{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Excess deaths due to COVID-19"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from pymc_extras.prior import Prior\n",
"\n",
"import causalpy as cp"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2\n",
"%config InlineBackend.figure_format = 'retina'\n",
"seed = 42"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load data"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" temp | \n",
" deaths | \n",
" year | \n",
" month | \n",
" t | \n",
" pre | \n",
"
\n",
" \n",
" | date | \n",
" | \n",
" | \n",
" | \n",
" | \n",
" | \n",
" | \n",
"
\n",
" \n",
" \n",
" \n",
" | 2006-01-01 | \n",
" 3.8 | \n",
" 49124 | \n",
" 2006 | \n",
" 1 | \n",
" 0 | \n",
" True | \n",
"
\n",
" \n",
" | 2006-02-01 | \n",
" 3.4 | \n",
" 42664 | \n",
" 2006 | \n",
" 2 | \n",
" 1 | \n",
" True | \n",
"
\n",
" \n",
" | 2006-03-01 | \n",
" 3.9 | \n",
" 49207 | \n",
" 2006 | \n",
" 3 | \n",
" 2 | \n",
" True | \n",
"
\n",
" \n",
" | 2006-04-01 | \n",
" 7.4 | \n",
" 40645 | \n",
" 2006 | \n",
" 4 | \n",
" 3 | \n",
" True | \n",
"
\n",
" \n",
" | 2006-05-01 | \n",
" 10.7 | \n",
" 42425 | \n",
" 2006 | \n",
" 5 | \n",
" 4 | \n",
" True | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {
"image/png": {
"height": 811,
"width": 711
}
},
"output_type": "display_data"
}
],
"source": [
"fig, ax = result.plot()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"==================================Pre-Post Fit==================================\n",
"Formula: standardize(deaths) ~ 0 + standardize(t) + C(month) + standardize(temp)\n",
"Model coefficients:\n",
" C(month)[1] 1.6, 94% HDI [1.1, 2]\n",
" C(month)[2] -0.2, 94% HDI [-0.66, 0.27]\n",
" C(month)[3] 0.26, 94% HDI [-0.11, 0.64]\n",
" C(month)[4] -0.033, 94% HDI [-0.32, 0.25]\n",
" C(month)[5] -0.15, 94% HDI [-0.46, 0.15]\n",
" C(month)[6] -0.21, 94% HDI [-0.64, 0.2]\n",
" C(month)[7] -0.026, 94% HDI [-0.54, 0.5]\n",
" C(month)[8] -0.42, 94% HDI [-0.91, 0.056]\n",
" C(month)[9] -0.45, 94% HDI [-0.82, -0.062]\n",
" C(month)[10] -0.06, 94% HDI [-0.34, 0.23]\n",
" C(month)[11] -0.36, 94% HDI [-0.7, -0.029]\n",
" C(month)[12] 0.072, 94% HDI [-0.36, 0.49]\n",
" standardize(t) 0.23, 94% HDI [0.16, 0.31]\n",
" standardize(temp) -0.45, 94% HDI [-0.74, -0.15]\n",
" y_hat_sigma 0.55, 94% HDI [0.5, 0.62]\n"
]
}
],
"source": [
"result.summary()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Effect Summary Reporting\n",
"\n",
"For decision-making, you often need a concise summary of the causal effect with key statistics. The `effect_summary()` method provides a decision-ready report with average and cumulative effects, HDI intervals, tail probabilities, and relative effects. This provides a comprehensive summary without manual post-processing.\n",
"\n",
":::{note}\n",
"Note that in this example, the data has been standardized, so the effect estimates are in standardized units. When interpreting the results, keep in mind that the effects are relative to the standardized scale of the outcome variable.\n",
":::\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" mean | \n",
" median | \n",
" hdi_lower | \n",
" hdi_upper | \n",
" p_gt_0 | \n",
" relative_mean | \n",
" relative_hdi_lower | \n",
" relative_hdi_upper | \n",
"
\n",
" \n",
" \n",
" \n",
" | average | \n",
" 0.912301 | \n",
" 0.914077 | \n",
" 0.728512 | \n",
" 1.110732 | \n",
" 1.0 | \n",
" 181.320390 | \n",
" 86.884940 | \n",
" 291.755568 | \n",
"
\n",
" \n",
" | cumulative | \n",
" 26.456723 | \n",
" 26.508243 | \n",
" 21.126834 | \n",
" 32.211233 | \n",
" 1.0 | \n",
" 181.320393 | \n",
" 86.884942 | \n",
" 291.755575 | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" mean | \n",
" median | \n",
" hdi_lower | \n",
" hdi_upper | \n",
" p_gt_0 | \n",
" relative_mean | \n",
" relative_hdi_lower | \n",
" relative_hdi_upper | \n",
"
\n",
" \n",
" \n",
" \n",
" | average | \n",
" 1.984056 | \n",
" 1.984917 | \n",
" 1.792856 | \n",
" 2.195756 | \n",
" 1.0 | \n",
" 292.810259 | \n",
" 182.813253 | \n",
" 414.928539 | \n",
"
\n",
" \n",
" | cumulative | \n",
" 11.904334 | \n",
" 11.909502 | \n",
" 10.757138 | \n",
" 13.174536 | \n",
" 1.0 | \n",
" 292.810263 | \n",
" 182.813255 | \n",
" 414.928545 | \n",
"
\n",
" \n",
"
\n",
"