loading packages

library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.3     v purrr   0.3.4
## v tibble  3.1.0     v dplyr   1.0.5
## v tidyr   1.1.3     v stringr 1.4.0
## v readr   1.4.0     v forcats 0.5.1
## Warning: package 'tibble' was built under R version 4.0.5
## Warning: package 'tidyr' was built under R version 4.0.5
## Warning: package 'dplyr' was built under R version 4.0.5
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

loading dataset

url="https://raw.githubusercontent.com/schoolkidrich/R/main/DATA_605/week12/who.csv"

who=read.csv(url)
summary(who)
##    Country             LifeExp      InfantSurvival   Under5Survival  
##  Length:190         Min.   :40.00   Min.   :0.8350   Min.   :0.7310  
##  Class :character   1st Qu.:61.25   1st Qu.:0.9433   1st Qu.:0.9253  
##  Mode  :character   Median :70.00   Median :0.9785   Median :0.9745  
##                     Mean   :67.38   Mean   :0.9624   Mean   :0.9459  
##                     3rd Qu.:75.00   3rd Qu.:0.9910   3rd Qu.:0.9900  
##                     Max.   :83.00   Max.   :0.9980   Max.   :0.9970  
##      TBFree           PropMD              PropRN             PersExp       
##  Min.   :0.9870   Min.   :0.0000196   Min.   :0.0000883   Min.   :   3.00  
##  1st Qu.:0.9969   1st Qu.:0.0002444   1st Qu.:0.0008455   1st Qu.:  36.25  
##  Median :0.9992   Median :0.0010474   Median :0.0027584   Median : 199.50  
##  Mean   :0.9980   Mean   :0.0017954   Mean   :0.0041336   Mean   : 742.00  
##  3rd Qu.:0.9998   3rd Qu.:0.0024584   3rd Qu.:0.0057164   3rd Qu.: 515.25  
##  Max.   :1.0000   Max.   :0.0351290   Max.   :0.0708387   Max.   :6350.00  
##     GovtExp             TotExp      
##  Min.   :    10.0   Min.   :    13  
##  1st Qu.:   559.5   1st Qu.:   584  
##  Median :  5385.0   Median :  5541  
##  Mean   : 40953.5   Mean   : 41696  
##  3rd Qu.: 25680.2   3rd Qu.: 26331  
##  Max.   :476420.0   Max.   :482750

1

scatterplot LifeExp~TotExp

# scatter plot represents a log relationship rather than a linear one
who%>%
  ggplot(aes(x=TotExp,y=LifeExp))+geom_point(stat='identity')

model 1

m1 = lm(LifeExp~TotExp,who)
summary(m1)
## 
## Call:
## lm(formula = LifeExp ~ TotExp, data = who)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -24.764  -4.778   3.154   7.116  13.292 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 6.475e+01  7.535e-01  85.933  < 2e-16 ***
## TotExp      6.297e-05  7.795e-06   8.079 7.71e-14 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 9.371 on 188 degrees of freedom
## Multiple R-squared:  0.2577, Adjusted R-squared:  0.2537 
## F-statistic: 65.26 on 1 and 188 DF,  p-value: 7.714e-14

I do not believe assumptions for linear regression are currently met

# residuals do not cluster around 0
plot(fitted(m1),resid(m1))

# residuals do not seem normally distributed 
qqnorm(resid(m1))

2 log transform for LifeExp and TotExp

scatter plot

who%>%
  ggplot(aes(x = LifeExp^4.6,y=TotExp^0.06))+geom_point()

model 2

m2 = lm(I(LifeExp^4.6)~I(TotExp^0.06), who)
summary(m2)
## 
## Call:
## lm(formula = I(LifeExp^4.6) ~ I(TotExp^0.06), data = who)
## 
## Residuals:
##        Min         1Q     Median         3Q        Max 
## -308616089  -53978977   13697187   59139231  211951764 
## 
## Coefficients:
##                  Estimate Std. Error t value Pr(>|t|)    
## (Intercept)    -736527910   46817945  -15.73   <2e-16 ***
## I(TotExp^0.06)  620060216   27518940   22.53   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 90490000 on 188 degrees of freedom
## Multiple R-squared:  0.7298, Adjusted R-squared:  0.7283 
## F-statistic: 507.7 on 1 and 188 DF,  p-value: < 2.2e-16

model 2 is “better” as it fits more assumptions and boasts a R^2 value closer to one.

# residuals cluster around 0
plot(fitted(m2),resid(m2))

# residual for model 2 is closer to normal than model 1 
qqnorm(resid(m2))

3

model 2 predictions

# accounting for 0.06 exponent for TotExp
TotExpPredict = data.frame(TotExp=c(1.5^(1/0.06),2.5^(1/0.06)))
TotExpPredict$prediction = predict(m2,TotExpPredict)

# accounting for 4.6 exponent for LifeExp
TotExpPredict$prediction = TotExpPredict$prediction^(1/4.6)
head(TotExpPredict)
##        TotExp prediction
## 1     860.705   63.31153
## 2 4288777.125   86.50645

4

model 3

m3 = lm(LifeExp~PropMD+TotExp+PropMD*TotExp,who)
summary(m3)
## 
## Call:
## lm(formula = LifeExp ~ PropMD + TotExp + PropMD * TotExp, data = who)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -27.320  -4.132   2.098   6.540  13.074 
## 
## Coefficients:
##                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)    6.277e+01  7.956e-01  78.899  < 2e-16 ***
## PropMD         1.497e+03  2.788e+02   5.371 2.32e-07 ***
## TotExp         7.233e-05  8.982e-06   8.053 9.39e-14 ***
## PropMD:TotExp -6.026e-03  1.472e-03  -4.093 6.35e-05 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 8.765 on 186 degrees of freedom
## Multiple R-squared:  0.3574, Adjusted R-squared:  0.3471 
## F-statistic: 34.49 on 3 and 186 DF,  p-value: < 2.2e-16

model 3 does not seem to be very good

# residuals form a pattern
plot(fitted(m3),resid(m3))

# residual for is not normally distributed
hist(resid(m3))

5

forecast = data.frame(PropMD = c(0.03),TotExp = c(14))
forecast$prediction = predict(m3,forecast)

# this prediction does not seem realistic as the predicted value is high for a low TotExp value.
head(forecast)
##   PropMD TotExp prediction
## 1   0.03     14    107.696