data(mtcars)
dat <- mtcars
View(dat)
str(dat)
## 'data.frame': 32 obs. of 11 variables:
## $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
## $ cyl : num 6 6 4 6 8 6 8 4 4 6 ...
## $ disp: num 160 160 108 258 360 ...
## $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
## $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
## $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
## $ qsec: num 16.5 17 18.6 19.4 17 ...
## $ vs : num 0 0 1 1 0 1 0 1 1 1 ...
## $ am : num 1 1 1 0 0 0 0 0 0 0 ...
## $ gear: num 4 4 4 3 3 3 3 4 4 4 ...
## $ carb: num 4 4 1 1 2 1 4 2 2 4 ...
head(dat)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
tail(dat)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.7 0 1 5 2
## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.9 1 1 5 2
## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.5 0 1 5 4
## Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.5 0 1 5 6
## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.6 0 1 5 8
## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.6 1 1 4 2
summary(dat)
## mpg cyl disp hp
## Min. :10.40 Min. :4.000 Min. : 71.1 Min. : 52.0
## 1st Qu.:15.43 1st Qu.:4.000 1st Qu.:120.8 1st Qu.: 96.5
## Median :19.20 Median :6.000 Median :196.3 Median :123.0
## Mean :20.09 Mean :6.188 Mean :230.7 Mean :146.7
## 3rd Qu.:22.80 3rd Qu.:8.000 3rd Qu.:326.0 3rd Qu.:180.0
## Max. :33.90 Max. :8.000 Max. :472.0 Max. :335.0
## drat wt qsec vs
## Min. :2.760 Min. :1.513 Min. :14.50 Min. :0.0000
## 1st Qu.:3.080 1st Qu.:2.581 1st Qu.:16.89 1st Qu.:0.0000
## Median :3.695 Median :3.325 Median :17.71 Median :0.0000
## Mean :3.597 Mean :3.217 Mean :17.85 Mean :0.4375
## 3rd Qu.:3.920 3rd Qu.:3.610 3rd Qu.:18.90 3rd Qu.:1.0000
## Max. :4.930 Max. :5.424 Max. :22.90 Max. :1.0000
## am gear carb
## Min. :0.0000 Min. :3.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:2.000
## Median :0.0000 Median :4.000 Median :2.000
## Mean :0.4062 Mean :3.688 Mean :2.812
## 3rd Qu.:1.0000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :1.0000 Max. :5.000 Max. :8.000
#independent variable (x) : car weight
#dependent variable (y): fuel efficiency
#linear regression
model <- lm(mpg ~ wt, data = dat)
summary(model)
##
## Call:
## lm(formula = mpg ~ wt, data = dat)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.5432 -2.3647 -0.1252 1.4096 6.8727
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 37.2851 1.8776 19.858 < 2e-16 ***
## wt -5.3445 0.5591 -9.559 1.29e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.046 on 30 degrees of freedom
## Multiple R-squared: 0.7528, Adjusted R-squared: 0.7446
## F-statistic: 91.38 on 1 and 30 DF, p-value: 1.294e-10
#For the regression coefficient estamate of wt being -5.34, which is statiscally significant, we can conclue that there is a significant negative correlation between wt (car weight) and mpg (fuel efficiency).
#plot 1
plot(dat$wt, dat$mpg, main = "scatterplot of wt vs mpg with regression line",
xlab = "wt", ylab = "mpg")
abline(model, col = "skyblue")
#plot 2
plot(dat$wt, dat$mpg,
xlab = "car weight", ylab = "fuel efficiency",
main = "scatter plot with regression line",
col = "pink", pch = 16)
#regression line
abline(model, col = "red", lwd=2)
legend("topright", legend = c("data points", "regression line"),
col = c("pink", "red"), pch = c(16, NA), lty = c(NA,1))
data("ToothGrowth")
data <- ToothGrowth
View(data)
str(data)
## 'data.frame': 60 obs. of 3 variables:
## $ len : num 4.2 11.5 7.3 5.8 6.4 10 11.2 11.2 5.2 7 ...
## $ supp: Factor w/ 2 levels "OJ","VC": 2 2 2 2 2 2 2 2 2 2 ...
## $ dose: num 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 ...
head(data)
## len supp dose
## 1 4.2 VC 0.5
## 2 11.5 VC 0.5
## 3 7.3 VC 0.5
## 4 5.8 VC 0.5
## 5 6.4 VC 0.5
## 6 10.0 VC 0.5
tail(data)
## len supp dose
## 55 24.8 OJ 2
## 56 30.9 OJ 2
## 57 26.4 OJ 2
## 58 27.3 OJ 2
## 59 29.4 OJ 2
## 60 23.0 OJ 2
summary(data)
## len supp dose
## Min. : 4.20 OJ:30 Min. :0.500
## 1st Qu.:13.07 VC:30 1st Qu.:0.500
## Median :19.25 Median :1.000
## Mean :18.81 Mean :1.167
## 3rd Qu.:25.27 3rd Qu.:2.000
## Max. :33.90 Max. :2.000
#independent variable: dose of orange juice
#dependent variable: length of odontoblasts
#linear regression
model2 <- lm(len ~ dose, data = data)
summary(model2)
##
## Call:
## lm(formula = len ~ dose, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -8.4496 -2.7406 -0.7452 2.8344 10.1139
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7.4225 1.2601 5.89 2.06e-07 ***
## dose 9.7636 0.9525 10.25 1.23e-14 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.601 on 58 degrees of freedom
## Multiple R-squared: 0.6443, Adjusted R-squared: 0.6382
## F-statistic: 105.1 on 1 and 58 DF, p-value: 1.233e-14
#For the regression coefficient estamate of dose being 9.76, which is statiscally significant, we can conclue that there is a significant positive correlation between dose (dose of orange juice) and len (length of odontoblast)
#plot 1
plot(data$dose, data$len, main = "scatterplot of dose vs len with regression line",
xlab = "dose", ylab = "len")
abline(model2, col = "lightgreen")
#plot2
plot(data$dose, data$len,
xlab = "dose of orange juice", ylab = "length of odontoblast",
main = "scatter plot with regression line",
col = "orange", pch = 16)
#regression line
abline(model2, col = "yellow", lwd=2)
legend("topright", legend = c("data points", "regression line"),
col = c("orange", "yellow"), pch = c(16, NA), lty = c(NA,1))
