Updating to fit with video presented on Coursera

07_RegressionModels/01_06_residualVariation/index.Rmd

@@ -83,44 +83,77 @@ for (i in 1 : n)
   lines(c(x[i], x[i]), c(y[i], yhat[i]), col = "red" , lwd = 2)
 ```
 
----
-## Residuals versus X
-```{r, echo = FALSE, fig.height=5, fig.width=5}
-plot(diamond$carat, e,  
-     xlab = "Mass (carats)", 
-     ylab = "Residuals (SIN $)", 
-     bg = "lightblue", 
-     col = "black", cex = 1.1, pch = 21,frame = FALSE)
-abline(h = 0, lwd = 2)
-for (i in 1 : n) 
-  lines(c(x[i], x[i]), c(e[i], 0), col = "red" , lwd = 2)
-```
-
----
+---  
 ## Non-linear data
 ```{r, echo = TRUE, fig.height=5, fig.width=5}
 x <- runif(100, -3, 3); y <- x + sin(x) + rnorm(100, sd = .2); 
-plot(x, y); abline(lm(y ~ x))
+library(ggplot2)
+g = ggplot(data.frame(x = x, y = y), aes(x = x, y = y))
+g = g + geom_smooth(method="lm", colour="black")
+g = g + geom_point(size = 7, colour="black", alpha = 0.4)
+g = g + geom_point(size = 5, colour="red", alpha = 0.4)
+g
 ```
 
 ---
 ```{r, echo = TRUE, fig.height=5, fig.width=5}
-plot(x, resid(lm(y ~ x))); 
-abline(h = 0)
+g = ggplot(data.frame(x = x, y = resid(lm(y ~ x))),
+           aes(x = x, y = y))
+g = g + geom_hline(yintercept = 0, size=2);
+g = g + geom_point(size = 7, colour = "black", alpha = 0.4)
+g = g + geom_point(size = 5, colour = "red", alpha = 0.4)
+g = g + xlab("X") + ylab("Residual")
+g
 ```
 
 ---
 ## Heteroskedasticity
 ```{r, echo = TRUE, fig.height=4.5, fig.width=4.5}
 x <- runif(100, 0, 6); y <- x + rnorm(100,  mean = 0, sd = .001 * x); 
-plot(x, y); abline(lm(y ~ x))
+g = ggplot(data.frame(x = x, y = y), aes(x = x, y = y))
+g = g + geom_smooth(method = "lm", colour = "black")
+g = g + geom_point(size = 7, colour = "black", alpha = 0.4)
+g = g + geom_point(size = 5, colour = "red", alpha = 0.4)
+g
 ```
 
 ---
 ## Getting rid of the blank space can be helpful
 ```{r, echo = TRUE, fig.height=4.5, fig.width=4.5}
-plot(x, resid(lm(y ~ x))); 
-abline(h = 0)
+g = ggplot(data.frame(x = x, y = resid(lm(y ~ x))),
+           aes(x = x, y = y))
+g = g + geom_hline(yintercept = 0, size = 2);
+g = g + geom_point(size = 7, colour = "black", alpha = 0.4)
+g = g + geom_point(size = 5, colour = "red", alpha = 0.4)
+g = g + xlab("X") + ylab("Residual")
+g
+```
+---
+##Running Residual Plot on Diamond Data
+```{r, echo = FALSE, fig.height=4.5, fig.width=4.5}
+
+diamond$e <- resid(lm(price ~ carat, data=diamond))
+g = ggplot(diamond, aes(x = carat, y = e))
+g = g + xlab("Mass (carats)")
+g = g + ylab("Residual price (SIN $)")
+g = g + geom_hline(yintercept = 0, size =2)
+g = g + geom_point(size = 7, colour = "black", alpha=0.5)
+g = g + geom_point(size = 5, colour = "blue", alpha=0.2)
+g
+```
+
+---
+##Diamond data residual plot
+```{r, echo = FALSE, fig.height=4.5, fig.width=4.5}
+e = c(resid(lm(price ~ 1, data = diamond)),
+      resid(lm(price ~ carat, data = diamond)))
+fit = factor(c(rep("Itc", nrow(diamond)),
+               rep("Itc, slope", nrow(diamond))))
+g = ggplot(data.frame(e = e, fit = fit), aes(y = e, x = fit, fill = fit))
+g = g + geom_dotplot(binaxis = "y", dotsize = 2, stackdir = "center", binwidth = 15)
+g = g + xlab("Fitting approach")
+g = g + ylab("Residual price")
+g
 ```
 
 ---