anscombe data that is part of the library(datasets) in R. And assign that data to a new object called data.data <- anscombe
fBasics() package!)library(fBasics)
## Loading required package: timeDate
## Loading required package: timeSeries
##
## Rmetrics Package fBasics
## Analysing Markets and calculating Basic Statistics
## Copyright (C) 2005-2014 Rmetrics Association Zurich
## Educational Software for Financial Engineering and Computational Science
## Rmetrics is free software and comes with ABSOLUTELY NO WARRANTY.
## https://www.rmetrics.org --- Mail to: info@rmetrics.org
basicStats(data)
## x1 x2 x3 x4 y1 y2
## nobs 11.000000 11.000000 11.000000 11.000000 11.000000 11.000000
## NAs 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
## Minimum 4.000000 4.000000 4.000000 8.000000 4.260000 3.100000
## Maximum 14.000000 14.000000 14.000000 19.000000 10.840000 9.260000
## 1. Quartile 6.500000 6.500000 6.500000 8.000000 6.315000 6.695000
## 3. Quartile 11.500000 11.500000 11.500000 8.000000 8.570000 8.950000
## Mean 9.000000 9.000000 9.000000 9.000000 7.500909 7.500909
## Median 9.000000 9.000000 9.000000 8.000000 7.580000 8.140000
## Sum 99.000000 99.000000 99.000000 99.000000 82.510000 82.510000
## SE Mean 1.000000 1.000000 1.000000 1.000000 0.612541 0.612568
## LCL Mean 6.771861 6.771861 6.771861 6.771861 6.136083 6.136024
## UCL Mean 11.228139 11.228139 11.228139 11.228139 8.865735 8.865795
## Variance 11.000000 11.000000 11.000000 11.000000 4.127269 4.127629
## Stdev 3.316625 3.316625 3.316625 3.316625 2.031568 2.031657
## Skewness 0.000000 0.000000 0.000000 2.466911 -0.048374 -0.978693
## Kurtosis -1.528926 -1.528926 -1.528926 4.520661 -1.199123 -0.514319
## y3 y4
## nobs 11.000000 11.000000
## NAs 0.000000 0.000000
## Minimum 5.390000 5.250000
## Maximum 12.740000 12.500000
## 1. Quartile 6.250000 6.170000
## 3. Quartile 7.980000 8.190000
## Mean 7.500000 7.500909
## Median 7.110000 7.040000
## Sum 82.500000 82.510000
## SE Mean 0.612196 0.612242
## LCL Mean 6.135943 6.136748
## UCL Mean 8.864057 8.865070
## Variance 4.122620 4.123249
## Stdev 2.030424 2.030579
## Skewness 1.380120 1.120774
## Kurtosis 1.240044 0.628751
correlationTest(data$x1, data$y1)
##
## Title:
## Pearson's Correlation Test
##
## Test Results:
## PARAMETER:
## Degrees of Freedom: 9
## SAMPLE ESTIMATES:
## Correlation: 0.8164
## STATISTIC:
## t: 4.2415
## P VALUE:
## Alternative Two-Sided: 0.00217
## Alternative Less: 0.9989
## Alternative Greater: 0.001085
## CONFIDENCE INTERVAL:
## Two-Sided: 0.4244, 0.9507
## Less: -1, 0.9388
## Greater: 0.5113, 1
##
## Description:
## Tue Sep 12 11:57:24 2017
correlationTest(data$x2, data$y2)
##
## Title:
## Pearson's Correlation Test
##
## Test Results:
## PARAMETER:
## Degrees of Freedom: 9
## SAMPLE ESTIMATES:
## Correlation: 0.8162
## STATISTIC:
## t: 4.2386
## P VALUE:
## Alternative Two-Sided: 0.002179
## Alternative Less: 0.9989
## Alternative Greater: 0.001089
## CONFIDENCE INTERVAL:
## Two-Sided: 0.4239, 0.9506
## Less: -1, 0.9387
## Greater: 0.5109, 1
##
## Description:
## Tue Sep 12 11:57:24 2017
correlationTest(data$x3, data$y3)
##
## Title:
## Pearson's Correlation Test
##
## Test Results:
## PARAMETER:
## Degrees of Freedom: 9
## SAMPLE ESTIMATES:
## Correlation: 0.8163
## STATISTIC:
## t: 4.2394
## P VALUE:
## Alternative Two-Sided: 0.002176
## Alternative Less: 0.9989
## Alternative Greater: 0.001088
## CONFIDENCE INTERVAL:
## Two-Sided: 0.4241, 0.9507
## Less: -1, 0.9387
## Greater: 0.511, 1
##
## Description:
## Tue Sep 12 11:57:24 2017
correlationTest(data$x4, data$y4)
##
## Title:
## Pearson's Correlation Test
##
## Test Results:
## PARAMETER:
## Degrees of Freedom: 9
## SAMPLE ESTIMATES:
## Correlation: 0.8165
## STATISTIC:
## t: 4.243
## P VALUE:
## Alternative Two-Sided: 0.002165
## Alternative Less: 0.9989
## Alternative Greater: 0.001082
## CONFIDENCE INTERVAL:
## Two-Sided: 0.4246, 0.9507
## Less: -1, 0.9388
## Greater: 0.5115, 1
##
## Description:
## Tue Sep 12 11:57:24 2017
plot(data$x1, data$y1, main="Scatterplot of x1 and y1",xlab="x1 Values", ylab="y1 Values")
plot(data$x2, data$y2, main="Scatterplot of x2 and y2",xlab="x2 Values", ylab="y2 Values")
plot(data$x3, data$y3, main="Scatterplot of x3 and y3",xlab="x3 Values", ylab="y3 Values")
plot(data$x4, data$y4, main="Scatterplot of x4 and y4",xlab="x4 Values", ylab="y4 Values")
par(mfrow=c(2,2))
plot(data$x1, data$y1, main="Scatterplot of x1 and y1",xlab="x1 Values", ylab="y1 Values",pch=19)
plot(data$x2, data$y2, main="Scatterplot of x2 and y2",xlab="x2 Values", ylab="y2 Values",pch=19)
plot(data$x3, data$y3, main="Scatterplot of x3 and y3",xlab="x3 Values", ylab="y3 Values",pch=19)
plot(data$x4, data$y4, main="Scatterplot of x4 and y4",xlab="x4 Values", ylab="y4 Values",pch=19)
lm() function.X1Y1 <- lm(data$y1~data$x1, data=data)
summary(X1Y1)
##
## Call:
## lm(formula = data$y1 ~ data$x1, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.92127 -0.45577 -0.04136 0.70941 1.83882
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.0001 1.1247 2.667 0.02573 *
## data$x1 0.5001 0.1179 4.241 0.00217 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.237 on 9 degrees of freedom
## Multiple R-squared: 0.6665, Adjusted R-squared: 0.6295
## F-statistic: 17.99 on 1 and 9 DF, p-value: 0.00217
X2Y2 <- lm(data$y2~data$x2, data=data)
summary(X2Y2)
##
## Call:
## lm(formula = data$y2 ~ data$x2, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.9009 -0.7609 0.1291 0.9491 1.2691
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.001 1.125 2.667 0.02576 *
## data$x2 0.500 0.118 4.239 0.00218 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.237 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
X3Y3 <- lm(data$y3~data$x3, data=data)
summary(X3Y3)
##
## Call:
## lm(formula = data$y3 ~ data$x3, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.1586 -0.6146 -0.2303 0.1540 3.2411
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.0025 1.1245 2.670 0.02562 *
## data$x3 0.4997 0.1179 4.239 0.00218 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.236 on 9 degrees of freedom
## Multiple R-squared: 0.6663, Adjusted R-squared: 0.6292
## F-statistic: 17.97 on 1 and 9 DF, p-value: 0.002176
X4Y4 <- lm(data$y4~data$x4, data=data)
summary(X4Y4)
##
## Call:
## lm(formula = data$y4 ~ data$x4, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.751 -0.831 0.000 0.809 1.839
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.0017 1.1239 2.671 0.02559 *
## data$x4 0.4999 0.1178 4.243 0.00216 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.236 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
#For x1 and y1 values
par(mfrow=c(2,2))
plot(data$x1, data$y1, main="Scatterplot of x1 and y1",xlab="x1 Values", ylab="y1 Values",pch=19)
abline(X1Y1)
#For x2 and y2 values
plot(data$x2, data$y2, main="Scatterplot of x2 and y2",xlab="x2 Values", ylab="y2 Values",pch=19)
abline(X2Y2)
#For x3 and y3 values
plot(data$x3, data$y3, main="Scatterplot of x3 and y3",xlab="x3 Values", ylab="y3 Values",pch=19)
abline(X3Y3)
#For x4 and y4 values
plot(data$x4, data$y4, main="Scatterplot of x4 and y4",xlab="x4 Values", ylab="y4 Values",pch=19)
abline(X4Y4)
#Model fit for x1,y1
anova(X1Y1)
## Analysis of Variance Table
##
## Response: data$y1
## Df Sum Sq Mean Sq F value Pr(>F)
## data$x1 1 27.510 27.5100 17.99 0.00217 **
## Residuals 9 13.763 1.5292
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Model fit for x2,y2
anova(X2Y2)
## Analysis of Variance Table
##
## Response: data$y2
## Df Sum Sq Mean Sq F value Pr(>F)
## data$x2 1 27.500 27.5000 17.966 0.002179 **
## Residuals 9 13.776 1.5307
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Model fit for x3,y3
anova(X3Y3)
## Analysis of Variance Table
##
## Response: data$y3
## Df Sum Sq Mean Sq F value Pr(>F)
## data$x3 1 27.470 27.4700 17.972 0.002176 **
## Residuals 9 13.756 1.5285
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Model fit for x4,y4
anova(X4Y4)
## Analysis of Variance Table
##
## Response: data$y4
## Df Sum Sq Mean Sq F value Pr(>F)
## data$x4 1 27.490 27.4900 18.003 0.002165 **
## Residuals 9 13.742 1.5269
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Data visualizations provides a unique perspective of a dataset and helps understand more beyond numerical relationships.
Anscombe’s Quartet consists of four datasets consisting of x and y values. Since they have almost identical statistical values its easier to assume that they have similar properties but when plotted we can see the values and interpretations of each data set is different
Therefore, this helps us realize that although the summary values are almost similar when we create data visualization it helps us identify the differences between data sets.