Vaccine Aparthaid: Working File
Tato Khundadze
Summarize Data
summary(data) country income_group continent
Length:141 Length:141 Length:141
Class :character Class :character Class :character
Mode :character Mode :character Mode :character
people_fully_vaccinated_per_hund (pfvph) total_deaths_per_million
Min. : 0.35 Min. : 3.21
1st Qu.:17.93 1st Qu.: 167.92
Median :41.17 Median : 773.22
Mean :40.95 Mean :1048.29
3rd Qu.:64.22 3rd Qu.:1750.86
Max. :87.56 Max. :6013.44
hospital_beds_per_thousand (hbpt) cardiovasc_death_rate
Min. : 0.100 Min. : 85.75
1st Qu.: 1.300 1st Qu.:155.90
Median : 2.500 Median :237.37
Mean : 2.994 Mean :253.09
3rd Qu.: 4.200 3rd Qu.:329.63
Max. :12.270 Max. :724.42
diabetes_prevalence population_density population
Min. : 1.820 Min. : 1.98 Min. :9.873e+04
1st Qu.: 5.310 1st Qu.: 37.73 1st Qu.:2.973e+06
Median : 7.110 Median : 82.60 Median :1.022e+07
Mean : 7.781 Mean : 209.20 Mean :4.995e+07
3rd Qu.: 9.750 3rd Qu.: 157.83 3rd Qu.:3.780e+07
Max. :22.020 Max. :7915.73 Max. :1.444e+09
aged_70_older log_vacc code year
Min. : 0.617 Min. :-1.050 Length:141 Min. :2020
1st Qu.: 2.385 1st Qu.: 2.886 Class :character 1st Qu.:2020
Median : 4.458 Median : 3.718 Mode :character Median :2020
Mean : 6.073 Mean : 3.275 Mean :2020
3rd Qu.: 9.720 3rd Qu.: 4.162 3rd Qu.:2020
Max. :16.240 Max. : 4.472 Max. :2020
gdppercapitapppcons2017 (gdppcapita)
Min. : 928.6
1st Qu.: 6118.4
Median : 14064.0
Mean : 21489.7
3rd Qu.: 31007.8
Max. :110261.2 Glance of the data: top 10
head(data,10)Variable list
ls(data) [1] "aged_70_older"
[2] "cardiovasc_death_rate"
[3] "code"
[4] "continent"
[5] "country"
[6] "diabetes_prevalence"
[7] "gdppercapitapppcons2017 (gdppcapita)"
[8] "hospital_beds_per_thousand (hbpt)"
[9] "income_group"
[10] "log_vacc"
[11] "people_fully_vaccinated_per_hund (pfvph)"
[12] "population"
[13] "population_density"
[14] "total_deaths_per_million"
[15] "year" Plot
ggplot(data=data, aes(x = log(`people_fully_vaccinated_per_hund (pfvph)`),
y= log(total_deaths_per_million))) + geom_point() +
geom_smooth(method = "lm", se=FALSE) +
ggtitle("Vaccination and death per million") +
xlab(" people fully vaccinated per hundred") + ylab("total deaths per million")
NA
NARegression - Restricted
reg1 <- lm(data=data,log(total_deaths_per_million)~ log(`people_fully_vaccinated_per_hund (pfvph)`))
summary (reg1)
Call:
lm(formula = log(total_deaths_per_million) ~ log(`people_fully_vaccinated_per_hund (pfvph)`),
data = data)
Residuals:
Min 1Q Median 3Q Max
-5.7083 -0.6423 0.2341 0.9019 2.3696
Coefficients:
Estimate Std. Error
(Intercept) 3.73497 0.33591
log(`people_fully_vaccinated_per_hund (pfvph)`) 0.72864 0.09611
t value Pr(>|t|)
(Intercept) 11.119 < 2e-16 ***
log(`people_fully_vaccinated_per_hund (pfvph)`) 7.582 4.4e-12 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 1.395 on 139 degrees of freedom
Multiple R-squared: 0.2925, Adjusted R-squared: 0.2875
F-statistic: 57.48 on 1 and 139 DF, p-value: 4.398e-12 Regression output for Complex Model
reg2 <- lm(data=data,log(total_deaths_per_million)~ log(`people_fully_vaccinated_per_hund (pfvph)`) +
log(`hospital_beds_per_thousand (hbpt)`))
summary(reg2)
Call:
lm(formula = log(total_deaths_per_million) ~ log(`people_fully_vaccinated_per_hund (pfvph)`) +
log(`hospital_beds_per_thousand (hbpt)`), data = data)
Residuals:
Min 1Q Median 3Q Max
-5.8265 -0.5765 0.2353 0.9306 2.3972
Coefficients:
Estimate Std. Error
(Intercept) 4.0201 0.3416
log(`people_fully_vaccinated_per_hund (pfvph)`) 0.5287 0.1162
log(`hospital_beds_per_thousand (hbpt)`) 0.4732 0.1628
t value Pr(>|t|)
(Intercept) 11.767 < 2e-16 ***
log(`people_fully_vaccinated_per_hund (pfvph)`) 4.551 1.16e-05 ***
log(`hospital_beds_per_thousand (hbpt)`) 2.907 0.00425 **
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 1.359 on 138 degrees of freedom
Multiple R-squared: 0.3334, Adjusted R-squared: 0.3237
F-statistic: 34.51 on 2 and 138 DF, p-value: 7.045e-13Regression Tables side by side
huxreg(reg1,reg2) ───────────────────────────────────────────────────────
(1) (2)
───────────────────────────────
(Intercept) 3.735 *** 4.020 ***
(0.336) (0.342)
log(`people_fully_vac 0.729 *** 0.529 ***
cinated_per_hund
(pfvph)`)
(0.096) (0.116)
log(`hospital_beds_pe 0.473 **
r_thousand (hbpt)`)
(0.163)
───────────────────────────────
N 141 141
R2 0.293 0.333
logLik -245.964 -241.773
AIC 497.928 491.547
───────────────────────────────────────────────────────
*** p < 0.001; ** p < 0.01; * p < 0.05.
Column names: names, model1, model2Analysis of Variance: F-test
anova(reg1, reg2, test='F')Analysis of Variance Table
Model 1: log(total_deaths_per_million) ~ log(`people_fully_vaccinated_per_hund (pfvph)`)
Model 2: log(total_deaths_per_million) ~ log(`people_fully_vaccinated_per_hund (pfvph)`) +
log(`hospital_beds_per_thousand (hbpt)`)
Res.Df RSS Df Sum of Sq F Pr(>F)
1 139 270.35
2 138 254.75 1 15.601 8.4512 0.004252 **
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1Conlusion for the nested model: the null hypothesis that ‘naive’ model is better is rejected.
Data source: https://ourworldindata.org/
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