Work with dateset

I use data from Moodle E-learning course, the dataset name is Life Expectancy Data Set, and I narrowed down the data to the year 2015 and the following variables:

Adult Mortality

Hepatitis B

HIV/AIDS

Diphtheria

I use this code:

adot.tmp <- read.csv(“Life_Expectancy_Data.csv”, sep = “,”, header = TRUE, dec = “.”, check.names = TRUE)

attach(adot.tmp)

adot <- adot.tmp[Year == 2015, c(“Country”, “Adult.Mortality”,“Hepatitis.B”, “HIVAIDS”, “Diphtheria”, “GDP”)]

detach(adot.tmp)

attach(adot)

Statistical summaries

I made some statistical summaries:

summary(adot)
   Country          Adult.Mortality  Hepatitis.B       HIVAIDS      
 Length:183         Min.   :  1.0   Min.   : 6.00   Min.   :0.1000  
 Class :character   1st Qu.: 74.0   1st Qu.:78.75   1st Qu.:0.1000  
 Mode  :character   Median :138.0   Median :93.00   Median :0.1000  
                    Mean   :152.9   Mean   :82.43   Mean   :0.6607  
                    3rd Qu.:213.0   3rd Qu.:97.00   3rd Qu.:0.4000  
                    Max.   :484.0   Max.   :99.00   Max.   :9.3000  
                                    NA's   :9                       
   Diphtheria         GDP          
 Min.   : 6.00   Min.   :   33.68  
 1st Qu.:83.50   1st Qu.:  766.01  
 Median :93.00   Median : 2916.23  
 Mean   :84.63   Mean   : 7185.33  
 3rd Qu.:97.00   3rd Qu.: 7290.11  
 Max.   :99.00   Max.   :66346.52  
                 NA's   :29

Regression Model

The regression model examines the relationship between Adult Mortality (dependent variable) and the Hepatitis B, HIV/AIDS, and Diphtheria (independent variables). It is expressed as:

Adult.Mortality=β0+β1Hepatitis.B+β2HIV/AIDS+β3Diphtheria+ϵ

regr <- lm(Adult.Mortality ~ +1 + Hepatitis.B + HIVAIDS + Diphtheria)
summary(regr)

Call:
lm(formula = Adult.Mortality ~ +1 + Hepatitis.B + HIVAIDS + Diphtheria)

Residuals:
     Min       1Q   Median       3Q      Max 
-288.617  -49.594    6.956   46.333  262.486 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept) 146.5063    26.4191   5.545 1.10e-07 ***
Hepatitis.B   1.0883     0.6049   1.799   0.0738 .  
HIVAIDS      42.2123     4.7345   8.916 7.37e-16 ***
Diphtheria   -1.2871     0.6596  -1.951   0.0527 .  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 76.9 on 170 degrees of freedom
  (9 observations deleted due to missingness)
Multiple R-squared:  0.3955,    Adjusted R-squared:  0.3848 
F-statistic: 37.07 on 3 and 170 DF,  p-value: < 2.2e-16
plot(regr)

Conclusion

Multiple R-squared is 0.3955, this indicates that approximately 39.55% of the variance in Adult Mortality can be explained by the predictors (Hepatitis B, HIV/AIDS, and Diphtheria). Adjusted R-squared is 0.3848, this adjusts the R-squared value for the number of predictors in the model. It is slightly lower than the Multiple R-squared, suggesting that the inclusion of predictors may not significantly improve the model’s explanatory power. The model is significant with a very low p-value (< 2.2e-16), it indicates that at least one of the predictors has a significant effect on Adult Mortality. Overall, the model suggests that the HIV/AIDS variable has a statistically significant positive association with Adult Mortality, while the associations with Hepatitis B and Diphtheria variables are less clear and require further investigation.

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