fix formatting of conclusions

Author: OriolAbril

examples/generalized_linear_models/GLM-robust-with-outlier-detection.ipynb

@@ -1076,7 +1076,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "PLot posterior joint distribution"
+    "Plot posterior joint distribution"
    ]
   },
   {
@@ -2026,22 +2026,22 @@
    "source": [
     "**Observe**:\n",
     "\n",
-    "##### The posterior preditive fit for:\n",
+    "The posterior preditive fit for:\n",
     "+ the **OLS model** is shown in **Green** and as expected, it doesn't appear to fit the majority of our datapoints very well, skewed by outliers\n",
     "+ the **Student-T model** is shown in **Orange** and does appear to fit the 'main axis' of datapoints quite well, ignoring outliers\n",
     "+ the **Hogg Signal vs Noise model** is shown in two parts:\n",
     "    + **Blue** for inliers fits the 'main axis' of datapoints well, ignoring outliers\n",
     "    + **Red** for outliers has a very large variance and has assigned 'outlier' points with more log likelihood than the Blue inlier model \n",
     "    \n",
     "    \n",
-    "##### We see that the **Hogg Signal vs Noise model** also yields specific estimates of _which_ datapoints are outliers:\n",
+    "We see that the **Hogg Signal vs Noise model** also yields specific estimates of _which_ datapoints are outliers:\n",
     "+ 17 'inlier' datapoints, in **Blue** and\n",
     "+ 3 'outlier' datapoints shown in **Red**.\n",
     "+ From a simple visual inspection, the classification seems fair, and agrees with Jake Vanderplas' findings.\n",
     "+ I've annotated these Red and the most outlying inliers to aid visual investigation\n",
     "    \n",
     "    \n",
-    "##### Overall:\n",
+    "Overall:\n",
     "+ the **Hogg Signal vs Noise model** behaves as promised, yielding a robust regression estimate and explicit labelling of inliers / outliers, but\n",
     "+ the **Hogg Signal vs Noise model** is quite complex, and whilst the regression seems robust, the traceplot shoes many divergences, and the model is potentially unstable\n",
     "+ if you simply want a robust regression without inlier / outlier labelling, the **Student-T model** may be a good compromise, offering a simple model, quick sampling, and a very similar estimate."