diff --git a/README.md b/README.md
index ebca4c4..37f5c2f 100644
--- a/README.md
+++ b/README.md
@@ -323,7 +323,7 @@ style="width:100.0%" />
 
 The first set of data `variation_causal_quartet` demonstrates that you
 can get the same average treatment effect despite variability across
-some pre-treatment characteristic (here called `z`).
+some pre-treatment characteristic (here called `covariate`).
 
 ``` r
 ggplot(variation_causal_quartet, aes(x = covariate, y = outcome, color = factor(exposure))) + 
diff --git a/README.qmd b/README.qmd
index fdac89d..1e22f8c 100644
--- a/README.qmd
+++ b/README.qmd
@@ -254,7 +254,7 @@ plot(pd_tree, pd_nn, pd_rf, pd_lin)
 
 ## Gelman Variation and Heterogeneity Causal Quartets
 
-The first set of data `variation_causal_quartet` demonstrates that you can get the same average treatment effect despite variability across some pre-treatment characteristic (here called `z`).
+The first set of data `variation_causal_quartet` demonstrates that you can get the same average treatment effect despite variability across some pre-treatment characteristic (here called `covariate`).
 
 ```{r}
 ggplot(variation_causal_quartet, aes(x = covariate, y = outcome, color = factor(exposure))) +