diff --git a/notebooks/Linear Regression/LR_1_1.ipynb b/notebooks/Linear Regression/LR_1_1.ipynb
index 2177fc7205ca7c8cda20b94bacc943ecabfa3cfd..7b737aa3613df8730c71f6c31f44f255a5bc0eae 100644
--- a/notebooks/Linear Regression/LR_1_1.ipynb	
+++ b/notebooks/Linear Regression/LR_1_1.ipynb	
@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "id": "6f6db233-fde7-4956-8255-c57e7df7c883",
    "metadata": {
     "tags": []
@@ -53,12 +53,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
    "id": "1be60c67-e837-4780-8bb2-cb7f550172ef",
    "metadata": {
     "tags": []
    },
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Matplotlib is building the font cache; this may take a moment.\n"
+     ]
+    },
     {
      "data": {
       "image/png": "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",
diff --git a/notebooks/Linear Regression/LR_3_4.ipynb b/notebooks/Linear Regression/LR_3_4.ipynb
index 72d81a5efacaa1552a0e82148d3bc53f76285a31..5a080753726168c00565917b4d6ca87402f8a97d 100644
--- a/notebooks/Linear Regression/LR_3_4.ipynb	
+++ b/notebooks/Linear Regression/LR_3_4.ipynb	
@@ -10,12 +10,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "9bb1b649-f875-4d02-9790-6e40e7e3b2e1",
    "metadata": {
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING (pytensor.tensor.blas): Using NumPy C-API based implementation for BLAS functions.\n"
+     ]
+    }
+   ],
    "source": [
     "import arviz as az\n",
     "import matplotlib.pyplot as plt\n",
@@ -29,7 +37,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "095e0fa1-8435-4f17-a5f1-2a29b9814f9e",
    "metadata": {
     "tags": []
@@ -59,7 +67,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "1643bd8e-cb22-4fa0-b75d-f3ba8b2bd708",
    "metadata": {
     "tags": []
@@ -104,7 +112,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Sampling 4 chains for 1_000 tune and 1_000 draw iterations (4_000 + 4_000 draws total) took 59 seconds.\n"
+      "Sampling 4 chains for 1_000 tune and 1_000 draw iterations (4_000 + 4_000 draws total) took 7 seconds.\n"
      ]
     }
    ],
@@ -125,7 +133,10 @@
    "source": [
     "- Es handelt sich um ein Modell für normalverteilte Daten, allerdings wird der Erwartungswert als eine lineare Funktion des TV-Werbebudgets modelliert. Der Achsenabschnitt ist $\\beta_0$ und die Steigung ist $\\beta_1$. Die Standardabweichung für das Rauschen ist $\\sigma$ und der Erwartungswert ist $\\mu$\n",
     "\n",
-    "- $\\mu$ wird als `Deterministic` Variable definiert. Es handelt sich hier nicht um eine Zufallsvariable, sondern um eine deterministische Variable, welche aus dem Achsenabschnitt, der Steigung und dem TV-Werbebudget bestimmt wird. Wir definieren die Variable als `Deterministic`, da wir später in `InferenceData` darauf zurückgreifen möchten. Wir hätten auch einfach $\\mu = \\beta_0 + \\beta_1 * werbung.TV$ oder $ \\_= pm.Normal(`y\\_pred`, mu=\\beta_0 + \\beta_1 * werbung.TV)$ schreiben können. Das Modell wäre dasselbe gewesen, allerdings wird $\\mu$ in diesem Fall nicht in `InferenceData` gespeichert \n",
+    "- $\\mu$ wird als `Deterministic` Variable definiert. Es handelt sich hier nicht um eine Zufallsvariable, sondern um eine deterministische Variable, welche aus dem Achsenabschnitt, der Steigung und dem TV-Werbebudget bestimmt wird. Wir definieren die Variable als `Deterministic`, da wir später in `InferenceData` darauf zurückgreifen möchten. Wir hätten auch einfach \n",
+    "\n",
+    "`mu = beta_0 + beta_1 * werbung.TV` oder \n",
+    "` mu= pm.Normal(`y_pred`, mu=beta_0 + beta_1 * werbung.TV)` schreiben können. Das Modell wäre dasselbe gewesen, allerdings wird $\\mu$ in diesem Fall nicht in `InferenceData` gespeichert \n",
     "\n",
     "- $\\mu$ ist ein Vektor mit derselben Länge wie `werbung.TV`"
    ]
@@ -140,7 +151,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 5,
    "id": "d162896e-2012-4436-b0be-b37b9e75f0b2",
    "metadata": {
     "tags": []
@@ -162,81 +173,81 @@
        "<polygon fill=\"white\" stroke=\"transparent\" points=\"-4,4 -4,-339.86 326.5,-339.86 326.5,4 -4,4\"/>\n",
        "<g id=\"clust1\" class=\"cluster\">\n",
        "<title>cluster200</title>\n",
-       "<path fill=\"none\" stroke=\"black\" d=\"M54.5,-8C54.5,-8 160.5,-8 160.5,-8 166.5,-8 172.5,-14 172.5,-20 172.5,-20 172.5,-209.93 172.5,-209.93 172.5,-215.93 166.5,-221.93 160.5,-221.93 160.5,-221.93 54.5,-221.93 54.5,-221.93 48.5,-221.93 42.5,-215.93 42.5,-209.93 42.5,-209.93 42.5,-20 42.5,-20 42.5,-14 48.5,-8 54.5,-8\"/>\n",
-       "<text text-anchor=\"middle\" x=\"150.5\" y=\"-15.8\" font-family=\"Times,serif\" font-size=\"14.00\">200</text>\n",
+       "<path fill=\"none\" stroke=\"black\" d=\"M162,-8C162,-8 268,-8 268,-8 274,-8 280,-14 280,-20 280,-20 280,-209.93 280,-209.93 280,-215.93 274,-221.93 268,-221.93 268,-221.93 162,-221.93 162,-221.93 156,-221.93 150,-215.93 150,-209.93 150,-209.93 150,-20 150,-20 150,-14 156,-8 162,-8\"/>\n",
+       "<text text-anchor=\"middle\" x=\"258\" y=\"-15.8\" font-family=\"Times,serif\" font-size=\"14.00\">200</text>\n",
        "</g>\n",
-       "<!-- beta_1 -->\n",
+       "<!-- sigma -->\n",
        "<g id=\"node1\" class=\"node\">\n",
-       "<title>beta_1</title>\n",
-       "<ellipse fill=\"none\" stroke=\"black\" cx=\"49.5\" cy=\"-298.38\" rx=\"49.49\" ry=\"37.45\"/>\n",
-       "<text text-anchor=\"middle\" x=\"49.5\" y=\"-309.68\" font-family=\"Times,serif\" font-size=\"14.00\">beta_1</text>\n",
-       "<text text-anchor=\"middle\" x=\"49.5\" y=\"-294.68\" font-family=\"Times,serif\" font-size=\"14.00\">~</text>\n",
-       "<text text-anchor=\"middle\" x=\"49.5\" y=\"-279.68\" font-family=\"Times,serif\" font-size=\"14.00\">Normal</text>\n",
+       "<title>sigma</title>\n",
+       "<ellipse fill=\"none\" stroke=\"black\" cx=\"70\" cy=\"-187.43\" rx=\"70.01\" ry=\"37.45\"/>\n",
+       "<text text-anchor=\"middle\" x=\"70\" y=\"-198.73\" font-family=\"Times,serif\" font-size=\"14.00\">sigma</text>\n",
+       "<text text-anchor=\"middle\" x=\"70\" y=\"-183.73\" font-family=\"Times,serif\" font-size=\"14.00\">~</text>\n",
+       "<text text-anchor=\"middle\" x=\"70\" y=\"-168.73\" font-family=\"Times,serif\" font-size=\"14.00\">HalfCauchy</text>\n",
        "</g>\n",
-       "<!-- mu -->\n",
+       "<!-- y_pred -->\n",
        "<g id=\"node4\" class=\"node\">\n",
-       "<title>mu</title>\n",
-       "<polygon fill=\"none\" stroke=\"black\" points=\"164.5,-213.93 50.5,-213.93 50.5,-160.93 164.5,-160.93 164.5,-213.93\"/>\n",
-       "<text text-anchor=\"middle\" x=\"107.5\" y=\"-198.73\" font-family=\"Times,serif\" font-size=\"14.00\">mu</text>\n",
-       "<text text-anchor=\"middle\" x=\"107.5\" y=\"-183.73\" font-family=\"Times,serif\" font-size=\"14.00\">~</text>\n",
-       "<text text-anchor=\"middle\" x=\"107.5\" y=\"-168.73\" font-family=\"Times,serif\" font-size=\"14.00\">Deterministic</text>\n",
+       "<title>y_pred</title>\n",
+       "<ellipse fill=\"lightgrey\" stroke=\"black\" cx=\"211\" cy=\"-76.48\" rx=\"49.49\" ry=\"37.45\"/>\n",
+       "<text text-anchor=\"middle\" x=\"211\" y=\"-87.78\" font-family=\"Times,serif\" font-size=\"14.00\">y_pred</text>\n",
+       "<text text-anchor=\"middle\" x=\"211\" y=\"-72.78\" font-family=\"Times,serif\" font-size=\"14.00\">~</text>\n",
+       "<text text-anchor=\"middle\" x=\"211\" y=\"-57.78\" font-family=\"Times,serif\" font-size=\"14.00\">Normal</text>\n",
        "</g>\n",
-       "<!-- beta_1&#45;&gt;mu -->\n",
-       "<g id=\"edge1\" class=\"edge\">\n",
-       "<title>beta_1&#45;&gt;mu</title>\n",
-       "<path fill=\"none\" stroke=\"black\" d=\"M67.69,-263.21C74.48,-250.45 82.19,-235.96 89.01,-223.16\"/>\n",
-       "<polygon fill=\"black\" stroke=\"black\" points=\"92.18,-224.65 93.79,-214.18 86,-221.36 92.18,-224.65\"/>\n",
+       "<!-- sigma&#45;&gt;y_pred -->\n",
+       "<g id=\"edge3\" class=\"edge\">\n",
+       "<title>sigma&#45;&gt;y_pred</title>\n",
+       "<path fill=\"none\" stroke=\"black\" d=\"M109.28,-156.08C127.74,-141.82 149.77,-124.79 168.6,-110.24\"/>\n",
+       "<polygon fill=\"black\" stroke=\"black\" points=\"170.96,-112.84 176.73,-103.96 166.68,-107.3 170.96,-112.84\"/>\n",
        "</g>\n",
        "<!-- beta_0 -->\n",
        "<g id=\"node2\" class=\"node\">\n",
        "<title>beta_0</title>\n",
-       "<ellipse fill=\"none\" stroke=\"black\" cx=\"166.5\" cy=\"-298.38\" rx=\"49.49\" ry=\"37.45\"/>\n",
-       "<text text-anchor=\"middle\" x=\"166.5\" y=\"-309.68\" font-family=\"Times,serif\" font-size=\"14.00\">beta_0</text>\n",
-       "<text text-anchor=\"middle\" x=\"166.5\" y=\"-294.68\" font-family=\"Times,serif\" font-size=\"14.00\">~</text>\n",
-       "<text text-anchor=\"middle\" x=\"166.5\" y=\"-279.68\" font-family=\"Times,serif\" font-size=\"14.00\">Normal</text>\n",
+       "<ellipse fill=\"none\" stroke=\"black\" cx=\"156\" cy=\"-298.38\" rx=\"49.49\" ry=\"37.45\"/>\n",
+       "<text text-anchor=\"middle\" x=\"156\" y=\"-309.68\" font-family=\"Times,serif\" font-size=\"14.00\">beta_0</text>\n",
+       "<text text-anchor=\"middle\" x=\"156\" y=\"-294.68\" font-family=\"Times,serif\" font-size=\"14.00\">~</text>\n",
+       "<text text-anchor=\"middle\" x=\"156\" y=\"-279.68\" font-family=\"Times,serif\" font-size=\"14.00\">Normal</text>\n",
+       "</g>\n",
+       "<!-- mu -->\n",
+       "<g id=\"node5\" class=\"node\">\n",
+       "<title>mu</title>\n",
+       "<polygon fill=\"none\" stroke=\"black\" points=\"272,-213.93 158,-213.93 158,-160.93 272,-160.93 272,-213.93\"/>\n",
+       "<text text-anchor=\"middle\" x=\"215\" y=\"-198.73\" font-family=\"Times,serif\" font-size=\"14.00\">mu</text>\n",
+       "<text text-anchor=\"middle\" x=\"215\" y=\"-183.73\" font-family=\"Times,serif\" font-size=\"14.00\">~</text>\n",
+       "<text text-anchor=\"middle\" x=\"215\" y=\"-168.73\" font-family=\"Times,serif\" font-size=\"14.00\">Deterministic</text>\n",
        "</g>\n",
        "<!-- beta_0&#45;&gt;mu -->\n",
-       "<g id=\"edge2\" class=\"edge\">\n",
+       "<g id=\"edge1\" class=\"edge\">\n",
        "<title>beta_0&#45;&gt;mu</title>\n",
-       "<path fill=\"none\" stroke=\"black\" d=\"M148.15,-263.51C141.18,-250.64 133.24,-235.97 126.24,-223.04\"/>\n",
-       "<polygon fill=\"black\" stroke=\"black\" points=\"129.17,-221.1 121.33,-213.97 123.01,-224.43 129.17,-221.1\"/>\n",
+       "<path fill=\"none\" stroke=\"black\" d=\"M174.35,-263.51C181.32,-250.64 189.26,-235.97 196.26,-223.04\"/>\n",
+       "<polygon fill=\"black\" stroke=\"black\" points=\"199.49,-224.43 201.17,-213.97 193.33,-221.1 199.49,-224.43\"/>\n",
        "</g>\n",
-       "<!-- sigma -->\n",
+       "<!-- beta_1 -->\n",
        "<g id=\"node3\" class=\"node\">\n",
-       "<title>sigma</title>\n",
-       "<ellipse fill=\"none\" stroke=\"black\" cx=\"252.5\" cy=\"-187.43\" rx=\"70.01\" ry=\"37.45\"/>\n",
-       "<text text-anchor=\"middle\" x=\"252.5\" y=\"-198.73\" font-family=\"Times,serif\" font-size=\"14.00\">sigma</text>\n",
-       "<text text-anchor=\"middle\" x=\"252.5\" y=\"-183.73\" font-family=\"Times,serif\" font-size=\"14.00\">~</text>\n",
-       "<text text-anchor=\"middle\" x=\"252.5\" y=\"-168.73\" font-family=\"Times,serif\" font-size=\"14.00\">HalfCauchy</text>\n",
-       "</g>\n",
-       "<!-- y_pred -->\n",
-       "<g id=\"node5\" class=\"node\">\n",
-       "<title>y_pred</title>\n",
-       "<ellipse fill=\"lightgrey\" stroke=\"black\" cx=\"111.5\" cy=\"-76.48\" rx=\"49.49\" ry=\"37.45\"/>\n",
-       "<text text-anchor=\"middle\" x=\"111.5\" y=\"-87.78\" font-family=\"Times,serif\" font-size=\"14.00\">y_pred</text>\n",
-       "<text text-anchor=\"middle\" x=\"111.5\" y=\"-72.78\" font-family=\"Times,serif\" font-size=\"14.00\">~</text>\n",
-       "<text text-anchor=\"middle\" x=\"111.5\" y=\"-57.78\" font-family=\"Times,serif\" font-size=\"14.00\">Normal</text>\n",
+       "<title>beta_1</title>\n",
+       "<ellipse fill=\"none\" stroke=\"black\" cx=\"273\" cy=\"-298.38\" rx=\"49.49\" ry=\"37.45\"/>\n",
+       "<text text-anchor=\"middle\" x=\"273\" y=\"-309.68\" font-family=\"Times,serif\" font-size=\"14.00\">beta_1</text>\n",
+       "<text text-anchor=\"middle\" x=\"273\" y=\"-294.68\" font-family=\"Times,serif\" font-size=\"14.00\">~</text>\n",
+       "<text text-anchor=\"middle\" x=\"273\" y=\"-279.68\" font-family=\"Times,serif\" font-size=\"14.00\">Normal</text>\n",
        "</g>\n",
-       "<!-- sigma&#45;&gt;y_pred -->\n",
-       "<g id=\"edge4\" class=\"edge\">\n",
-       "<title>sigma&#45;&gt;y_pred</title>\n",
-       "<path fill=\"none\" stroke=\"black\" d=\"M213.22,-156.08C194.77,-141.82 172.73,-124.79 153.9,-110.24\"/>\n",
-       "<polygon fill=\"black\" stroke=\"black\" points=\"155.82,-107.3 145.77,-103.96 151.54,-112.84 155.82,-107.3\"/>\n",
+       "<!-- beta_1&#45;&gt;mu -->\n",
+       "<g id=\"edge2\" class=\"edge\">\n",
+       "<title>beta_1&#45;&gt;mu</title>\n",
+       "<path fill=\"none\" stroke=\"black\" d=\"M254.81,-263.21C248.02,-250.45 240.31,-235.96 233.49,-223.16\"/>\n",
+       "<polygon fill=\"black\" stroke=\"black\" points=\"236.5,-221.36 228.71,-214.18 230.32,-224.65 236.5,-221.36\"/>\n",
        "</g>\n",
        "<!-- mu&#45;&gt;y_pred -->\n",
-       "<g id=\"edge3\" class=\"edge\">\n",
+       "<g id=\"edge4\" class=\"edge\">\n",
        "<title>mu&#45;&gt;y_pred</title>\n",
-       "<path fill=\"none\" stroke=\"black\" d=\"M108.44,-160.89C108.84,-149.98 109.32,-136.89 109.78,-124.35\"/>\n",
-       "<polygon fill=\"black\" stroke=\"black\" points=\"113.29,-124.12 110.16,-114 106.29,-123.87 113.29,-124.12\"/>\n",
+       "<path fill=\"none\" stroke=\"black\" d=\"M214.07,-160.89C213.67,-149.98 213.18,-136.89 212.72,-124.35\"/>\n",
+       "<polygon fill=\"black\" stroke=\"black\" points=\"216.21,-123.87 212.34,-114 209.21,-124.12 216.21,-123.87\"/>\n",
        "</g>\n",
        "</g>\n",
        "</svg>\n"
       ],
       "text/plain": [
-       "<graphviz.graphs.Digraph at 0x7f7096448d00>"
+       "<graphviz.graphs.Digraph at 0x7f7c1ebe3430>"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -246,7 +257,7 @@
     "# Die Graphik kann gespeichert werden:\n",
     "# gv = pm.model_to_graphviz(model_lb)\n",
     "# gv.format = 'png'\n",
-    "#gv.render(filename='model_graph')"
+    "# gv.render(filename='model_graph')"
    ]
   },
   {
@@ -259,7 +270,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 6,
    "id": "cd6f5f29-49eb-49a4-a88f-4952bef8fbc4",
    "metadata": {
     "tags": []
@@ -289,7 +300,7 @@
    "id": "08301477-189c-4fa1-a5e9-45012fb16768",
    "metadata": {},
    "source": [
-    "- Damit wir nicht für jeden Wert von \\Rcom{werbung.TV} einen Graphen generieren, spezifizieren wir mittels des Arguments `var_names=[\"~ mu\"]`, dass wir die Variable $\\mu$ ausschliessen (negieren). Alternativ könnten wir auch die Variablen, für welche wir einen Posterior Plot erstellen möchten, als Liste angeben: `var_names=[\"beta_0\", \"beta_1\", \"sigma\"]`"
+    "- Damit wir nicht für jeden Wert von `werbung.TV` einen Graphen generieren, spezifizieren wir mittels des Arguments `var_names=[\"~ mu\"]`, dass wir die Variable $\\mu$ ausschliessen (negieren). Alternativ könnten wir auch die Variablen, für welche wir einen Posterior Plot erstellen möchten, als Liste angeben: `var_names=[\"beta_0\", \"beta_1\", \"sigma\"]`"
    ]
   },
   {
diff --git a/notebooks/Linear Regression/LR_3_5.ipynb b/notebooks/Linear Regression/LR_3_5.ipynb
index 8ef132682a5aa23368bdb93cee796d8eeca33844..56787b205a4097c4328f91eb2f8b82d51ef98633 100644
--- a/notebooks/Linear Regression/LR_3_5.ipynb	
+++ b/notebooks/Linear Regression/LR_3_5.ipynb	
@@ -152,7 +152,7 @@
    "source": [
     "- Die Funktion `az.extract` fügt die Dimensionen von `chain` und `draw` in einer `sample` Dimension zusammen. Falls wir zum Beispiel `chains=4` und `draws=1000` haben, ergibt dies 4000 samples. Dies wird für die weitere Bearbeitung von Bedeutung sein.\n",
     "\n",
-    "- Wir benützen das `num_samples` Argument, um eine Teilstichprobe von der Posterior-Verteilung zu entnehmen. `az.extract` operiert auf der Posterior-Gruppe. Falls Informationen von einer anderen Gruppe benötigt wird, kann dies mit Hilfe des `group` Arguments spezifiziert werden.\n",
+    "- Wir benützen das `num_samples` Argument, um eine Teilstichprobe von der Posterior-Verteilung zu entnehmen. `az.extract` operiert auf der Posterior-Gruppe. Falls Informationen von einer anderen Gruppe benötigt werden, kann dies mit Hilfe des `group` Arguments spezifiziert werden.\n",
     "\n",
     "- Wir definieren ein `DataArray` mit dem Namen `x_plot`, welches gleich grosse Intervalle zwischen dem Minimum und Maximum von `TV` macht. Hier sind es 50 Intervalle.\n",
     "\n",