fix reference error

docs/profiles.html

@@ -159,7 +159,7 @@ <h3><span class="header-section-number">5.2.1</span> Clusters<a href="profiles.h
 </div>
 <div id="xgboost-model" class="section level3 hasAnchor" number="5.2.2">
 <h3><span class="header-section-number">5.2.2</span> XGBoost model<a href="profiles.html#xgboost-model" class="anchor-section" aria-label="Anchor link to header"></a></h3>
-<p>The model’s predictive capacity was quantitatively assessed via receiver operating characteristic (ROC) analysis across five distinct clusters. The ROC curves (see [ML model interpretation][simple]) illustrate a differential capacity of the model to classify each cluster based on the nutritional profiles derived from various fishing strategies. Cluster 2 and 5 demonstrated superior model performance, indicated by a curve proximate to the top-left, suggesting high sensitivity and specificity. Clusters 1 and 4 showed marginally lower but comparable discrimination ability. Cluster 3 indicated a slight decrease in sensitivity and exhibited the model’s lowest performance, with a curve markedly farther from the ideal top-left position. Collectively, an aggregate AUC of 0.87 signifies a strong overall ability of the model to differentiate between the clusters, albeit with varying degrees of precision. These findings underscore the model’s effectiveness in predicting nutritional outcomes based on fishing strategies, with implications for tailoring nutrient-sensitive fisheries management interventions.</p>
+<p>The model’s predictive capacity was quantitatively assessed via receiver operating characteristic (ROC) analysis across five distinct clusters. The ROC curves (see <a href="simple.html#simple">ML model interpretation</a>) illustrate a differential capacity of the model to classify each cluster based on the nutritional profiles derived from various fishing strategies. Cluster 2 and 5 demonstrated superior model performance, indicated by a curve proximate to the top-left, suggesting high sensitivity and specificity. Clusters 1 and 4 showed marginally lower but comparable discrimination ability. Cluster 3 indicated a slight decrease in sensitivity and exhibited the model’s lowest performance, with a curve markedly farther from the ideal top-left position. Collectively, an aggregate AUC of 0.87 signifies a strong overall ability of the model to differentiate between the clusters, albeit with varying degrees of precision. These findings underscore the model’s effectiveness in predicting nutritional outcomes based on fishing strategies, with implications for tailoring nutrient-sensitive fisheries management interventions.</p>
 <div class="figure"><span style="display:block;" id="fig:model-settings"></span>
 <img src="Timor-nutrient-sensitive-fisheries-management_files/figure-html/model-settings-1.png" alt="Receiver Operating Characteristic (ROC) Curves with Data Points for Cluster-Based Classification. The curves delineate the sensitivity versus 1-specificity for the five clusters derived from the XGBoost classification model. Each cluster is represented by a distinct color with data points marked, which illustrates the true positive rate against the false positive rate for each respective cluster. The closeness of each curve to the top-left corner indicates the model’s classification efficacy per cluster, with Cluster 1 and 2 showing the highest performance. The overall model demonstrates substantial predictive accuracy with a composite AUC value of 0.86." width="576" />
 <p class="caption">
@@ -197,7 +197,7 @@ <h2><span class="header-section-number">5.4</span> Next steps<a href="profiles.h
 <p>Explore the model:</p>
 <ul>
 <li><p>Quantify the importance of each predictor on the model outcome</p></li>
-<li><p>Assess the direction of the effect of each predictor, that is analyze which features have the most impact on driving predictions towards each cluster. [SHAP Values][simple] are a good way to address that.</p></li>
+<li><p>Assess the direction of the effect of each predictor, that is analyze which features have the most impact on driving predictions towards each cluster. <a href="simple.html#simple">SHAP Values</a> are a good way to address that.</p></li>
 </ul>
 
 </div>

docs_book/04-profiles.Rmd

@@ -87,7 +87,7 @@ clusterdf %>%
 
 ### XGBoost model
 
-The model's predictive capacity was quantitatively assessed via receiver operating characteristic (ROC) analysis across five distinct clusters. The ROC curves (see [ML model interpretation][simple]) illustrate a differential capacity of the model to classify each cluster based on the nutritional profiles derived from various fishing strategies. Cluster 2 and 5 demonstrated superior model performance, indicated by a curve proximate to the top-left, suggesting high sensitivity and specificity. Clusters 1 and 4 showed marginally lower but comparable discrimination ability. Cluster 3 indicated a slight decrease in sensitivity and exhibited the model's lowest performance, with a curve markedly farther from the ideal top-left position. Collectively, an aggregate AUC of 0.87 signifies a strong overall ability of the model to differentiate between the clusters, albeit with varying degrees of precision. These findings underscore the model's effectiveness in predicting nutritional outcomes based on fishing strategies, with implications for tailoring nutrient-sensitive fisheries management interventions.
+The model's predictive capacity was quantitatively assessed via receiver operating characteristic (ROC) analysis across five distinct clusters. The ROC curves (see [ML model interpretation][In simple terms]) illustrate a differential capacity of the model to classify each cluster based on the nutritional profiles derived from various fishing strategies. Cluster 2 and 5 demonstrated superior model performance, indicated by a curve proximate to the top-left, suggesting high sensitivity and specificity. Clusters 1 and 4 showed marginally lower but comparable discrimination ability. Cluster 3 indicated a slight decrease in sensitivity and exhibited the model's lowest performance, with a curve markedly farther from the ideal top-left position. Collectively, an aggregate AUC of 0.87 signifies a strong overall ability of the model to differentiate between the clusters, albeit with varying degrees of precision. These findings underscore the model's effectiveness in predicting nutritional outcomes based on fishing strategies, with implications for tailoring nutrient-sensitive fisheries management interventions.
 
 ```{r model-settings, echo=FALSE, fig.cap="Receiver Operating Characteristic (ROC) Curves with Data Points for Cluster-Based Classification. The curves delineate the sensitivity versus 1-specificity for the five clusters derived from the XGBoost classification model. Each cluster is represented by a distinct color with data points marked, which illustrates the true positive rate against the false positive rate for each respective cluster. The closeness of each curve to the top-left corner indicates the model’s classification efficacy per cluster, with Cluster 1 and 2 showing the highest performance. The overall model demonstrates substantial predictive accuracy with a composite AUC value of 0.86.", fig.height=5, fig.width=6, message=FALSE, warning=FALSE}
 df_field <-
@@ -282,4 +282,4 @@ Explore the model:
 
 -   Quantify the importance of each predictor on the model outcome
 
--   Assess the direction of the effect of each predictor, that is analyze which features have the most impact on driving predictions towards each cluster. [SHAP Values][simple] are a good way to address that.
+-   Assess the direction of the effect of each predictor, that is analyze which features have the most impact on driving predictions towards each cluster. [SHAP Values][In simple terms] are a good way to address that.