remove .names.repair warnings

Author: edarin

tutorials/workflow/populationModel_workfow.Rmd renamed to tutorials/workflow/populationModel_workflow.Rmd

@@ -489,7 +489,7 @@ In practice, the hierarchy has little impact in this controlled environment (the
 
 Finally we can implement the goodness-of-fit check that was commonly used in the tutorials: the observed vs predicted plot at cluster level.
 
-```{r}
+```{r, message=F, warning=F}
 # New validation: cluster-based
 comp_obs_poisson_lognormal_hierarchical_cp <- as_tibble(samples_poisson_lognormal_hierarchical_cp$pop_post_pred) %>% 
   summarise(across(
@@ -602,7 +602,7 @@ We see a gain in goodness-of-fit for the low values of population counts, due to
 
 A more thorough analysis can be undertaken by comparing the residuals from the two models.
 
-```{r}
+```{r, message=FALSE, warning=F}
 # validation metrics based on residuals
 comp_obs_poisson_lognormal_hierarchical_var <- as_tibble(samples_poisson_lognormal_hierarchical_var$pop_post_pred) %>% 
   summarise(across(
@@ -676,7 +676,7 @@ fit_poisson_lognormal_hierarchical_nclp <- stan(
 )
 ```
 
-We can plot the estimated parameters by adding the deviation $delta_{settlement}$ to the baseline, {alpha_{national}}:
+We can plot the estimated parameters by adding the deviation $delta_{settlement}$ to the baseline, $alpha_{national}$:
 
 ```{r}
 samples_poisson_lognormal_hierarchical_nclp<- rstan::extract(fit_poisson_lognormal_hierarchical_nclp)