficient is the change in life expectancy for a 1-unit increase in Health spending, holding GDP and internet constant
Adjusted R² lets us know if adding variables improves the model
plot(model1$fitted.values, model1$residuals)
abline(h = 0)
The ideal is a random scatter
The violation is Pattern or funnel shape
qqnorm(model1$residuals)
qqline(model1$residuals)
The points follow the line
The violation is curved or scattered away from line
residuals <- model2$residuals
rmse <- sqrt(mean(residuals^2)
)
rmse
## [1] 4.056417
RMSE measures the average prediction error in life expectancy
Lower RMSE means a better model fit
Large residuals means worse predictions for certain countries This means there could be, outliers, missing variables or unique country conditions
Multicollinearity happens when two predictors are highly correlated, such as Energy and Electricity.
This means it can make coefficients unstable, make it difficult to interpret individual effects, and reduce the reliability of the model.
Even if the model predicts well overall, individual variables may appear insignificant due to overlap.