Tarea para la casa
Valeria Alfaro
2024-03-02
ion_waters <- read.table("ion_waters.csv",head=T,dec=".",sep=",")
View(ion_waters)str(ion_waters)## 'data.frame': 19 obs. of 3 variables:
## $ type : chr "GW" "S" "S" "GW" ...
## $ n.nitrate: num 0.2 0.98 0.59 0.19 0.46 0.2 0.31 0.27 0.33 0.2 ...
## $ sulphate : num 2.57 10.82 4.99 2.43 7.04 ...Exploración de datos
summary(ion_waters$n.nitrate)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1900 0.2000 0.2700 0.3232 0.3200 0.9800summary(ion_waters$sulphate)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.810 2.020 2.810 3.329 3.715 10.820Sub-Grupos
water <- read.table("ion_waters.csv",head=T,dec=".",sep = ",")
water## type n.nitrate sulphate
## 1 GW 0.20 2.57
## 2 S 0.98 10.82
## 3 S 0.59 4.99
## 4 GW 0.19 2.43
## 5 S 0.46 7.04
## 6 GW 0.20 3.12
## 7 S 0.31 3.75
## 8 GW 0.27 2.68
## 9 S 0.33 1.83
## 10 GW 0.20 0.81
## 11 GW 0.23 3.68
## 12 GW 0.26 4.01
## 13 S 0.40 2.81
## 14 S 0.30 2.90
## 15 GW 0.26 1.41
## 16 GW 0.27 2.93
## 17 GW 0.20 1.92
## 18 S 0.29 2.12
## 19 GW 0.20 1.43 WATERGW <- water[,1:3]
View(WATERGW)
GW <- subset(water , type=="GW")
GW## type n.nitrate sulphate
## 1 GW 0.20 2.57
## 4 GW 0.19 2.43
## 6 GW 0.20 3.12
## 8 GW 0.27 2.68
## 10 GW 0.20 0.81
## 11 GW 0.23 3.68
## 12 GW 0.26 4.01
## 15 GW 0.26 1.41
## 16 GW 0.27 2.93
## 17 GW 0.20 1.92
## 19 GW 0.20 1.43WATERS <- water[,1:3]
View(WATERS)
S <- subset(water , type=="S")
S## type n.nitrate sulphate
## 2 S 0.98 10.82
## 3 S 0.59 4.99
## 5 S 0.46 7.04
## 7 S 0.31 3.75
## 9 S 0.33 1.83
## 13 S 0.40 2.81
## 14 S 0.30 2.90
## 18 S 0.29 2.12Diferencias promedio
Aguas subterranea (GW)
mean(GW$n.nitrate)## [1] 0.2254545mean(GW$sulphate)## [1] 2.453636Aguas subterranea (s)
mean(S$n.nitrate)## [1] 0.4575mean(S$sulphate)## [1] 4.5325promedio nitrato
S.nitrate<-(S$n.nitrate)
gw.nitrate<-(GW$n.nitrate)
S.nitrate## [1] 0.98 0.59 0.46 0.31 0.33 0.40 0.30 0.29gw.nitrate## [1] 0.20 0.19 0.20 0.27 0.20 0.23 0.26 0.26 0.27 0.20 0.20PRUEBA F: Significancia de VARIANZA NITRATO
var.test(S$n.nitrate, gw.nitrate)##
## F test to compare two variances
##
## data: S$n.nitrate and gw.nitrate
## F = 50.552, num df = 7, denom df = 10, p-value = 1.041e-06
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 12.79866 240.68604
## sample estimates:
## ratio of variances
## 50.55244Hipotesis nula: NO hay variaciones significativas en la varianza (0) Hipotesis alternativa: SI hay variaciones significativas en la varianza (1)
RESULTADO: 0 NO ES SIGNIFICATIVO
PRUEBA T: Significancia de PROMEDIO NITRATO
t.test(S$n.nitrate, gw.nitrate, mu = 0, paired = FALSE, var.equal = FALSE)##
## Welch Two Sample t-test
##
## data: S$n.nitrate and gw.nitrate
## t = 2.7796, df = 7.2018, p-value = 0.02655
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 0.03575589 0.42833502
## sample estimates:
## mean of x mean of y
## 0.4575000 0.2254545Hipotesis nula: NO hay variaciones significativas en el promedio (0) Hipotesis alternativa: SI hay variaciones significativas en el promedio (1)
RESULTADO: 1 SI ES SIGNIFICATIVO
promedio sulfato
S.sulphate<-(S$sulphate)
gw.sulphate<-(GW$sulphate)
S.sulphate## [1] 10.82 4.99 7.04 3.75 1.83 2.81 2.90 2.12gw.sulphate## [1] 2.57 2.43 3.12 2.68 0.81 3.68 4.01 1.41 2.93 1.92 1.43PRUEBA F:Significancia de VARIANZA sulfato
var.test(S$sulphate, gw.sulphate)##
## F test to compare two variances
##
## data: S$sulphate and gw.sulphate
## F = 9.547, num df = 7, denom df = 10, p-value = 0.001975
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 2.417057 45.454144
## sample estimates:
## ratio of variances
## 9.546951Hipotesis nula: NO hay variaciones significativas en la varianza (0) Hipotesis alternativa: SI hay variaciones significativas en la varianza (1)
RESULTADO: 0 NO ES SIGNIFICATIVO
PRUEBA T: Significancia de PROMEDIO NITRATO
t.test(S$sulphate, gw.sulphate, mu = 0, paired = FALSE, var.equal = FALSE)##
## Welch Two Sample t-test
##
## data: S$sulphate and gw.sulphate
## t = 1.8544, df = 8.0743, p-value = 0.1005
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.5021694 4.6598967
## sample estimates:
## mean of x mean of y
## 4.532500 2.453636Hipotesis nula: NO hay variaciones significativas en el promedio (0) Hipotesis alternativa: SI hay variaciones significativas en el promedio (1)
RESULTADO: 1 SI ES SIGNIFICATIVO
si hay diferencias significativas entre ambos promedio de nitrato y sulfato
Gráfca variables para evidenciar la correlación
library(ggplot2)
plot(GW$n.nitrate,GW$sulphate,pch=19,col="blue",cex=1)
plot(S$n.nitrate,S$sulphate,pch=19,col="red",cex=1)
No hay correlación
Estimación modelo de regresión lineal
S.nitrate<-(S$n.nitrate)
gw.nitrate<-(GW$n.nitrate)
S.nitrate## [1] 0.98 0.59 0.46 0.31 0.33 0.40 0.30 0.29gw.nitrate## [1] 0.20 0.19 0.20 0.27 0.20 0.23 0.26 0.26 0.27 0.20 0.20regresión lineal GW (subterránea)
MODEL1=lm(GW$n.nitrate ~ GW$sulphate)
MODEL1##
## Call:
## lm(formula = GW$n.nitrate ~ GW$sulphate)
##
## Coefficients:
## (Intercept) GW$sulphate
## 0.19612 0.01195summary(MODEL1)##
## Call:
## lm(formula = GW$n.nitrate ~ GW$sulphate)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.03517 -0.02296 -0.01012 0.02740 0.04702
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.19612 0.02726 7.193 5.12e-05 ***
## GW$sulphate 0.01195 0.01037 1.153 0.279
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.03245 on 9 degrees of freedom
## Multiple R-squared: 0.1286, Adjusted R-squared: 0.0318
## F-statistic: 1.328 on 1 and 9 DF, p-value: 0.2788plot(MODEL1,which=1)
regresión lineal S (superficial)
MODEL2=lm(S$n.nitrate ~ S$sulphate)
MODEL2##
## Call:
## lm(formula = S$n.nitrate ~ S$sulphate)
##
## Coefficients:
## (Intercept) S$sulphate
## 0.14060 0.06992summary(MODEL2)##
## Call:
## lm(formula = S$n.nitrate ~ S$sulphate)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.17281 -0.05572 0.03131 0.06792 0.10051
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.14060 0.06901 2.037 0.08775 .
## S$sulphate 0.06992 0.01288 5.429 0.00162 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1041 on 6 degrees of freedom
## Multiple R-squared: 0.8309, Adjusted R-squared: 0.8027
## F-statistic: 29.48 on 1 and 6 DF, p-value: 0.001618plot(MODEL2,which=1)