anscombe
data that is part of the library(datasets)
in R
. And assign that data to a new object called data
.data=anscombe
View(data)
fBasics()
package!)summary(data)
## x1 x2 x3 x4
## Min. : 4.0 Min. : 4.0 Min. : 4.0 Min. : 8
## 1st Qu.: 6.5 1st Qu.: 6.5 1st Qu.: 6.5 1st Qu.: 8
## Median : 9.0 Median : 9.0 Median : 9.0 Median : 8
## Mean : 9.0 Mean : 9.0 Mean : 9.0 Mean : 9
## 3rd Qu.:11.5 3rd Qu.:11.5 3rd Qu.:11.5 3rd Qu.: 8
## Max. :14.0 Max. :14.0 Max. :14.0 Max. :19
## y1 y2 y3 y4
## Min. : 4.260 Min. :3.100 Min. : 5.39 Min. : 5.250
## 1st Qu.: 6.315 1st Qu.:6.695 1st Qu.: 6.25 1st Qu.: 6.170
## Median : 7.580 Median :8.140 Median : 7.11 Median : 7.040
## Mean : 7.501 Mean :7.501 Mean : 7.50 Mean : 7.501
## 3rd Qu.: 8.570 3rd Qu.:8.950 3rd Qu.: 7.98 3rd Qu.: 8.190
## Max. :10.840 Max. :9.260 Max. :12.74 Max. :12.500
var(data$x1)
## [1] 11
var(data$x2)
## [1] 11
var(data$x3)
## [1] 11
var(data$x4)
## [1] 11
var(data$y1)
## [1] 4.127269
var(data$y2)
## [1] 4.127629
var(data$y3)
## [1] 4.12262
var(data$y4)
## [1] 4.123249
library(fBasics)
## Loading required package: timeDate
## Loading required package: timeSeries
cor.test(data$x1,data$y1)
##
## Pearson's product-moment correlation
##
## data: data$x1 and data$y1
## t = 4.2415, df = 9, p-value = 0.00217
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.4243912 0.9506933
## sample estimates:
## cor
## 0.8164205
cor.test(data$x2,data$y2)
##
## Pearson's product-moment correlation
##
## data: data$x2 and data$y2
## t = 4.2386, df = 9, p-value = 0.002179
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.4239389 0.9506402
## sample estimates:
## cor
## 0.8162365
cor.test(data$x3,data$y3)
##
## Pearson's product-moment correlation
##
## data: data$x3 and data$y3
## t = 4.2394, df = 9, p-value = 0.002176
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.4240623 0.9506547
## sample estimates:
## cor
## 0.8162867
cor.test(data$x4,data$y4)
##
## Pearson's product-moment correlation
##
## data: data$x4 and data$y4
## t = 4.243, df = 9, p-value = 0.002165
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.4246394 0.9507224
## sample estimates:
## cor
## 0.8165214
plot(data$x1,data$y1)
plot(data$x2,data$y2)
plot(data$x3,data$y3)
plot(data$x4,data$y4)
par(mfrow=c(2,2))
plot(data$x1,data$y1,pch=18)
plot(data$x2,data$y2,pch=18)
plot(data$x3,data$y3,pch=18)
plot(data$x4,data$y4,pch=18)
lm()
function.lm1=lm(data$x1~data$y1)
summary(lm1)
##
## Call:
## lm(formula = data$x1 ~ data$y1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6522 -1.5117 -0.2657 1.2341 3.8946
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.9975 2.4344 -0.410 0.69156
## data$y1 1.3328 0.3142 4.241 0.00217 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.019 on 9 degrees of freedom
## Multiple R-squared: 0.6665, Adjusted R-squared: 0.6295
## F-statistic: 17.99 on 1 and 9 DF, p-value: 0.00217
lm2=lm(data$x2~data$y2)
summary(lm2)
##
## Call:
## lm(formula = data$x2 ~ data$y2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.8516 -1.4315 -0.3440 0.8467 4.2017
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.9948 2.4354 -0.408 0.69246
## data$y2 1.3325 0.3144 4.239 0.00218 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.02 on 9 degrees of freedom
## Multiple R-squared: 0.6662, Adjusted R-squared: 0.6292
## F-statistic: 17.97 on 1 and 9 DF, p-value: 0.002179
lm3=lm(data$x3~data$y3)
summary(lm3)
##
## Call:
## lm(formula = data$x3 ~ data$y3)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9869 -1.3733 -0.0266 1.3200 3.2133
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.0003 2.4362 -0.411 0.69097
## data$y3 1.3334 0.3145 4.239 0.00218 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.019 on 9 degrees of freedom
## Multiple R-squared: 0.6663, Adjusted R-squared: 0.6292
## F-statistic: 17.97 on 1 and 9 DF, p-value: 0.002176
lm4=lm(data$x4~data$y4)
summary(lm4)
##
## Call:
## lm(formula = data$x4 ~ data$y4)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.7859 -1.4122 -0.1853 1.4551 3.3329
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.0036 2.4349 -0.412 0.68985
## data$y4 1.3337 0.3143 4.243 0.00216 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.018 on 9 degrees of freedom
## Multiple R-squared: 0.6667, Adjusted R-squared: 0.6297
## F-statistic: 18 on 1 and 9 DF, p-value: 0.002165
par(mfrow=c(2,2))
plot(data$x1,data$y1)
abline(lm1,col="purple")
plot(data$x2,data$y2)
abline(lm2,col="red")
plot(data$x3,data$y3)
abline(lm3,col="blue")
plot(data$x4,data$y4)
abline(lm4,col="orange")
anova(lm1)
Analysis of Variance Table
Response: data\(x1 Df Sum Sq Mean Sq F value Pr(>F) data\)y1 1 73.32 73.320 17.99 0.00217 ** Residuals 9 36.68 4.076
— Signif. codes: 0 ‘’ 0.001 ’’ 0.01 ’’ 0.05 ‘.’ 0.1 ‘’ 1
anova(lm2)
Analysis of Variance Table
Response: data\(x2 Df Sum Sq Mean Sq F value Pr(>F) data\)y2 1 73.287 73.287 17.966 0.002179 ** Residuals 9 36.713 4.079
— Signif. codes: 0 ‘’ 0.001 ’’ 0.01 ’’ 0.05 ‘.’ 0.1 ‘’ 1
anova(lm3)
Analysis of Variance Table
Response: data\(x3 Df Sum Sq Mean Sq F value Pr(>F) data\)y3 1 73.296 73.296 17.972 0.002176 ** Residuals 9 36.704 4.078
— Signif. codes: 0 ‘’ 0.001 ’’ 0.01 ’’ 0.05 ‘.’ 0.1 ‘’ 1
anova(lm4)
Analysis of Variance Table
Response: data\(x4 Df Sum Sq Mean Sq F value Pr(>F) data\)y4 1 73.338 73.338 18.003 0.002165 ** Residuals 9 36.662 4.074
— Signif. codes: 0 ‘’ 0.001 ’’ 0.01 ’’ 0.05 ‘.’ 0.1 ‘’ 1
From the mean and variance tests, we found that the variances for x1, x2, x3,and x4 were all the same and the variances for y1, y2, y3, and y4 were close to each other. So it seems like they are similar to each other.Then we drew the graphs and fitted them for the linear regression model. Only the third group of data fitted well. The lesson of Anscombe’s Quarter showed us that data visualization can give us more clear information about our data and make us have a better understanding.