Week 04 clean up more

Week 04/house_prices.Rmd

@@ -274,7 +274,7 @@ stargazer(fit_08, intercept.bottom = FALSE, single.row = TRUE, type = "text")
 
 Visualizing the model coefficients and their standard errors is often more intuitive than starring at regression tables. The `coefplot` function allows to easily produce high quality plots of model coefficients.
 
-Here, we plot the coefficients of the `OverallQual` dummy variables.
+Here, we plot the coefficients of the `OverallQual` dummy variables in model `fit_04`.
 
 ```{r}
 coefplot(fit_04, intercept = FALSE)
@@ -285,7 +285,7 @@ coefplot(fit_04, intercept = FALSE)
 
 Likewise, a plot of a model's response as a function of selected explanatory variables can help to extract new knowledge from a model. The `plotmo` package offers a great variety of model plotting features, including, for example, 3D model surface plots. Unfortunately, the package does not build on top of `ggplot2` and, hence, the plots are less visually appealing.
 
-Let's first go back to model `fit_08` and visualize the non-linear effect of `GrLivArea` on `SalePrice`.
+Let's visualize the non-linear effect of `GrLivArea` on `SalePrice` in model `fit_08`.
 
 ```{r}
 plotmo(fit_08)