diff --git a/session-2-intuition/intuition.ipynb b/session-2-intuition/intuition.ipynb
new file mode 100644
index 0000000..f54adc1
--- /dev/null
+++ b/session-2-intuition/intuition.ipynb
@@ -0,0 +1,758 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "2392afbf",
+   "metadata": {},
+   "source": [
+    "# Week 2 Lab (Jupyter) — Descriptive Stats + Sampling Variability + Bootstrap\n",
+    "**Course focus:** Descriptive statistics (center/spread/shape) + population vs sample + sampling variability  \n",
+    "**Lab focus:** Bootstrap intuition (mean vs median) + why estimates “move” + effect of sample size \\(n\\)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "9c041bc5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([ 0.00123015,  0.29874554, -0.27413786])"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Cell 1 — Imports + settings\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "rng = np.random.default_rng(7)\n",
+    "rng.normal(size=3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cfba4554",
+   "metadata": {},
+   "source": [
+    "## Example 1 — Descriptive statistics (center, spread, shape)\n",
+    "We’ll compute: mean/median, SD/variance, IQR, five-number summary, and flag outliers using the 1.5×IQR rule."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "784c7898",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(0    3.567780\n",
+       " 1    1.159428\n",
+       " 2    1.668679\n",
+       " 3    1.543439\n",
+       " 4    4.254155\n",
+       " Name: x, dtype: float64,\n",
+       " count    60.000000\n",
+       " mean      3.999189\n",
+       " std       5.105683\n",
+       " min       0.512643\n",
+       " 25%       1.657953\n",
+       " 50%       2.505819\n",
+       " 75%       4.258704\n",
+       " max      36.847101\n",
+       " Name: x, dtype: float64)"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Cell 2 — Build a dataset with skew + an outlier\n",
+    "n = 60\n",
+    "x = rng.lognormal(mean=1.0, sigma=0.6, size=n)  # right-skewed\n",
+    "x[-1] *= 10  # inject outlier\n",
+    "x = pd.Series(x, name=\"x\")\n",
+    "\n",
+    "x.head(),x.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "45e74326",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "({'min': np.float64(0.5126428223213325),\n",
+       "  'Q1': np.float64(1.657952864334265),\n",
+       "  'median': np.float64(2.5058190123666924),\n",
+       "  'Q3': np.float64(4.258704400008809),\n",
+       "  'max': np.float64(36.84710076013428)},\n",
+       " np.float64(2.600751535674544),\n",
+       " (np.float64(-2.2431744391775514), np.float64(8.159831703520625)))"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Cell 3 — Five-number summary + IQR + outlier fences\n",
+    "q1 = x.quantile(0.25)\n",
+    "q3 = x.quantile(0.75)\n",
+    "iqr = q3 - q1\n",
+    "\n",
+    "lower_fence = q1 - 1.5 * iqr\n",
+    "upper_fence = q3 + 1.5 * iqr\n",
+    "\n",
+    "five_num = {\n",
+    "    \"min\": x.min(),\n",
+    "    \"Q1\": q1,\n",
+    "    \"median\": x.median(),\n",
+    "    \"Q3\": q3,\n",
+    "    \"max\": x.max(),\n",
+    "}\n",
+    "five_num, iqr, (lower_fence, upper_fence)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "ace3d784",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "({'mean': np.float64(3.999188799394666),\n",
+       "  'median': np.float64(2.5058190123666924),\n",
+       "  'std': np.float64(5.105682866634222),\n",
+       "  'var': np.float64(26.067997534642245),\n",
+       "  'IQR': np.float64(2.600751535674544),\n",
+       "  'n_outliers': 4},\n",
+       " 13    13.336209\n",
+       " 25    11.128763\n",
+       " 45    13.372176\n",
+       " 59    36.847101\n",
+       " Name: x, dtype: float64)"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Cell 4 — Identify outliers + summary of center/spread\n",
+    "outliers = x[(x < lower_fence) | (x > upper_fence)]\n",
+    "summary = {\n",
+    "    \"mean\": x.mean(),\n",
+    "    \"median\": x.median(),\n",
+    "    \"std\": x.std(ddof=1),\n",
+    "    \"var\": x.var(ddof=1),\n",
+    "    \"IQR\": iqr,\n",
+    "    \"n_outliers\": len(outliers),\n",
+    "}\n",
+    "summary, outliers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "dc88300e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Cell 5 — Visual diagnostics: histogram + boxplot\n",
+    "plt.figure()\n",
+    "plt.hist(x, bins=25)\n",
+    "plt.title(\"Histogram (skew + outlier)\")\n",
+    "plt.xlabel(\"x\"); plt.ylabel(\"count\")\n",
+    "plt.show()\n",
+    "\n",
+    "plt.figure()\n",
+    "plt.boxplot(x, vert=False, showmeans=True)\n",
+    "plt.title(\"Boxplot (shows outliers)\")\n",
+    "plt.ylabel(\"x\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d350a5c9",
+   "metadata": {},
+   "source": [
+    "## Example 2 — Sampling variability: why estimates “move”\n",
+    "We create a *population* (known distribution), then repeatedly take random samples and compute the sample mean.\n",
+    "We compare how variability changes for different sample sizes \\(n\\)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "f53b9065",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(np.float64(3.246809305332583), np.float64(2.1294506397257105))"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Cell 6 — Define a population (large synthetic population)\n",
+    "# (Treat this as the \"true\" population we are sampling from.)\n",
+    "population = rng.lognormal(mean=1.0, sigma=0.6, size=200_000)\n",
+    "pop_mu = population.mean()\n",
+    "pop_sd = population.std(ddof=0)\n",
+    "\n",
+    "pop_mu, pop_sd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "9b895975",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(np.float64(0.6432811001722105),\n",
+       " np.float64(0.30330130600629723),\n",
+       " np.float64(0.14896614310477774))"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Cell 7 — Repeated sampling experiment\n",
+    "def repeated_sampling_means(pop, n, R=3000, rng=7):\n",
+    "    means = np.empty(R)\n",
+    "    for r in range(R):\n",
+    "        sample = rng.choice(pop, size=n, replace=False)\n",
+    "        means[r] = sample.mean()\n",
+    "    return means\n",
+    "\n",
+    "R = 300\n",
+    "means_n10  = repeated_sampling_means(population, n=10,  R=R, rng=rng)\n",
+    "means_n50  = repeated_sampling_means(population, n=50,  R=R, rng=rng)\n",
+    "means_n200 = repeated_sampling_means(population, n=200, R=R, rng=rng)\n",
+    "means_n10\n",
+    "np.std(means_n10, ddof=1), np.std(means_n50, ddof=1), np.std(means_n200, ddof=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "4526ebf1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Cell 8 — Plot sampling distributions of the mean for different n\n",
+    "bins = 10\n",
+    "plt.figure()\n",
+    "plt.hist(means_n10, bins=bins)\n",
+    "plt.axvline(pop_mu)\n",
+    "plt.title(\"Sampling distribution of mean (n=10)\")\n",
+    "plt.xlabel(\"sample mean\"); plt.ylabel(\"count\")\n",
+    "plt.show()\n",
+    "\n",
+    "plt.figure()\n",
+    "plt.hist(means_n50, bins=bins)\n",
+    "plt.axvline(pop_mu)\n",
+    "plt.title(\"Sampling distribution of mean (n=50)\")\n",
+    "plt.xlabel(\"sample mean\"); plt.ylabel(\"count\")\n",
+    "plt.show()\n",
+    "\n",
+    "plt.figure()\n",
+    "plt.hist(means_n200, bins=bins)\n",
+    "plt.axvline(pop_mu)\n",
+    "plt.title(\"Sampling distribution of mean (n=200)\")\n",
+    "plt.xlabel(\"sample mean\"); plt.ylabel(\"count\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "383c11d5",
+   "metadata": {},
+   "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>n</th>\n",
+       "      <th>SD of sample means (empirical SE)</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>10</td>\n",
+       "      <td>0.643281</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>50</td>\n",
+       "      <td>0.303301</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>200</td>\n",
+       "      <td>0.148966</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     n  SD of sample means (empirical SE)\n",
+       "0   10                           0.643281\n",
+       "1   50                           0.303301\n",
+       "2  200                           0.148966"
+      ]
+     },
+     "execution_count": 58,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Cell 9 — Quick table: variability vs n (empirical standard error)\n",
+    "se_table = pd.DataFrame({\n",
+    "    \"n\": [10, 50, 200],\n",
+    "    \"SD of sample means (empirical SE)\": [\n",
+    "        np.std(means_n10, ddof=1),\n",
+    "        np.std(means_n50, ddof=1),\n",
+    "        np.std(means_n200, ddof=1),\n",
+    "    ]\n",
+    "})\n",
+    "se_table"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6d9064f2",
+   "metadata": {},
+   "source": [
+    "## Example 3 — Bootstrap intuition: mean vs median (with an outlier)\n",
+    "Bootstrap = resample *with replacement* from the observed sample to approximate sampling variability."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "31905223",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Cell 10 — Bootstrap function\n",
+    "def bootstrap_statistic(x, stat_fn, B=5000, rng=None):\n",
+    "    if rng is None:\n",
+    "        rng = np.random.default_rng()\n",
+    "    x = np.asarray(x)\n",
+    "    n = len(x)\n",
+    "    stats = np.empty(B, dtype=float)\n",
+    "    for b in range(B):\n",
+    "        sample = rng.choice(x, size=n, replace=True)\n",
+    "        stats[b] = stat_fn(sample)\n",
+    "    return stats\n",
+    "\n",
+    "def percentile_ci(samples, alpha=0.05):\n",
+    "    lo = np.quantile(samples, alpha/2)\n",
+    "    hi = np.quantile(samples, 1 - alpha/2)\n",
+    "    return lo, hi"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "id": "b583c4a1",
+   "metadata": {},
+   "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>stat</th>\n",
+       "      <th>point_estimate</th>\n",
+       "      <th>bootstrap_SD</th>\n",
+       "      <th>CI_95_lo</th>\n",
+       "      <th>CI_95_hi</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>mean</td>\n",
+       "      <td>3.999189</td>\n",
+       "      <td>0.648365</td>\n",
+       "      <td>2.964689</td>\n",
+       "      <td>5.471043</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>median</td>\n",
+       "      <td>2.505819</td>\n",
+       "      <td>0.295072</td>\n",
+       "      <td>2.103734</td>\n",
+       "      <td>3.163472</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     stat  point_estimate  bootstrap_SD  CI_95_lo  CI_95_hi\n",
+       "0    mean        3.999189      0.648365  2.964689  5.471043\n",
+       "1  median        2.505819      0.295072  2.103734  3.163472"
+      ]
+     },
+     "execution_count": 66,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Cell 11 — Run bootstrap for mean and median on the observed sample x\n",
+    "B = 5000\n",
+    "boot_mean = bootstrap_statistic(x.values, np.mean, B=B, rng=rng)\n",
+    "boot_med  = bootstrap_statistic(x.values, np.median, B=B, rng=rng)\n",
+    "\n",
+    "mean_ci = percentile_ci(boot_mean, alpha=0.05)\n",
+    "med_ci  = percentile_ci(boot_med,  alpha=0.05)\n",
+    "\n",
+    "pd.DataFrame({\n",
+    "    \"stat\": [\"mean\", \"median\"],\n",
+    "    \"point_estimate\": [x.mean(), x.median()],\n",
+    "    \"bootstrap_SD\": [np.std(boot_mean, ddof=1), np.std(boot_med, ddof=1)],\n",
+    "    \"CI_95_lo\": [mean_ci[0], med_ci[0]],\n",
+    "    \"CI_95_hi\": [mean_ci[1], med_ci[1]],\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "87532376",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjsAAAHHCAYAAABZbpmkAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjgsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvwVt1zgAAAAlwSFlzAAAPYQAAD2EBqD+naQAANZdJREFUeJzt3Ql0FGXa9vE7JBA2k8gakLDvu4IirsgqRMQBXBFQEUcMKEQR4yAKAkF0BHQUxA18BwYHFX0BAZHNhbAqgoAZQBAcSKIgCYskQPo793Pe6q87JEBCkuo8+f/OKTtdVV1dS0tf/WwV5PF4PAIAAGCpEm7vAAAAQEEi7AAAAKsRdgAAgNUIOwAAwGqEHQAAYDXCDgAAsBphBwAAWI2wAwAArEbYAQAAViPsAHDFrFmzJCgoSPbt2+ed16FDBzMVBn3vF154wftc/9Z5v//+e6G8f+3ateWBBx4olPcCijvCDpDly9d3qlKlitxyyy2yZMmSAj9Pb775ptmHvPj888/9vriLk7Vr15pjP3r0qASaQN43oDgJcXsHgEAzbtw4qVOnjuht45KTk00A6dGjhyxcuFBuu+22Ag07lSpVytOvfQ07b7zxRpEPPF988UWeAsXYsWPNeYuIiLjo1/35558SElKw/wSeb98SExOlRAl+bwKFgbADZNG9e3dp27at9/mgQYOkatWq8q9//atAw05hOXPmjGRmZkqpUqUk0BT0PulxZ2RkSOnSpc3kptDQUFffHyhO+FkBXID+Ii9Tpsw5pQAnTpyQJ598UqKioswXV6NGjeSVV14xJUJZw8WLL74o9erVM+tpW41nn31W0tPTvevovO3bt8uaNWu8VWhO25XTp0+b0oEGDRqYL+iKFSvKDTfcIMuXLzfLtdRAS3WUbxWc0vYw+rfu19SpU737sGPHDvOlP2bMGGnTpo2Eh4dLuXLl5MYbb5RVq1b57b/vNqZMmSK1atUy5+Pmm2+WH3/88aI+P3psHTt2NK+rUaOGjB8/3gSPrLJrs/P6669Ls2bNpGzZsnL55ZebIDp37lyzTEuyRo4caf7W0jjn2J12QPr30KFDZc6cOWYbeuxLly71LsuuJEzb7Nx1110SFhZmzvUTTzwhp06dOud8ZFfl6LvNC+1bdm12fv75Z7nzzjulQoUK5nivvfZaWbx4sd86q1evNtv597//LRMmTDDnUz8XnTp1kt27d/ute/LkSfnpp58uqh2SnvfmzZvL1q1bzbXV969fv7589NFHZrl+Ntu1a2euoX7Wv/zyy3O28d///lceeugh8+NAz7We8/fee89vnbx87mbOnOn97F599dWycePGCx4P4IuSHSCL1NRU8+WgoSUlJcV82R4/flzuv/9+7zq67Pbbbzf/QGvJT+vWrWXZsmXmy03/wddQ4Hj44Ydl9uzZ0rdvXxOO1q9fL/Hx8bJz505ZsGCBWUeDyLBhw6R8+fLyt7/9zczTLwznS1PX1+1cc801kpaWJps2bZLvvvtOunTpIn/961/l4MGDJvz8z//8T7bX8/333zdf2I888oj5wtAvU93OO++8I/fee68MHjxYjh07Ju+++65069ZNNmzYYI7J1wcffGDWiYmJMduaNm2aCTDbtm3z7mt2kpKSTLsnDX3PPPOM+XLTLy/90ryQt99+Wx5//HFz7pzQoV/Geg7vu+8+6d27t/znP/8xpW56zrUaUFWuXNm7jZUrV5pgoKFHl2vIOB8NOrqOnvN169bJa6+9Jn/88Yc5/ty4mH3zpVWm1113nQkoeswatPRzo58zDRx/+ctf/NafNGmSqQZ76qmnzGd28uTJ0q9fP3NuHHod9dw///zzF1XFqceppZf33HOPCV3Tp083f2tYHD58uDz66KPmvL/88svmmhw4cEAuu+wy7/5rOHMCph6ntnXT/z/0s6avV7n93Gmw1XX0c67b1uPUc6vBsGTJkrm6JijGPACM999/X4tkzplCQ0M9s2bN8jtLn376qVk2fvx4v/l9+/b1BAUFeXbv3m2eb9myxaz38MMP+6331FNPmfkrV670zmvWrJnn5ptvPudqtGrVyhMdHX3eqxQTE2O2l9XevXvN/LCwME9KSorfsjNnznjS09P95v3xxx+eqlWreh566KFztlGmTBnPr7/+6p2/fv16M3/EiBHn3bfhw4eb9XR9h+5LeHi4ma/bd+jx+56DXr16mfNyPi+//PI523Ho/BIlSni2b9+e7bLnn3/e+1z/1nm3336733qPPfaYmf/DDz/4nQ/9vFxom+fbt1q1ankGDhx4znn6+uuvvfOOHTvmqVOnjqd27dqes2fPmnmrVq0y6zVp0sTv+k2bNs3M37Ztm3ees67vPuVEz7uuO3fuXO+8n376yXsO161b552/bNmyc87BoEGDPNWqVfP8/vvvftu95557zLU+efJknj53FStW9Bw5csQ7/7PPPjPzFy5ceMFjAhxUYwFZaJWQlpLo9M9//tP8MtZSlU8++cSvQXBwcLD5Be5LS270O8/pvaXrqdjY2HPWU1mrKHKqRtNqoF27duX5WvXp0+ecEgXdf6eNjFYpHTlyxJS+aDWRlhpldccdd8gVV1zhfa6lTFqt4RxjTnS5/uLX9R26L1oKcTHH/uuvv15StYVWyTRt2vSi19eSK19a4qYudJyXSrev50irKB1a0qelcVqlo1WPvh588EG/Nk5aFaS0xMO3ako/jxfbcF3fT0tyHFpdpdegSZMm5lo7nL+d99L3+Pjjj6Vnz57mby0ZdSYtsdGSJ+czldvP3d13322qL893nMCFEHaALPQLp3PnzmbSL2QNJPplqUXz2t5A/fLLL1K9enVvEb5DvxSc5c6jVjVo2wdfkZGR5kvEWe9CvcO063LDhg2lRYsWpqpMq3JyQ9uMZEerSVq2bOltC6QhRI9Xv5yy0jZDWek++Y6Tkx09xuxeq1+kFzJq1CjzBazXRLehQeTbb7+V/Dj2nGTdV20rotfwQsd5qfQ8ZXdOsn6mHDVr1vR77gQCrYrKK23/47T3cmi7Gm2XlnWe73v99ttv5jOq1ZP6GfKdNJQprRLOy+euII4TxQ9hB7jQ/yQlSpjSnUOHDuW5dCXrF0hu3HTTTbJnzx7T0FMbkGp7h6uuuso8Xqzs2sdoqZU2kNUvc20zoQ13tTRL2+Fk13jYDfpFr120582bZ0o8tPRAH7UNysW6mLZBubl2OV3Ls2fPSmHSEpLsZG0gnx/bvNB7OZ8XbdfmlIpmna6//vo8fe4K4jhR/NBAGbgIWsyutKGy0h5J2htFG076lu5ozxdnufOo/4BrSHJ+oTuNOfWXsLPehQKRNijWX8g66T5oANKqCa1eu9Brc6KNXuvWrWuq53xfn1OQyC7oaQPcCzX41WPM7rUaYi6GNmjWqgydtGRNG6dqL6S4uDhTMnApQTI7uq++pUHaw0mvoXOcTslC1oECsyuly82+6XnK7pxk/UwFIi2Z0f8PNPBpiWh+fu6A/EDJDnAB2vVbB7vTdgZOYNFBBvUf9n/84x9+62qvG/0HXMfqcdZzelv5evXVV81jdHS035d6diPtHj582O+5VutotZhv13V9rcrNSL3OL2bfX8jakychISHb9T/99FPT08yhPWd0fedYc6LnQHs16foOrfbQHj4XkvXY9RpolaLus16XvB77+Tjd+B3aG085x6ld0rVn1VdffXXOoJBZ5Wbf9DzpOfI9/zq8gVYNadDKTbujvHQ9vxT6WdJ2YVrylt1wBHq9fdfNzecOyA+U7ABZaONi59e0tjPQrq/6a1+7TesXndKGmFq1pd3EtS1Hq1atTCD67LPPTBdbLaJXOn/gwIHmC0u/8LSxrH6haZsFbfCr23DouCPa1VfHoNEwo7eq0KJ9/ZLThqa6XEt4tNu5/jrWNkS+r1XaYFobhOoXim9D0+xoF2P9da1dmjV07d27V2bMmGHezynB8qX7pFVIQ4YMMUFLA5y2t3j66afP+z66XLvE33rrrab7uNP1XEsqLtT2qGvXrqZ9k1aBaPd27a6vAVP31ylRc45dr4Ues3ZH1uvjBI3c0vOg3b11f/ULWKtdtLu1XkuHlqhp12991Ia1Gny0lCur3Oybfr60m7qGKr2Oeq31c6L7oyEiL6Mt57br+aXQ86FDMWjjZe1Srp8jbXysjY61FFT/zsvnDsgX3n5ZQDGXXdfz0qVLe1q3bu2ZPn26JzMz02997Ras3a6rV6/uKVmypKdBgwamq3HW9U6fPu0ZO3as6UKs60VFRXni4uI8p06d8lsvKSnJdDG/7LLLzHs7XbC1e/s111zjiYiIMN2/Gzdu7JkwYYInIyPD+1rtzjts2DBP5cqVTdd3539tp/uu7ldWup8TJ040XaC1e/2VV17pWbRokekOrfMcvtv4+9//bvZf17/xxhu93bEvZOvWreZ49HxeccUVnhdffNHz7rvvXrDr+VtvveW56aabTPdjfc969ep5Ro4c6UlNTfXbvm5Pt6tdpH23qX9rt/zs5NT1fMeOHWYIAb0Ol19+uWfo0KGeP//80++12o1au1prl2pd76677jLd6bPr5p3TvmXteq727Nlj3luvtZ4rve56TXw53cnnz5/vNz+7LvG57XqeXTd/3c/shj7I7twmJyebefoZ0c96ZGSkp1OnTp6ZM2de0ucuu/e+mGMCHEH6n/yJTQBspCVX2oZFB5LTAewAoKihzQ4AALAaYQcAAFiNsAMAAKxGmx0AAGA1SnYAAIDVCDsAAMBqDCr4f/d1OXjwoBmkLL+HngcAAAVDR8/R2/bojZnPO/CmJ0DEx8ebgaKeeOIJ7zwdyOuxxx7zVKhQwVOuXDlP7969zcBrvn755RdPjx49zGBrOqDaU089ZQZxy40DBw6cM5gcE+eAzwCfAT4DfAb4DEiROAf6PX4+AVGys3HjRnnrrbekZcuWfvNHjBghixcvlvnz50t4eLgZHl9vAvjtt9+a5XpvIh1uXIeTX7t2rbkr9YABA8yQ7BMnTrzo93eGnT9w4ID3dgAAACCwpaWlSVRUlN8NmQOyN5beC+Wqq64yN9HTewK1bt3a3HMnNTXV3ElX70vUt29fs67er0hvxKj3q7n22mvNPYz0PitaBaX3zVF6j5VRo0aZG8/pTQMv9mRpmNL3JOwAAFA0XOz3t+sNlGNiYkzpTOfOnf3mb9682dzV2Hd+48aNpWbNmt674+pjixYtvEFH6U0Q9eC3b9+e43vqTQx1Hd8JAADYydVqrHnz5pk74mo1VlZJSUmmZCYiIsJvvgYbXeas4xt0nOXOspzEx8fL2LFj8+koAABAIHOtZEfbxzzxxBMyZ84cKV26dKG+d1xcnCnycibdFwAAYCfXwo5WU6WkpJj2OiEhIWZas2aNvPbaa+ZvLaHJyMiQo0eP+r0uOTnZNEhW+qjPsy53luUkNDTU1O35TgAAwE6uhZ1OnTrJtm3bZMuWLd6pbdu20q9fP+/f2qtqxYoV3tckJibK/v37pX379ua5Puo2NDQ5li9fbsJL06ZNXTkuAAAQWFxrs6PdxJo3b+43r1y5clKxYkXv/EGDBklsbKxUqFDBBJhhw4aZgKM9sVTXrl1NqOnfv79MnjzZtNMZPXq0afSspTcAAAABMc5OTqZMmWJGROzTp4/pQaU9rbSLuiM4OFgWLVokQ4YMMSFIw9LAgQNl3Lhxru43AAAIHK6PsxMIGGcHAICip8iMswMAAFCQCDsAAMBqhB0AAGA1wg4AALAaYQcAAFiNsAMAAKxG2AEAAFYL6EEFAZvVfmZxrtbfNym6wPYFAGxGyQ4AALAaYQcAAFiNsAMAAKxG2AEAAFYj7AAAAKsRdgAAgNUIOwAAwGqEHQAAYDXCDgAAsBphBwAAWI2wAwAArEbYAQAAViPsAAAAqxF2AACA1Qg7AADAaoQdAABgNcIOAACwWojbOwDYpPYzi93eBQBAFpTsAAAAqxF2AACA1Qg7AADAaoQdAABgNcIOAACwGmEHAABYjbADAACsRtgBAABWczXsTJ8+XVq2bClhYWFmat++vSxZssS7vEOHDhIUFOQ3Pfroo37b2L9/v0RHR0vZsmWlSpUqMnLkSDlz5owLRwMAAAKRqyMo16hRQyZNmiQNGjQQj8cjs2fPll69esn3338vzZo1M+sMHjxYxo0b532NhhrH2bNnTdCJjIyUtWvXyqFDh2TAgAFSsmRJmThxoivHBAAAAourYadnz55+zydMmGBKe9atW+cNOxpuNMxk54svvpAdO3bIl19+KVWrVpXWrVvLiy++KKNGjZIXXnhBSpUqVSjHAQAAAlfAtNnRUpp58+bJiRMnTHWWY86cOVKpUiVp3ry5xMXFycmTJ73LEhISpEWLFiboOLp16yZpaWmyffv2Qj8GAAAQeFy/Eei2bdtMuDl16pSUL19eFixYIE2bNjXL7rvvPqlVq5ZUr15dtm7dakpsEhMT5ZNPPjHLk5KS/IKOcp7rspykp6ebyaHhCAAA2Mn1sNOoUSPZsmWLpKamykcffSQDBw6UNWvWmMDzyCOPeNfTEpxq1apJp06dZM+ePVKvXr08v2d8fLyMHTs2n44AAAAEMtersbRdTf369aVNmzYmhLRq1UqmTZuW7brt2rUzj7t37zaP2pYnOTnZbx3neU7tfJRWh2m4cqYDBw7k4xEBAIBA4nrYySozM9OvismXlgApLeFRWv2l1WApKSnedZYvX266sTtVYdkJDQ31dnd3JgAAYCdXq7G0hKV79+5Ss2ZNOXbsmMydO1dWr14ty5YtM1VV+rxHjx5SsWJF02ZnxIgRctNNN5mxeVTXrl1NqOnfv79MnjzZtNMZPXq0xMTEmEADAADgatjREhkdF0fHxwkPDzchRoNOly5dTNWSdimfOnWq6aEVFRUlffr0MWHGERwcLIsWLZIhQ4aYUp5y5cqZNj++4/IA2an9zOKLPjH7JkVzEgGgCHM17Lz77rs5LtNwow2VL0R7a33++ef5vGcAAMAWAddmBwAAID8RdgAAgNUIOwAAwGqEHQAAYDXCDgAAsBphBwAAWI2wAwAArEbYAQAAViPsAAAAqxF2AACA1Qg7AADAaoQdAABgNcIOAACwGmEHAABYjbADAACsRtgBAABWI+wAAACrEXYAAIDVCDsAAMBqhB0AAGA1wg4AALAaYQcAAFgtxO0dAOCu2s8sztX6+yZFF9i+AEBBoGQHAABYjZIdIJ9LPgAAgYWSHQAAYDXCDgAAsBrVWICF1Wk0IgaA/4+SHQAAYDXCDgAAsBphBwAAWI2wAwAArEbYAQAAViPsAAAAqxF2AACA1VwNO9OnT5eWLVtKWFiYmdq3by9LlizxLj916pTExMRIxYoVpXz58tKnTx9JTk7228b+/fslOjpaypYtK1WqVJGRI0fKmTNnXDgaAAAQiFwNOzVq1JBJkybJ5s2bZdOmTdKxY0fp1auXbN++3SwfMWKELFy4UObPny9r1qyRgwcPSu/evb2vP3v2rAk6GRkZsnbtWpk9e7bMmjVLxowZ4+JRAQCAQBLk8Xg8EkAqVKggL7/8svTt21cqV64sc+fONX+rn376SZo0aSIJCQly7bXXmlKg2267zYSgqlWrmnVmzJgho0aNkt9++01KlSp1Ue+ZlpYm4eHhkpqaakqYYD/bb+6ZmxGUc3suGJ0ZQKC42O/vgGmzo6U08+bNkxMnTpjqLC3tOX36tHTu3Nm7TuPGjaVmzZom7Ch9bNGihTfoqG7dupmDd0qHspOenm7W8Z0AAICdXA8727ZtM+1xQkND5dFHH5UFCxZI06ZNJSkpyZTMRERE+K2vwUaXKX30DTrOcmdZTuLj400SdKaoqKgCOTYAAOA+18NOo0aNZMuWLbJ+/XoZMmSIDBw4UHbs2FGg7xkXF2eKvJzpwIEDBfp+AADAPa7f9VxLb+rXr2/+btOmjWzcuFGmTZsmd999t2l4fPToUb/SHe2NFRkZaf7Wxw0bNvhtz+mt5ayTHS1F0gkAANjP9ZKdrDIzM02bGg0+JUuWlBUrVniXJSYmmq7m2qZH6aNWg6WkpHjXWb58uWmkpFVhAAAArpbsaHVS9+7dTaPjY8eOmZ5Xq1evlmXLlpm2NIMGDZLY2FjTQ0sDzLBhw0zA0Z5YqmvXribU9O/fXyZPnmza6YwePdqMzUPJDQAAcD3saInMgAED5NChQybc6ACDGnS6dOlilk+ZMkVKlChhBhPU0h7tafXmm296Xx8cHCyLFi0ybX00BJUrV860+Rk3bpyLRwUAAAJJwI2z4wbG2Sl+bB9npyAxzg6AQFHkxtkBAAAoCIQdAABgNcIOAACwGmEHAABYjbADAACsRtgBAABWI+wAAACrEXYAAIDVCDsAAMBqhB0AAGA1wg4AALAaYQcAAFiNsAMAAKxG2AEAAFYj7AAAAKsRdgAAgNUIOwAAwGqEHQAAYDXCDgAAsBphBwAAWI2wAwAArEbYAQAAViPsAAAAqxF2AACA1Qg7AADAaoQdAABgNcIOAACwGmEHAABYjbADAACsFuL2DgD5ofYzizmRAIBsUbIDAACsRskOgIAocds3KZorAaBAULIDAACsRskOAhbtcAIT1wVAUUPJDgAAsJqrYSc+Pl6uvvpqueyyy6RKlSpyxx13SGJiot86HTp0kKCgIL/p0Ucf9Vtn//79Eh0dLWXLljXbGTlypJw5c6aQjwYAAAQiV6ux1qxZIzExMSbwaDh59tlnpWvXrrJjxw4pV66cd73BgwfLuHHjvM811DjOnj1rgk5kZKSsXbtWDh06JAMGDJCSJUvKxIkTC/2YAABAYHE17CxdutTv+axZs0zJzObNm+Wmm27yCzcaZrLzxRdfmHD05ZdfStWqVaV169by4osvyqhRo+SFF16QUqVKFfhxAACAwBVQbXZSU1PNY4UKFfzmz5kzRypVqiTNmzeXuLg4OXnypHdZQkKCtGjRwgQdR7du3SQtLU22b9+e7fukp6eb5b4TAACwU8D0xsrMzJThw4fL9ddfb0KN47777pNatWpJ9erVZevWrabERtv1fPLJJ2Z5UlKSX9BRznNdllNbobFjxxbo8QAAgMAQMGFH2+78+OOP8s033/jNf+SRR7x/awlOtWrVpFOnTrJnzx6pV69ent5LS4diY2O9z7VkJyoq6hL2HgAABKqAqMYaOnSoLFq0SFatWiU1atQ477rt2rUzj7t37zaP2pYnOTnZbx3neU7tfEJDQyUsLMxvAgAAdnI17Hg8HhN0FixYICtXrpQ6depc8DVbtmwxj1rCo9q3by/btm2TlJQU7zrLly83AaZp06YFuPcAAKAoCHG76mru3Lny2WefmbF2nDY24eHhUqZMGVNVpct79OghFStWNG12RowYYXpqtWzZ0qyrXdU11PTv318mT55stjF69GizbS3BAQAAxZurJTvTp083PbB04EAtqXGmDz/80CzXbuPapVwDTePGjeXJJ5+UPn36yMKFC73bCA4ONlVg+qilPPfff78ZZ8d3XB4AAFB8hbhdjXU+2mhYBx68EO2t9fnnn+fjngEAAFsERANlAACAgkLYAQAAViPsAAAAqxF2AACA1Qg7AADAaoQdAABgNcIOAACwGmEHAABYjbADAACsRtgBAABWI+wAAACrEXYAAIDVCDsAAMBqhB0AAGA1wg4AALAaYQcAAFiNsAMAAKxG2AEAAFYj7AAAAKsRdgAAgNXyFHY6duwoR48ePWd+WlqaWQYAAFCkw87q1aslIyPjnPmnTp2Sr7/+Oj/2CwAAIF+E5GblrVu3ev/esWOHJCUleZ+fPXtWli5dKldccUX+7BkAAEBhh53WrVtLUFCQmbKrripTpoy8/vrr+bFfAAAAhR929u7dKx6PR+rWrSsbNmyQypUre5eVKlVKqlSpIsHBwfmzZwAAAIUddmrVqmUeMzMz8+O9AQAAAivs+Nq1a5esWrVKUlJSzgk/Y8aMyY99AwAAcCfsvP322zJkyBCpVKmSREZGmjY8Dv2bsAMAAIp02Bk/frxMmDBBRo0alf97BAAA4PY4O3/88Yfceeed+bkfAAAAgRN2NOh88cUX+b83AAAAgVCNVb9+fXnuuedk3bp10qJFCylZsqTf8scffzy/9g9AMVH7mcUXve6+SdEFui8A7BLk0YFzcqlOnTo5bzAoSH7++WcpSvSeXuHh4ZKamiphYWFu7w7y8OWH4oWwAyA33995KtnRwQUBAACsbbMDAABQVOSpZOehhx467/L33nvvorYTHx8vn3zyifz000/mvlrXXXedvPTSS9KoUSO/O6k/+eSTMm/ePElPT5du3brJm2++KVWrVvWus3//fjPujw5yWL58eRk4cKDZdkhInsdMBAAAxb3rue+koyivXLnSBJejR49e9HbWrFkjMTExpqHz8uXL5fTp09K1a1c5ceKEd50RI0bIwoULZf78+Wb9gwcPSu/evf3uth4dHS0ZGRmydu1amT17tsyaNYuBDQEAQN4bKGdHbxmhpSv16tWTp59+Ok/b+O2338zNRDXU3HTTTabBkd5sdO7cudK3b1+zjpYCNWnSRBISEuTaa6+VJUuWyG233WZCkFPaM2PGDDPgoW5Pb1B6ITRQDkw0UEZOaKAMIDff3/nWZqdEiRISGxsrU6ZMyfM2dGdVhQoVzOPmzZtNaU/nzp296zRu3Fhq1qxpwo7SR+3+7lutpVVdegK2b9+e7ftodZgu950AAICd8rWB8p49e+TMmTN5LhkaPny4XH/99dK8eXMzLykpyZTMRERE+K2rwUaXOev4Bh1nubMsO9qeR5OgM0VFReVpnwEAQODLUwteLcHxpTVhhw4dksWLF5vGwXmhbXd+/PFH+eabb6SgxcXF+R2DluwQeAAAsFOews73339/ThWWtq35+9//fsGeWtkZOnSoLFq0SL766iupUaOGd77eUV0bHmujZ9/SneTkZLPMWWfDhg1+29PlzrLshIaGmgkAANgvT2FHu3jnBy0RGjZsmCxYsEBWr159zsjMbdq0MbeiWLFihfTp08fMS0xMNF3N27dvb57ro96BXXuEaeNmpT27tKFS06ZN82U/AQBA0XVJA9FobycNH0rHxtHSndxWXWlPq88++0wuu+wybxsbbUej4+7o46BBg0yVkzZa1gCj4UgDjvbEUtpVXUNN//79ZfLkyWYbo0ePNtum9AYAAOSpgbKOg6PVVdWqVTNdxHWqXr26CSYnT5686O1Mnz7d9MDq0KGD2ZYzffjhh951tHeXdi3Xkh19H62a0vF8HMHBwaYKTB81BN1///0yYMAAGTduHFcXAADkbZydv/71r/Lll1/KP/7xD9N7SmnDYr3beZcuXUyIKUoYZycwMc4OcsI4OwAK/EagH3/8sXz00UemRMbRo0cPU/V01113FbmwAwAA7JWnaiytqso6to3SBsK5qcYCAAAIyLCjbWOef/55c5NOx59//iljx4719pICAAAIBHmqxpo6darceuutZkycVq1amXk//PCD6f30xRdf5Pc+AgAAFG7Y0XtR7dq1S+bMmWNuzKnuvfde6devn2m3AwAAUKTDjt5bStvsDB482G/+e++9Z8be0TuOAwAAFNk2O2+99Za5+3hWzZo1kxkzZuTHfgEAALgXdnSUYh38LysdQVlvCAoAAFCkw47eIfzbb789Z77O05GUAQAAinSbHW2rM3z4cDl9+rR07NjRzNObdT799NPy5JNP5vc+AgAAFG7YGTlypBw+fFgee+wxycjIMPNKly5tGibHxcXlfW8AAAACIewEBQXJSy+9JM8995zs3LnTdDdv0KABdxkHAAB2hB1H+fLl5eqrr86/vQEAAAiEBsoAAADFomQHANxQ+5nFuVp/36ToAtsXAIGPsIOA/pICAOBSUY0FAACsRtgBAABWI+wAAACrEXYAAIDVCDsAAMBqhB0AAGA1wg4AALAaYQcAAFiNsAMAAKxG2AEAAFYj7AAAAKsRdgAAgNUIOwAAwGqEHQAAYDXCDgAAsBphBwAAWI2wAwAArEbYAQAAVnM17Hz11VfSs2dPqV69ugQFBcmnn37qt/yBBx4w832nW2+91W+dI0eOSL9+/SQsLEwiIiJk0KBBcvz48UI+EgAAEKhcDTsnTpyQVq1ayRtvvJHjOhpuDh065J3+9a9/+S3XoLN9+3ZZvny5LFq0yASoRx55pBD2HgAAFAUhbr559+7dzXQ+oaGhEhkZme2ynTt3ytKlS2Xjxo3Stm1bM+/111+XHj16yCuvvGJKjAAAQPEW8G12Vq9eLVWqVJFGjRrJkCFD5PDhw95lCQkJpurKCTqqc+fOUqJECVm/fr1LewwAAAKJqyU7F6JVWL1795Y6derInj175NlnnzUlQRpygoODJSkpyQQhXyEhIVKhQgWzLCfp6elmcqSlpRXocQAAAPcEdNi55557vH+3aNFCWrZsKfXq1TOlPZ06dcrzduPj42Xs2LH5tJcAACCQBXw1lq+6detKpUqVZPfu3ea5tuVJSUnxW+fMmTOmh1ZO7XxUXFycpKameqcDBw4U+L4DAAB3FKmw8+uvv5o2O9WqVTPP27dvL0ePHpXNmzd711m5cqVkZmZKu3btztvoWbuq+04AAMBOrlZj6Xg4TimN2rt3r2zZssW0udFJq5r69OljSmm0zc7TTz8t9evXl27dupn1mzRpYtr1DB48WGbMmCGnT5+WoUOHmuovemIBcNR+ZvFFn4x9k6I5cYBlXC3Z2bRpk1x55ZVmUrGxsebvMWPGmAbIW7duldtvv10aNmxoBgts06aNfP3116ZkxjFnzhxp3LixacOjXc5vuOEGmTlzpotHBQAAAomrJTsdOnQQj8eT4/Jly5ZdcBtaAjR37tx83jMAAGCLItVmBwAAILcIOwAAwGqEHQAAYDXCDgAAsBphBwAAWI2wAwAArEbYAQAAViPsAAAAqxF2AACA1Qg7AADAaoQdAABgNVfvjYXid0dpAAAKGyU7AADAaoQdAABgNcIOAACwGmEHAABYjQbKAJDHBvf7JkVz7oAigJIdAABgNcIOAACwGmEHAABYjbADAACsRtgBAABWI+wAAACrEXYAAIDVCDsAAMBqhB0AAGA1wg4AALAaYQcAAFiNsAMAAKxG2AEAAFYj7AAAAKsRdgAAgNUIOwAAwGqEHQAAYDXCDgAAsJqrYeerr76Snj17SvXq1SUoKEg+/fRTv+Uej0fGjBkj1apVkzJlykjnzp1l165dfuscOXJE+vXrJ2FhYRIRESGDBg2S48ePF/KRAACAQOVq2Dlx4oS0atVK3njjjWyXT548WV577TWZMWOGrF+/XsqVKyfdunWTU6dOedfRoLN9+3ZZvny5LFq0yASoRx55pBCPAgAABLIQN9+8e/fuZsqOlupMnTpVRo8eLb169TLzPvjgA6lataopAbrnnntk586dsnTpUtm4caO0bdvWrPP6669Ljx495JVXXjElRgAAoHgL2DY7e/fulaSkJFN15QgPD5d27dpJQkKCea6PWnXlBB2l65coUcKUBOUkPT1d0tLS/CYAAGCngA07GnSUluT40ufOMn2sUqWK3/KQkBCpUKGCd53sxMfHm+DkTFFRUQVyDAAAwH0BG3YKUlxcnKSmpnqnAwcOuL1LAADAxjY75xMZGWkek5OTTW8shz5v3bq1d52UlBS/1505c8b00HJen53Q0FAzIXu1n1nMqQEAWCNgw06dOnVMYFmxYoU33GjbGm2LM2TIEPO8ffv2cvToUdm8ebO0adPGzFu5cqVkZmaatj0AECg/DPZNii7QfQEQoGFHx8PZvXu3X6PkLVu2mDY3NWvWlOHDh8v48eOlQYMGJvw899xzpofVHXfcYdZv0qSJ3HrrrTJ48GDTPf306dMydOhQ01OLnlgAAMD1sLNp0ya55ZZbvM9jY2PN48CBA2XWrFny9NNPm7F4dNwcLcG54YYbTFfz0qVLe18zZ84cE3A6depkemH16dPHjM0DAACggjw6oE0xp9Vj2itLGyvrSMzFHW12gPxHNRbg3vd3seyNBQAAig/CDgAAsBphBwAAWC1gu54DQHFuC0cbHyD/ULIDAACsRtgBAABWI+wAAACrEXYAAIDVCDsAAMBqhB0AAGA1wg4AALAaYQcAAFiNsAMAAKxG2AEAAFbjdhEAUMRvL8GtJYDzo2QHAABYjbADAACsRtgBAABWI+wAAACrEXYAAIDVCDsAAMBqhB0AAGA1wg4AALAaYQcAAFiNsAMAAKxG2AEAAFYj7AAAAKsRdgAAgNUIOwAAwGqEHQAAYDXCDgAAsBphBwAAWI2wAwAArEbYAQAAViPsAAAAqwV02HnhhRckKCjIb2rcuLF3+alTpyQmJkYqVqwo5cuXlz59+khycrKr+wwAAAJLQIcd1axZMzl06JB3+uabb7zLRowYIQsXLpT58+fLmjVr5ODBg9K7d29X9xcAAASWEAlwISEhEhkZec781NRUeffdd2Xu3LnSsWNHM+/999+XJk2ayLp16+Taa691YW8BAECgCfiSnV27dkn16tWlbt260q9fP9m/f7+Zv3nzZjl9+rR07tzZu65WcdWsWVMSEhLOu8309HRJS0vzmwAAgJ0COuy0a9dOZs2aJUuXLpXp06fL3r175cYbb5Rjx45JUlKSlCpVSiIiIvxeU7VqVbPsfOLj4yU8PNw7RUVFFfCRAAAAtwR0NVb37t29f7ds2dKEn1q1asm///1vKVOmTJ63GxcXJ7Gxsd7nWrJD4AEAwE4BXbKTlZbiNGzYUHbv3m3a8WRkZMjRo0f91tHeWNm18fEVGhoqYWFhfhMAALBTkQo7x48flz179ki1atWkTZs2UrJkSVmxYoV3eWJiomnT0759e1f3EwAABI6ArsZ66qmnpGfPnqbqSruVP//88xIcHCz33nuvaWszaNAgUx1VoUIFUzozbNgwE3ToiQUAAIpE2Pn1119NsDl8+LBUrlxZbrjhBtOtXP9WU6ZMkRIlSpjBBLWHVbdu3eTNN990e7cBAEAACfJ4PB4p5rSBspYU6dg9tN8Rqf3MYrcvCYAAsW9StNu7AFzy93dAl+wg/xBgAADFVZFqoAwAAJBbhB0AAGA1wg4AALAaYQcAAFiNsAMAAKxG2AEAAFYj7AAAAKsxzg4AIF/G6GIAQgQqwg4AoNARolCYqMYCAABWI+wAAACrEXYAAIDVCDsAAMBqhB0AAGA1emMBAAq9hxVQmCjZAQAAViPsAAAAq1GNBQCwqnqMkZyRFWGnCKN+HACAC6MaCwAAWI2wAwAArEbYAQAAViPsAAAAqxF2AACA1Qg7AADAaoQdAABgNcIOAACwGmEHAABYjbADAACsxu0iAADF9lY63EereKBkBwAAWI2wAwAArEY1FgCg2KLKq3iwpmTnjTfekNq1a0vp0qWlXbt2smHDBrd3CQAABAArSnY+/PBDiY2NlRkzZpigM3XqVOnWrZskJiZKlSpVXN03fjUAgB2K4r/nudnnQNrv/GZFyc6rr74qgwcPlgcffFCaNm1qQk/ZsmXlvffec3vXAACAy4p8yU5GRoZs3rxZ4uLivPNKlCghnTt3loSEBClKcpvAAQB2KIr//tcuQiVdRT7s/P7773L27FmpWrWq33x9/tNPP2X7mvT0dDM5UlNTzWNaWlq+719m+sl83yYAILDVHDFfiqK0XHwP5ub7rSC+X3236/F47A47eREfHy9jx449Z35UVJQr+wMAQCAIn1q0tus4duyYhIeH2xt2KlWqJMHBwZKcnOw3X59HRkZm+xqt8tIGzY7MzEw5cuSIVKxYUYKCggp8n22k6VrD4oEDByQsLMzt3Sn2uB6BhesROLgWdl0PLdHRoFO9evXzrlfkw06pUqWkTZs2smLFCrnjjju84UWfDx06NNvXhIaGmslXREREoeyv7fTDStgJHFyPwML1CBxcC3uux/lKdKwJO0pLaQYOHCht27aVa665xnQ9P3HihOmdBQAAijcrws7dd98tv/32m4wZM0aSkpKkdevWsnTp0nMaLQMAgOLHirCjtMoqp2orFDytFnz++efPqR6EO7gegYXrETi4FsXzegR5LtRfCwAAoAizYgRlAACAnBB2AACA1Qg7AADAaoQdAABgNcIOLsn06dOlZcuW3gGh2rdvL0uWLOGsBoBJkyaZEcGHDx/u9q4USy+88II5/75T48aN3d6tYu2///2v3H///Wa0/DJlykiLFi1k06ZNbu9WsVO7du1z/t/QKSYmpsDe05qu53BHjRo1zJdqgwYNzLDds2fPll69esn3338vzZo147K4ZOPGjfLWW2+ZIAr36P8DX375pfd5SAj/5Lrljz/+kOuvv15uueUW84OscuXKsmvXLrn88std26fi/O/T2bNnvc9//PFH6dKli9x5550F9p78n4dL0rNnT7/nEyZMMKU969atI+y45Pjx49KvXz95++23Zfz48W7tBv4v3OR0jz4Urpdeesncg+n999/3zqtTpw6XwQUaNH3pD+Z69erJzTffXGDvSTUW8o0m9Xnz5plbdWh1FtyhRcHR0dHSuXNnLoHLtORAb1BYt25dE0D379/v9i4VW//7v/9rbimkpQdVqlSRK6+80vwggLsyMjLkn//8pzz00EMFeiNuSnZwybZt22bCzalTp6R8+fKyYMECadq0KWfWBRo2v/vuO1NMDHe1a9dOZs2aJY0aNZJDhw7J2LFj5cYbbzRF9pdddhmXp5D9/PPPptRZ76X47LPPmv9HHn/8cXMzab23Itzx6aefytGjR+WBBx4o0PdhBGXkSzLXX6ypqany0UcfyTvvvCNr1qwh8BSyAwcOmF+uy5cv97bV6dChg7lXnN4cF+7Sf9Br1aolr776qgwaNIjLUcg01Oj/H2vXrvXO07CjoSchIYHr4ZJu3bqZa7Nw4cICfR+qsXDJ9INav359adOmjcTHx0urVq1k2rRpnNlCtnnzZklJSZGrrrrKtBXRSUPna6+9Zv72bRCIwhcRESENGzaU3bt3c/pdUK1atXN+gDVp0oSqRRf98ssvpgH/ww8/XODvRTUW8l1mZqakp6dzZgtZp06dTJWirwcffNB0dx41apQEBwdzTVxuOL5nzx7p378/18EF2hMrMTHRb95//vMfU9oGd2hjcW0/pW0MCxphB5ckLi5OunfvLjVr1pRjx47J3LlzZfXq1bJs2TLObCHTdiDNmzf3m1euXDkzpkjW+Sh4Tz31lOmtqF+mBw8eNHd21sB57733cvpdMGLECLnuuutk4sSJctddd8mGDRtk5syZZoI7P4o17Gh7qcIYkoGwg0ui1SYDBgwwDTDDw8NNWxENOjpmAlCc/frrrybYHD582HS1veGGG8yQDFm73aJwXH311abzhP5AGzdunOl2rm3ZtJccCp9WX2lbT+2FVRhooAwAAKxGA2UAAGA1wg4AALAaYQcAAFiNsAMAAKxG2AEAAFYj7AAAAKsRdgAAgNUIOwAAwGqEHQAAYDXCDgAAsBphB0BA6tChgwwbNkyGDx8ul19+uVStWlXefvttOXHihLmbu974tH79+rJkyRLva3788UdzY9ry5cub9fUO47///rt3+dKlS809qiIiIswNUm+77TZzJ3LHvn37JCgoSD755BO55ZZbpGzZstKqVStJSEgo9OMHkH8IOwAC1uzZs6VSpUrmDtUafIYMGSJ33nmnuXv1d999J127djWB5uTJk3L06FHp2LGjXHnllbJp0yYTbJKTk80drh0alGJjY83yFStWSIkSJeQvf/mLuQOzr7/97W/mruVbtmyRhg0bmht6njlzxoUzACA/cCNQAAFbsnP27Fn5+uuvzXP9Ozw8XHr37i0ffPCBmZeUlCTVqlUzJS96F2Vdd9myZX53Ho+KipLExEQTWrLSUh+9C/m2bdukefPmpmRH74b9zjvvyKBBg8w6O3bskGbNmsnOnTulcePGhXb8APIPJTsAAlbLli29fwcHB5uqpxYtWnjnaVWVSklJkR9++EFWrVplqrCcyQknTlXVrl27TClN3bp1JSwsTGrXrm3m79+/P8f31TDlvAeAoinE7R0AgJyULFnS77m2p/Gdp8+VVkMdP35cevbsKS+99NI523ECiy6vVauWaftTvXp18zot0cnIyMjxfX3fA0DRRNgBYIWrrrpKPv74Y1NaExJy7j9thw8fNtVZGnRuvPFGM++bb75xYU8BFDaqsQBYISYmRo4cOWKqqTZu3GiqrrT9jvbc0vY+2qNLq8Fmzpwpu3fvlpUrV5rGygDsR9gBYAWtlvr2229NsNFeWtq2R7utazdz7XWl07x582Tz5s2m6mrEiBHy8ssvu73bAAoBvbEAAIDVKNkBAABWI+wAAACrEXYAAIDVCDsAAMBqhB0AAGA1wg4AALAaYQcAAFiNsAMAAKxG2AEAAFYj7AAAAKsRdgAAgNUIOwAAQGz2/wA7uNinVm3VPAAAAABJRU5ErkJggg==",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Cell 12 — Plot bootstrap distributions\n",
+    "plt.figure()\n",
+    "plt.hist(boot_mean, bins=40)\n",
+    "plt.title(\"Bootstrap distribution: mean\")\n",
+    "plt.xlabel(\"mean\"); plt.ylabel(\"count\")\n",
+    "plt.show()\n",
+    "\n",
+    "plt.figure()\n",
+    "plt.hist(boot_med, bins=40)\n",
+    "plt.title(\"Bootstrap distribution: median\")\n",
+    "plt.xlabel(\"median\"); plt.ylabel(\"count\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "id": "822bf7bb",
+   "metadata": {},
+   "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>case</th>\n",
+       "      <th>mean</th>\n",
+       "      <th>median</th>\n",
+       "      <th>SD(boot mean)</th>\n",
+       "      <th>SD(boot median)</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>with outlier</td>\n",
+       "      <td>3.999189</td>\n",
+       "      <td>2.505819</td>\n",
+       "      <td>0.663112</td>\n",
+       "      <td>0.294632</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>no outlier</td>\n",
+       "      <td>3.442445</td>\n",
+       "      <td>2.451680</td>\n",
+       "      <td>0.356388</td>\n",
+       "      <td>0.291492</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "           case      mean    median  SD(boot mean)  SD(boot median)\n",
+       "0  with outlier  3.999189  2.505819       0.663112         0.294632\n",
+       "1    no outlier  3.442445  2.451680       0.356388         0.291492"
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Cell 13 — Remove the outlier and compare stability\n",
+    "x_no = x.iloc[:-1]  # drop the injected outlier\n",
+    "boot_mean_no = bootstrap_statistic(x_no.values, np.mean, B=B, rng=rng)\n",
+    "boot_med_no  = bootstrap_statistic(x_no.values, np.median, B=B, rng=rng)\n",
+    "\n",
+    "comparison = pd.DataFrame({\n",
+    "    \"case\": [\"with outlier\", \"no outlier\"],\n",
+    "    \"mean\": [x.mean(), x_no.mean()],\n",
+    "    \"median\": [x.median(), x_no.median()],\n",
+    "    \"SD(boot mean)\": [np.std(boot_mean, ddof=1), np.std(boot_mean_no, ddof=1)],\n",
+    "    \"SD(boot median)\": [np.std(boot_med, ddof=1), np.std(boot_med_no, ddof=1)],\n",
+    "})\n",
+    "comparison"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "91229b9d",
+   "metadata": {},
+   "source": [
+    "# Student Task (deliverables)\n",
+    "### Submit a single notebook (.ipynb) with the following:\n",
+    "\n",
+    "## Task A — Descriptive Stats (10 pts)\n",
+    "1. Compute and report: mean, median, SD, IQR, five-number summary.  \n",
+    "2. Plot: histogram + boxplot.  \n",
+    "3. Identify outliers using the 1.5×IQR rule and print them.\n",
+    "\n",
+    "## Task B — Sampling Variability (10 pts)\n",
+    "1. Using the provided population experiment, run repeated sampling for **n = 10, 50, 200**.  \n",
+    "2. Plot the sampling distributions (3 histograms).  \n",
+    "3. Make a table of the empirical standard error (SD of sample means) vs n.  \n",
+    "4. Write 3–4 sentences: **Why does variability decrease when n increases?**\n",
+    "\n",
+    "## Task C — Bootstrap Mean vs Median (10 pts)\n",
+    "1. Bootstrap the mean and median (B=5000) for the dataset with the outlier.  \n",
+    "2. Plot both bootstrap distributions.  \n",
+    "3. Compute 95% percentile CIs for mean and median.  \n",
+    "4. Repeat after removing the outlier and compare:\n",
+    "   - Which statistic changes more (mean or median)?\n",
+    "   - Which bootstrap distribution is wider, and why?\n",
+    "\n",
+    "## Reflection (Bonus +2)\n",
+    "In one paragraph: “Big n does not fix systematic bias.” Give one real-world example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "id": "1b309ab9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'TaskB_explanation': 'WRITE YOUR 3–4 SENTENCES HERE',\n",
+       " 'TaskC_comparison': 'WRITE YOUR COMPARISON HERE',\n",
+       " 'Bonus_reflection': 'OPTIONAL: WRITE YOUR PARAGRAPH HERE'}"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Cell 14 — Student: write answers here (replace with your text)\n",
+    "answers = {\n",
+    "    \"TaskB_explanation\": \"WRITE YOUR 3–4 SENTENCES HERE\",\n",
+    "    \"TaskC_comparison\": \"WRITE YOUR COMPARISON HERE\",\n",
+    "    \"Bonus_reflection\": \"OPTIONAL: WRITE YOUR PARAGRAPH HERE\",\n",
+    "}\n",
+    "answers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f30b9ae8",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv (3.14.2)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.14.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}