Fix typo

Signed-off-by: Nathaniel <NathanielF@users.noreply.github.com>

Author: NathanielF

examples/case_studies/bayesian_sem_workflow.ipynb

@@ -2792,7 +2792,7 @@
    "id": "6de4795b",
    "metadata": {},
    "source": [
-    "The sampler diagnostics suggest that the model is having trouble samplng from the B matrix. This is a little concern because arguably the structural relations are the primary parameters of interest in the SEM setting. Anything which undercuts our confidence in their estimation, undermines the whole modelling exercise."
+    "The sampler diagnostics suggest that the model is having trouble samplng from the B matrix. This is a little concerning because the structural relations are the primary parameters of interest in the SEM setting. Anything which undercuts our confidence in their estimation, undermines the whole modelling exercise."
    ]
   },
   {
@@ -2823,6 +2823,14 @@
     "\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f0aae228",
+   "metadata": {},
+   "source": [
+    "where we have finally added structure to the residuals of the multivariate normal outcome by imposing a non-zero covariance relation between `UF1` and `FOR`."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 19,

examples/case_studies/bayesian_sem_workflow.myst.md

@@ -745,7 +745,7 @@ However, the model diagnostics appear less robust. The sampler seemed to have di
 plot_diagnostics(idata_sem_model_v1, parameters);
 ```
 
-The sampler diagnostics suggest that the model is having trouble samplng from the B matrix. This is a little concern because arguably the structural relations are the primary parameters of interest in the SEM setting. Anything which undercuts our confidence in their estimation, undermines the whole modelling exercise.
+The sampler diagnostics suggest that the model is having trouble samplng from the B matrix. This is a little concerning because the structural relations are the primary parameters of interest in the SEM setting. Anything which undercuts our confidence in their estimation, undermines the whole modelling exercise.
 
 +++
 
@@ -771,6 +771,10 @@ JS  ~ CTS + DTP + SWB
 ```
 
 
++++
+
+where we have finally added structure to the residuals of the multivariate normal outcome by imposing a non-zero covariance relation between `UF1` and `FOR`.
+
 ```{code-cell} ipython3
 with pm.Model(coords=coords) as sem_model_v2: