diff --git a/Example.ipynb b/Example.ipynb
index e4e190e..b870d84 100644
--- a/Example.ipynb
+++ b/Example.ipynb
@@ -12,10 +12,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 1,
    "id": "unagtd36et9",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/gcskoenig/university/postdoc/software/fippy/.venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -51,7 +59,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 2,
    "id": "g70buecg0cr",
    "metadata": {},
    "outputs": [],
@@ -75,7 +83,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 3,
    "id": "jixurrokr1p",
    "metadata": {},
    "outputs": [
@@ -83,7 +91,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "loo repeats: 100%|██████████| 10/10 [00:04<00:00,  2.14it/s]\n"
+      "loo repeats: 100%|██████████| 10/10 [00:11<00:00,  1.13s/it]\n"
      ]
     },
     {
@@ -119,43 +127,43 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>MedInc</th>\n",
-       "      <td>0.983193</td>\n",
-       "      <td>0.015720</td>\n",
+       "      <td>1.010619</td>\n",
+       "      <td>0.011459</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>HouseAge</th>\n",
-       "      <td>0.087737</td>\n",
-       "      <td>0.005152</td>\n",
+       "      <td>0.086470</td>\n",
+       "      <td>0.003263</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveRooms</th>\n",
-       "      <td>0.050332</td>\n",
-       "      <td>0.002670</td>\n",
+       "      <td>0.050517</td>\n",
+       "      <td>0.003076</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveBedrms</th>\n",
-       "      <td>0.034925</td>\n",
-       "      <td>0.003491</td>\n",
+       "      <td>0.035415</td>\n",
+       "      <td>0.002183</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Population</th>\n",
-       "      <td>0.029846</td>\n",
-       "      <td>0.003811</td>\n",
+       "      <td>0.029757</td>\n",
+       "      <td>0.004251</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveOccup</th>\n",
-       "      <td>0.639702</td>\n",
-       "      <td>0.014052</td>\n",
+       "      <td>0.649712</td>\n",
+       "      <td>0.016526</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Latitude</th>\n",
-       "      <td>0.548656</td>\n",
-       "      <td>0.006349</td>\n",
+       "      <td>0.547909</td>\n",
+       "      <td>0.013289</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Longitude</th>\n",
-       "      <td>0.465232</td>\n",
-       "      <td>0.007624</td>\n",
+       "      <td>0.462036</td>\n",
+       "      <td>0.009765</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -164,17 +172,17 @@
       "text/plain": [
        "            importance       std\n",
        "feature                         \n",
-       "MedInc        0.983193  0.015720\n",
-       "HouseAge      0.087737  0.005152\n",
-       "AveRooms      0.050332  0.002670\n",
-       "AveBedrms     0.034925  0.003491\n",
-       "Population    0.029846  0.003811\n",
-       "AveOccup      0.639702  0.014052\n",
-       "Latitude      0.548656  0.006349\n",
-       "Longitude     0.465232  0.007624"
+       "MedInc        1.010619  0.011459\n",
+       "HouseAge      0.086470  0.003263\n",
+       "AveRooms      0.050517  0.003076\n",
+       "AveBedrms     0.035415  0.002183\n",
+       "Population    0.029757  0.004251\n",
+       "AveOccup      0.649712  0.016526\n",
+       "Latitude      0.547909  0.013289\n",
+       "Longitude     0.462036  0.009765"
       ]
      },
-     "execution_count": 23,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -186,13 +194,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 4,
    "id": "7ijwj84viiq",
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 800x400 with 1 Axes>"
       ]
@@ -207,7 +215,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 5,
    "id": "z3896agkdk9",
    "metadata": {},
    "outputs": [
@@ -246,51 +254,51 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>MedInc</th>\n",
-       "      <td>0.983193</td>\n",
-       "      <td>0.971339</td>\n",
-       "      <td>0.995046</td>\n",
+       "      <td>1.010619</td>\n",
+       "      <td>1.001978</td>\n",
+       "      <td>1.019260</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>HouseAge</th>\n",
-       "      <td>0.087737</td>\n",
-       "      <td>0.083851</td>\n",
-       "      <td>0.091622</td>\n",
+       "      <td>0.086470</td>\n",
+       "      <td>0.084010</td>\n",
+       "      <td>0.088930</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveRooms</th>\n",
-       "      <td>0.050332</td>\n",
-       "      <td>0.048319</td>\n",
-       "      <td>0.052345</td>\n",
+       "      <td>0.050517</td>\n",
+       "      <td>0.048197</td>\n",
+       "      <td>0.052836</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveBedrms</th>\n",
-       "      <td>0.034925</td>\n",
-       "      <td>0.032293</td>\n",
-       "      <td>0.037558</td>\n",
+       "      <td>0.035415</td>\n",
+       "      <td>0.033769</td>\n",
+       "      <td>0.037061</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Population</th>\n",
-       "      <td>0.029846</td>\n",
-       "      <td>0.026972</td>\n",
-       "      <td>0.032719</td>\n",
+       "      <td>0.029757</td>\n",
+       "      <td>0.026552</td>\n",
+       "      <td>0.032963</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveOccup</th>\n",
-       "      <td>0.639702</td>\n",
-       "      <td>0.629106</td>\n",
-       "      <td>0.650298</td>\n",
+       "      <td>0.649712</td>\n",
+       "      <td>0.637251</td>\n",
+       "      <td>0.662174</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Latitude</th>\n",
-       "      <td>0.548656</td>\n",
-       "      <td>0.543868</td>\n",
-       "      <td>0.553443</td>\n",
+       "      <td>0.547909</td>\n",
+       "      <td>0.537889</td>\n",
+       "      <td>0.557930</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Longitude</th>\n",
-       "      <td>0.465232</td>\n",
-       "      <td>0.459483</td>\n",
-       "      <td>0.470980</td>\n",
+       "      <td>0.462036</td>\n",
+       "      <td>0.454672</td>\n",
+       "      <td>0.469399</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -299,17 +307,17 @@
       "text/plain": [
        "            importance     lower     upper\n",
        "feature                                   \n",
-       "MedInc        0.983193  0.971339  0.995046\n",
-       "HouseAge      0.087737  0.083851  0.091622\n",
-       "AveRooms      0.050332  0.048319  0.052345\n",
-       "AveBedrms     0.034925  0.032293  0.037558\n",
-       "Population    0.029846  0.026972  0.032719\n",
-       "AveOccup      0.639702  0.629106  0.650298\n",
-       "Latitude      0.548656  0.543868  0.553443\n",
-       "Longitude     0.465232  0.459483  0.470980"
+       "MedInc        1.010619  1.001978  1.019260\n",
+       "HouseAge      0.086470  0.084010  0.088930\n",
+       "AveRooms      0.050517  0.048197  0.052836\n",
+       "AveBedrms     0.035415  0.033769  0.037061\n",
+       "Population    0.029757  0.026552  0.032963\n",
+       "AveOccup      0.649712  0.637251  0.662174\n",
+       "Latitude      0.547909  0.537889  0.557930\n",
+       "Longitude     0.462036  0.454672  0.469399"
       ]
      },
-     "execution_count": 25,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -321,7 +329,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 6,
    "id": "35ktorh5igj",
    "metadata": {},
    "outputs": [
@@ -360,51 +368,51 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>MedInc</th>\n",
-       "      <td>0.983193</td>\n",
-       "      <td>48.980050</td>\n",
+       "      <td>1.010619</td>\n",
+       "      <td>49.950671</td>\n",
        "      <td>0.000000e+00</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>HouseAge</th>\n",
-       "      <td>0.087737</td>\n",
-       "      <td>14.297275</td>\n",
-       "      <td>1.081111e-44</td>\n",
+       "      <td>0.086470</td>\n",
+       "      <td>14.520800</td>\n",
+       "      <td>4.963070e-46</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveRooms</th>\n",
-       "      <td>0.050332</td>\n",
-       "      <td>16.341071</td>\n",
-       "      <td>1.307575e-57</td>\n",
+       "      <td>0.050517</td>\n",
+       "      <td>16.869801</td>\n",
+       "      <td>3.384111e-61</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveBedrms</th>\n",
-       "      <td>0.034925</td>\n",
-       "      <td>14.534917</td>\n",
-       "      <td>4.079602e-46</td>\n",
+       "      <td>0.035415</td>\n",
+       "      <td>14.882055</td>\n",
+       "      <td>3.118742e-48</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Population</th>\n",
-       "      <td>0.029846</td>\n",
-       "      <td>9.297043</td>\n",
-       "      <td>9.119397e-20</td>\n",
+       "      <td>0.029757</td>\n",
+       "      <td>9.887909</td>\n",
+       "      <td>3.361651e-22</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveOccup</th>\n",
-       "      <td>0.639702</td>\n",
-       "      <td>41.267508</td>\n",
-       "      <td>0.000000e+00</td>\n",
+       "      <td>0.649712</td>\n",
+       "      <td>40.999026</td>\n",
+       "      <td>5.892189e-308</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Latitude</th>\n",
-       "      <td>0.548656</td>\n",
-       "      <td>43.148839</td>\n",
+       "      <td>0.547909</td>\n",
+       "      <td>43.676626</td>\n",
        "      <td>0.000000e+00</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Longitude</th>\n",
-       "      <td>0.465232</td>\n",
-       "      <td>37.150954</td>\n",
-       "      <td>2.807604e-260</td>\n",
+       "      <td>0.462036</td>\n",
+       "      <td>37.494587</td>\n",
+       "      <td>1.909839e-264</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -413,17 +421,17 @@
       "text/plain": [
        "            importance  statistic        p_value\n",
        "feature                                         \n",
-       "MedInc        0.983193  48.980050   0.000000e+00\n",
-       "HouseAge      0.087737  14.297275   1.081111e-44\n",
-       "AveRooms      0.050332  16.341071   1.307575e-57\n",
-       "AveBedrms     0.034925  14.534917   4.079602e-46\n",
-       "Population    0.029846   9.297043   9.119397e-20\n",
-       "AveOccup      0.639702  41.267508   0.000000e+00\n",
-       "Latitude      0.548656  43.148839   0.000000e+00\n",
-       "Longitude     0.465232  37.150954  2.807604e-260"
+       "MedInc        1.010619  49.950671   0.000000e+00\n",
+       "HouseAge      0.086470  14.520800   4.963070e-46\n",
+       "AveRooms      0.050517  16.869801   3.384111e-61\n",
+       "AveBedrms     0.035415  14.882055   3.118742e-48\n",
+       "Population    0.029757   9.887909   3.361651e-22\n",
+       "AveOccup      0.649712  40.999026  5.892189e-308\n",
+       "Latitude      0.547909  43.676626   0.000000e+00\n",
+       "Longitude     0.462036  37.494587  1.909839e-264"
       ]
      },
-     "execution_count": 26,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -445,7 +453,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 7,
    "id": "jwdm1ciy59",
    "metadata": {},
    "outputs": [
@@ -453,7 +461,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "loo repeats: 100%|██████████| 10/10 [00:05<00:00,  1.97it/s]\n"
+      "loo repeats: 100%|██████████| 10/10 [00:11<00:00,  1.13s/it]\n"
      ]
     },
     {
@@ -489,43 +497,43 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>MedInc</th>\n",
-       "      <td>0.364206</td>\n",
-       "      <td>0.010589</td>\n",
+       "      <td>0.363590</td>\n",
+       "      <td>0.015302</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>HouseAge</th>\n",
-       "      <td>0.074690</td>\n",
-       "      <td>0.004705</td>\n",
+       "      <td>0.069607</td>\n",
+       "      <td>0.004295</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveRooms</th>\n",
-       "      <td>0.025262</td>\n",
-       "      <td>0.001877</td>\n",
+       "      <td>0.024443</td>\n",
+       "      <td>0.002114</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveBedrms</th>\n",
-       "      <td>0.020005</td>\n",
-       "      <td>0.002436</td>\n",
+       "      <td>0.020562</td>\n",
+       "      <td>0.001304</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Population</th>\n",
-       "      <td>0.030496</td>\n",
-       "      <td>0.003527</td>\n",
+       "      <td>0.029385</td>\n",
+       "      <td>0.004353</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>AveOccup</th>\n",
-       "      <td>0.645351</td>\n",
-       "      <td>0.018404</td>\n",
+       "      <td>0.649379</td>\n",
+       "      <td>0.013847</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Latitude</th>\n",
-       "      <td>0.236018</td>\n",
-       "      <td>0.007338</td>\n",
+       "      <td>0.235190</td>\n",
+       "      <td>0.008187</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Longitude</th>\n",
-       "      <td>0.240721</td>\n",
-       "      <td>0.005821</td>\n",
+       "      <td>0.239665</td>\n",
+       "      <td>0.007626</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -534,17 +542,17 @@
       "text/plain": [
        "            importance       std\n",
        "feature                         \n",
-       "MedInc        0.364206  0.010589\n",
-       "HouseAge      0.074690  0.004705\n",
-       "AveRooms      0.025262  0.001877\n",
-       "AveBedrms     0.020005  0.002436\n",
-       "Population    0.030496  0.003527\n",
-       "AveOccup      0.645351  0.018404\n",
-       "Latitude      0.236018  0.007338\n",
-       "Longitude     0.240721  0.005821"
+       "MedInc        0.363590  0.015302\n",
+       "HouseAge      0.069607  0.004295\n",
+       "AveRooms      0.024443  0.002114\n",
+       "AveBedrms     0.020562  0.001304\n",
+       "Population    0.029385  0.004353\n",
+       "AveOccup      0.649379  0.013847\n",
+       "Latitude      0.235190  0.008187\n",
+       "Longitude     0.239665  0.007626"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -556,13 +564,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 8,
    "id": "0myn6kb14a2",
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 800x400 with 1 Axes>"
       ]
@@ -587,7 +595,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 9,
    "id": "c61ig7bjfrq",
    "metadata": {},
    "outputs": [
@@ -679,7 +687,7 @@
        "Longitude     0.098352  0.0"
       ]
      },
-     "execution_count": 29,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -696,7 +704,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 10,
    "id": "bfoh3j0x6nd",
    "metadata": {},
    "outputs": [
@@ -737,7 +745,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "id": "ke2qtx2f6er",
    "metadata": {},
    "outputs": [
@@ -745,8 +753,100 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "permutations:  12%|█▏        | 6/50 [00:23<02:53,  3.94s/it]"
+      "permutations: 100%|██████████| 50/50 [03:41<00:00,  4.44s/it]\n"
      ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>importance</th>\n",
+       "      <th>std</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>feature</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>MedInc</th>\n",
+       "      <td>0.633797</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>HouseAge</th>\n",
+       "      <td>0.034321</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AveRooms</th>\n",
+       "      <td>0.041751</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AveBedrms</th>\n",
+       "      <td>0.009760</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Population</th>\n",
+       "      <td>0.009580</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AveOccup</th>\n",
+       "      <td>0.247910</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Latitude</th>\n",
+       "      <td>0.146486</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Longitude</th>\n",
+       "      <td>0.124346</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            importance  std\n",
+       "feature                    \n",
+       "MedInc        0.633797  0.0\n",
+       "HouseAge      0.034321  0.0\n",
+       "AveRooms      0.041751  0.0\n",
+       "AveBedrms     0.009760  0.0\n",
+       "Population    0.009580  0.0\n",
+       "AveOccup      0.247910  0.0\n",
+       "Latitude      0.146486  0.0\n",
+       "Longitude     0.124346  0.0"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -758,10 +858,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "id": "yd50a6oienq",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/gcskoenig/university/postdoc/software/fippy/.venv/lib/python3.11/site-packages/numpy/_core/_methods.py:219: RuntimeWarning: Degrees of freedom <= 0 for slice\n",
+      "  ret = _var(a, axis=axis, dtype=dtype, out=out, ddof=ddof,\n",
+      "/Users/gcskoenig/university/postdoc/software/fippy/.venv/lib/python3.11/site-packages/numpy/_core/_methods.py:208: RuntimeWarning: invalid value encountered in divide\n",
+      "  ret = um.true_divide(\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "result_msage.hbarplot(figsize=(8, 4));"
    ]
@@ -778,10 +899,110 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "id": "f9pdiciqo7n",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "permutations: 100%|██████████| 50/50 [03:53<00:00,  4.67s/it]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>importance</th>\n",
+       "      <th>std</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>feature</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>MedInc</th>\n",
+       "      <td>0.525191</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>HouseAge</th>\n",
+       "      <td>0.041323</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AveRooms</th>\n",
+       "      <td>0.095334</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AveBedrms</th>\n",
+       "      <td>0.036779</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Population</th>\n",
+       "      <td>0.011276</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AveOccup</th>\n",
+       "      <td>0.240177</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Latitude</th>\n",
+       "      <td>0.161467</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Longitude</th>\n",
+       "      <td>0.134007</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            importance  std\n",
+       "feature                    \n",
+       "MedInc        0.525191  0.0\n",
+       "HouseAge      0.041323  0.0\n",
+       "AveRooms      0.095334  0.0\n",
+       "AveBedrms     0.036779  0.0\n",
+       "Population    0.011276  0.0\n",
+       "AveOccup      0.240177  0.0\n",
+       "Latitude      0.161467  0.0\n",
+       "Longitude     0.134007  0.0"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "result_csage = explainer.sage(\n",
     "    X_test, y_test, distribution=\"conditional\", n_samples=10, n_repeats=1, n_permutations=50\n",
@@ -791,10 +1012,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "id": "7pgo1femsqb",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/gcskoenig/university/postdoc/software/fippy/.venv/lib/python3.11/site-packages/numpy/_core/_methods.py:219: RuntimeWarning: Degrees of freedom <= 0 for slice\n",
+      "  ret = _var(a, axis=axis, dtype=dtype, out=out, ddof=ddof,\n",
+      "/Users/gcskoenig/university/postdoc/software/fippy/.venv/lib/python3.11/site-packages/numpy/_core/_methods.py:208: RuntimeWarning: invalid value encountered in divide\n",
+      "  ret = um.true_divide(\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "result_csage.hbarplot(figsize=(8, 4));"
    ]
@@ -811,10 +1053,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "id": "e94gkhea8f9",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1400x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "import matplotlib.pyplot as plt\n",
     "\n",
@@ -834,10 +1087,103 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "id": "4h58i2649r4",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>importance</th>\n",
+       "      <th>std</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>feature</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>MedInc</th>\n",
+       "      <td>1.010619</td>\n",
+       "      <td>0.011459</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>HouseAge</th>\n",
+       "      <td>0.086470</td>\n",
+       "      <td>0.003263</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AveRooms</th>\n",
+       "      <td>0.050517</td>\n",
+       "      <td>0.003076</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AveBedrms</th>\n",
+       "      <td>0.035415</td>\n",
+       "      <td>0.002183</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Population</th>\n",
+       "      <td>0.029757</td>\n",
+       "      <td>0.004251</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AveOccup</th>\n",
+       "      <td>0.649712</td>\n",
+       "      <td>0.016526</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Latitude</th>\n",
+       "      <td>0.547909</td>\n",
+       "      <td>0.013289</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Longitude</th>\n",
+       "      <td>0.462036</td>\n",
+       "      <td>0.009765</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            importance       std\n",
+       "feature                         \n",
+       "MedInc        1.010619  0.011459\n",
+       "HouseAge      0.086470  0.003263\n",
+       "AveRooms      0.050517  0.003076\n",
+       "AveBedrms     0.035415  0.002183\n",
+       "Population    0.029757  0.004251\n",
+       "AveOccup      0.649712  0.016526\n",
+       "Latitude      0.547909  0.013289\n",
+       "Longitude     0.462036  0.009765"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "result_pfi.to_csv(\"/tmp/pfi_result.csv\")\n",
     "\n",
@@ -849,7 +1195,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -863,7 +1209,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.11.15"
   }
  },
  "nbformat": 4,
diff --git a/README.md b/README.md
index 72a7810..06ac47a 100644
--- a/README.md
+++ b/README.md
@@ -5,7 +5,9 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 [![Python](https://img.shields.io/pypi/pyversions/fippy)](https://pypi.org/project/fippy/)
 
-A Python package for model-agnostic feature importance with statistical inference. Fippy implements a unified framework where feature importance methods are composed from three orthogonal axes:
+A Python package for model-agnostic feature importance with support for conditional sampling and statistical inference. Includes PFI, CFI, RFI, LOCO, and SAGE, along with hypothesis tests for individual feature relevance and confidence intervals for importance estimates.
+
+All existing methods quantify feature importance by measuring how removing a feature from the model affects the prediction loss, but they differ across three axes: **attribution** concerns how credit is assigned across features, **restriction** determines how a feature is removed, and **distribution** specifies which reference distribution replacement values are drawn from.
 
 | Axis | Options | Description |
 |---|---|---|
@@ -13,7 +15,19 @@ A Python package for model-agnostic feature importance with statistical inferenc
 | **Restriction** | `resample`, `marginalize`, `refit` | How the removed feature is handled |
 | **Distribution** | `marginal`, `conditional` | Which distribution replacement values are drawn from |
 
-This gives rise to well-known methods as special cases:
+For example, LOO importance with resampling from the conditional distribution (i.e. CFI):
+
+```python
+from fippy import Explainer
+from fippy.samplers import GaussianSampler
+from fippy.losses import squared_error
+
+sampler = GaussianSampler(X_train)
+explainer = Explainer(model.predict, X_train, loss=squared_error, sampler=sampler)
+result = explainer.loo(X_test, y_test, "resample", distribution="conditional")
+```
+
+Based on that logic, the package also offers convenience functions for popular methods:
 
 | Method | Attribution | Restriction | Distribution | Alias |
 |---|---|---|---|---|
@@ -23,6 +37,26 @@ This gives rise to well-known methods as special cases:
 | LOCO | loo | refit | — | `loco()` |
 | SAGE | shapley | marginalize | marginal or conditional | `sage()` |
 
+All methods return an `ExplanationResult`, which provides built-in tools for inference and visualization:
+
+- **`importance()`** — mean importance per feature with standard deviations
+- **`ci()`** — confidence intervals (t-based or quantile-based)
+- **`test()`** — hypothesis tests for individual feature relevance (t-test or Wilcoxon signed-rank test) with multiple testing correction
+- **`hbarplot()`** — horizontal bar plot of importances with confidence intervals
+
+LOO methods support parallelization over features via the `n_jobs` parameter.
+
+## Contents
+
+- [Installation](#installation)
+- [Quick start](#quick-start)
+- [Samplers](#samplers)
+- [Feature groups](#feature-groups)
+- [Plotting](#plotting)
+- [Statistical inference](#statistical-inference)
+- [Serialization](#serialization)
+- [Disclaimer](#disclaimer)
+
 ## Installation
 
 Requires Python >= 3.11.
@@ -124,29 +158,27 @@ All convenience methods are shortcuts for `loo()` and `shapley()`:
 result = explainer.loo(X_test, y_test, "resample", distribution="marginal")
 ```
 
-## Statistical inference
+## Samplers
 
-`ExplanationResult` provides built-in inference on the importance scores.
+| Sampler | Distribution | Description |
+|---|---|---|
+| `PermutationSampler` | marginal | Draws from training marginal (used automatically) |
+| `GaussianSampler` | conditional | Multivariate Gaussian conditional P(X_J \| X_S) |
 
-```python
-# Mean importance with standard deviation
-result.importance()
+Additional samplers (regression-based, ARF, TabPFN) are planned.
 
-# Confidence intervals (t-based or quantile-based)
-result.ci(alpha=0.05, method="t")
+## Feature groups
 
-# Hypothesis test H0: importance_j <= 0
-result.test(method="t", alternative="greater", p_adjust="bonferroni")
+Features can be grouped and assessed jointly:
 
-# Observation-wise importance scores
-result.obs_importance()
+```python
+# As a dict
+explainer.pfi(X_test, y_test, features={"size": ["width", "height"], "color": ["r", "g", "b"]})
 
-# Relative importance (as fraction of baseline loss)
-result.importance(relative=True)
+# As a list (each element becomes one group)
+explainer.pfi(X_test, y_test, features=["width", "height", "color"])
 ```
 
-Multiple testing corrections: `"bonferroni"`, `"holm"`, `"bh"` (Benjamini-Hochberg).
-
 ## Plotting
 
 Visualize results with horizontal bar plots showing confidence intervals:
@@ -165,26 +197,28 @@ fig.tight_layout()
 
 See `Example.ipynb` for a complete walkthrough with plots.
 
-## Feature groups
+## Statistical inference
 
-Features can be grouped and assessed jointly:
+`ExplanationResult` provides built-in inference on the importance scores.
 
 ```python
-# As a dict
-explainer.pfi(X_test, y_test, features={"size": ["width", "height"], "color": ["r", "g", "b"]})
+# Mean importance with standard deviation
+result.importance()
 
-# As a list (each element becomes one group)
-explainer.pfi(X_test, y_test, features=["width", "height", "color"])
-```
+# Confidence intervals (t-based or quantile-based)
+result.ci(alpha=0.05, method="t")
 
-## Samplers
+# Hypothesis test H0: importance_j <= 0
+result.test(method="t", alternative="greater", p_adjust="bonferroni")
 
-| Sampler | Distribution | Description |
-|---|---|---|
-| `PermutationSampler` | marginal | Draws from training marginal (used automatically) |
-| `GaussianSampler` | conditional | Multivariate Gaussian conditional P(X_J \| X_S) |
+# Observation-wise importance scores
+result.obs_importance()
 
-Additional samplers (regression-based, ARF, TabPFN) are planned.
+# Relative importance (as fraction of baseline loss)
+result.importance(relative=True)
+```
+
+Multiple testing corrections: `"bonferroni"`, `"holm"`, `"bh"` (Benjamini-Hochberg).
 
 ## Serialization
 
@@ -194,10 +228,8 @@ from fippy import ExplanationResult
 loaded = ExplanationResult.from_csv("importance.csv")
 ```
 
-## Status
+## Disclaimer
 
 The package is under active development. The core API is stable, but additional samplers and cross-validation features are planned.
 
-## References
-
 The package was previously called `rfi` and accompanies our paper on Relative Feature Importance: [[arXiv]](https://arxiv.org/abs/2007.08283)