update readme

README.Rmd

@@ -313,11 +313,11 @@ model <- mgcv::gam(Sepal.Width ~ s(Petal.Length), data = iris)
 deriv <- estimate_slopes(model,
   trend = "Petal.Length",
   by = "Petal.Length",
-  length = 100
+  length = 200
 )
 
 # 2. Visualize predictions and derivative
-plot(estimate_relation(model, length = 100)) /
+plot(estimate_relation(model, length = 200)) /
   plot(deriv) +
   geom_hline(yintercept = 0, linetype = "dashed")
 ```
@@ -360,7 +360,7 @@ Also referred to as **Johnson-Neyman intervals**, this plot shows how the effect
 
 For instance, the plot below shows that the effect of `hp` (the y-axis) is significantly negative only when `wt` is low (`< ~4`).
 
-```{r eval=FALSE}
+```{r}
 model <- lm(mpg ~ hp * wt, data = mtcars)
 
 slopes <- estimate_slopes(model, trend = "hp", by = "wt", length = 200)

README.md

@@ -429,11 +429,11 @@ model <- mgcv::gam(Sepal.Width ~ s(Petal.Length), data = iris)
 deriv <- estimate_slopes(model,
   trend = "Petal.Length",
   by = "Petal.Length",
-  length = 100
+  length = 200
 )
 
 # 2. Visualize predictions and derivative
-plot(estimate_relation(model, length = 100)) /
+plot(estimate_relation(model, length = 200)) /
   plot(deriv) +
   geom_hline(yintercept = 0, linetype = "dashed")
 ```
@@ -501,6 +501,8 @@ slopes <- estimate_slopes(model, trend = "hp", by = "wt", length = 200)
 plot(slopes)
 ```
 
+<img src="man/figures/unnamed-chunk-13-1.png" width="100%" />
+
 ### Visualize predictions with random effects
 
 Aside from plotting the coefficient of each random effect (as done