{ "cells": [ { "cell_type": "markdown", "id": "a15cd228-d1cd-4d52-bc62-92aa975f798c", "metadata": {}, "source": [ "(excess_deaths)=\n", "# Counterfactual inference: calculating excess deaths due to COVID-19\n", "\n", ":::{post} July, 2022\n", ":tags: counterfactuals, causal inference, time series, case study, Bayesian workflow, forecasting, causal impact, regression, posterior predictive\n", ":category: intermediate\n", ":author: Benjamin T. Vincent\n", ":::\n", "\n", "Causal reasoning and counterfactual thinking are really interesting but complex topics! Nevertheless, we can make headway into understanding the ideas through relatively simple examples. This notebook focuses on the concepts and the practical implementation of Bayesian causal reasoning using PyMC.\n", "\n", "We do this using the sobering but important example of calculating excess deaths due to COVID-19. As such, the ideas in this notebook strongly overlap with Google's [CausalImpact](https://google.github.io/CausalImpact/CausalImpact.html) (see {cite:t}google_causal_impact2015). Practically, we will try to estimate the number of 'excess deaths' since the onset of COVID-19, using data from England and Wales. Excess deaths are defined as:\n", "\n", "$$\n", "\\text{Excess deaths} = \n", " \\underbrace{\\text{Reported Deaths}}_{\\text{noisy measure of actual deaths}} \n", " - \\underbrace{\\text{Expected Deaths}}_{\\text{unmeasurable counterfactual}}\n", "$$\n", "\n", "Making a claim about excess deaths requires causal/counterfactual reasoning. While the reported number of deaths is nothing but a (maybe noisy and/or lagged) measure of a real observable fact in the world, _expected deaths_ is unmeasurable because these are never realised in our timeline. That is, the expected deaths is a counterfactual thought experiment where we can ask \"What would/will happen if?\"" ] }, { "cell_type": "markdown", "id": "9b827bb1-ce58-436c-b4d0-e4931c4f1829", "metadata": {}, "source": [ "## Overall strategy\n", "How do we go about this, practically? We will follow this strategy:\n", "1. Import data on reported number of deaths from all causes (our outcome variable), as well as a few reasonable predictor variables: \n", " - average monthly temperature\n", " - month of the year, which we use to model seasonal effects\n", " - and time which is used to model any underlying linear trend.\n", "2. Split into pre and post covid datasets. This is an important step. We want to come up with a model based upon what we know _before_ COVID-19 so that we can construct our counterfactual predictions based on data before COVID-19 had any impact.\n", "3. Estimate model parameters based on the pre dataset. \n", "4. [Retrodict](https://en.wikipedia.org/wiki/Retrodiction) the number of deaths expected by the model in the pre COVID-19 period. This is not a counterfactual, but acts to tell us how capable the model is at accounting for the already observed data.\n", "5. Counterfactual inference - we use our model to construct a counterfactual forecast. What would we expect to see in the future if there was no COVID-19? This can be achieved by using the famous do-operator Practically, we do this with posterior prediction on out-of-sample data. \n", "6. Calculate the excess deaths by comparing the reported deaths with our counterfactual (expected number of deaths)." ] }, { "cell_type": "markdown", "id": "66adb952-c78a-48c4-9c86-a18d5446154e", "metadata": {}, "source": [ "## Modelling strategy\n", "We could take many different approaches to the modelling. Because we are dealing with time series data, then it would be very sensible to use a time series modelling approach. For example, Google's [CausalImpact](https://google.github.io/CausalImpact/CausalImpact.html) uses a [Bayesian structural time-series](https://en.wikipedia.org/wiki/Bayesian_structural_time_series) model, but there are many alternative time series models we could choose. \n", "\n", "But because the focus of this case study is on the counterfactual reasoning rather than the specifics of time-series modelling, I chose the simpler approach of linear regression for time-series model (see {cite:t}martin2021bayesian for more on this)." ] }, { "cell_type": "markdown", "id": "7ce1937a-fe3f-4281-b482-82e8e6cd92d1", "metadata": { "tags": [] }, "source": [ "## Causal inference disclaimer\n", "\n", "Readers should be aware that there are of course limits to the causal claims we can make here. If we were dealing with a marketing example where we ran a promotion for a period of time and wanted to make inferences about _excess sales_, then we could only make strong causal claims if we had done our due diligence in accounting for other factors which may have also taken place during our promotion period. \n", "\n", "Similarly, there are [many other things that changed in the UK since January 2020](https://en.wikipedia.org/wiki/2020_in_the_United_Kingdom#Events) (the well documented time of the first COVID-19 cases) in England and Wales. So if we wanted to be rock solid then we should account for other feasibly relevant factors.\n", "\n", "Finally, we are _not_ claiming that $x$ people died directly from the COVID-19 virus. The beauty of the concept of excess deaths is that it captures deaths from all causes that are in excess of what we would expect. As such, it covers not only those who died directly from the COVID-19 virus, but also from all downstream effects of the virus and availability of care, for example." ] }, { "cell_type": "code", "execution_count": 1, "id": "f9fbb462-3baf-4b8d-aad4-270bbd0a4018", "metadata": {}, "outputs": [], "source": [ "import calendar\n", "import os\n", "\n", "import arviz as az\n", "import matplotlib.dates as mdates\n", "import matplotlib.pyplot as plt\n", "import numpy as np\n", "import pandas as pd\n", "import pymc as pm\n", "import pytensor.tensor as pt\n", "import seaborn as sns\n", "import xarray as xr" ] }, { "cell_type": "code", "execution_count": 2, "id": "861d3310-56d9-43cb-9baa-178e155eba3d", "metadata": {}, "outputs": [], "source": [ "%config InlineBackend.figure_format = 'retina'\n", "RANDOM_SEED = 8927\n", "rng = np.random.default_rng(RANDOM_SEED)\n", "az.style.use(\"arviz-darkgrid\")" ] }, { "cell_type": "markdown", "id": "2bbd94c9-c102-4116-91a1-50fe396ca089", "metadata": {}, "source": [ "Now let's define some helper functions" ] }, { "cell_type": "code", "execution_count": 3, "id": "bdaae928-aabe-410d-b345-237a7c2361d2", "metadata": { "tags": [ "hide-cell" ] }, "outputs": [], "source": [ "def ZeroSumNormal(name, *, sigma=None, active_dims=None, dims, model=None):\n", " model = pm.modelcontext(model=model)\n", "\n", " if isinstance(dims, str):\n", " dims = [dims]\n", "\n", " if isinstance(active_dims, str):\n", " active_dims = [active_dims]\n", "\n", " if active_dims is None:\n", " active_dims = dims[-1]\n", "\n", " def extend_axis(value, axis):\n", " n_out = value.shape[axis] + 1\n", " sum_vals = value.sum(axis, keepdims=True)\n", " norm = sum_vals / (pt.sqrt(n_out) + n_out)\n", " fill_val = norm - sum_vals / pt.sqrt(n_out)\n", " out = pt.concatenate([value, fill_val], axis=axis)\n", " return out - norm\n", "\n", " dims_reduced = []\n", " active_axes = []\n", " for i, dim in enumerate(dims):\n", " if dim in active_dims:\n", " active_axes.append(i)\n", " dim_name = f\"{dim}_reduced\"\n", " if name not in model.coords:\n", " model.add_coord(dim_name, length=len(model.coords[dim]) - 1, mutable=False)\n", " dims_reduced.append(dim_name)\n", " else:\n", " dims_reduced.append(dim)\n", "\n", " raw = pm.Normal(f\"{name}_raw\", sigma=sigma, dims=dims_reduced)\n", " for axis in active_axes:\n", " raw = extend_axis(raw, axis)\n", " return pm.Deterministic(name, raw, dims=dims)\n", "\n", "\n", "def format_x_axis(ax, minor=False):\n", " # major ticks\n", " ax.xaxis.set_major_formatter(mdates.DateFormatter(\"%Y %b\"))\n", " ax.xaxis.set_major_locator(mdates.YearLocator())\n", " ax.grid(which=\"major\", linestyle=\"-\", axis=\"x\")\n", " # minor ticks\n", " if minor:\n", " ax.xaxis.set_minor_formatter(mdates.DateFormatter(\"%Y %b\"))\n", " ax.xaxis.set_minor_locator(mdates.MonthLocator())\n", " ax.grid(which=\"minor\", linestyle=\":\", axis=\"x\")\n", " # rotate labels\n", " for label in ax.get_xticklabels(which=\"both\"):\n", " label.set(rotation=70, horizontalalignment=\"right\")\n", "\n", "\n", "def plot_xY(x, Y, ax):\n", " quantiles = Y.quantile((0.025, 0.25, 0.5, 0.75, 0.975), dim=(\"chain\", \"draw\")).transpose()\n", "\n", " az.plot_hdi(\n", " x,\n", " hdi_data=quantiles.sel(quantile=[0.025, 0.975]),\n", " fill_kwargs={\"alpha\": 0.25},\n", " smooth=False,\n", " ax=ax,\n", " )\n", " az.plot_hdi(\n", " x,\n", " hdi_data=quantiles.sel(quantile=[0.25, 0.75]),\n", " fill_kwargs={\"alpha\": 0.5},\n", " smooth=False,\n", " ax=ax,\n", " )\n", " ax.plot(x, quantiles.sel(quantile=0.5), color=\"C1\", lw=3)\n", "\n", "\n", "# default figure sizes\n", "figsize = (10, 5)\n", "\n", "# create a list of month strings, for plotting purposes\n", "month_strings = calendar.month_name[1:]" ] }, { "cell_type": "markdown", "id": "a09f2651-5817-40c4-b19f-1b7478e6b167", "metadata": {}, "source": [ "## Import data\n", "For our purposes we will obtain number of deaths (per month) reported in England and Wales. This data is available from the Office of National Statistics dataset [Deaths registered monthly in England and Wales](https://www.ons.gov.uk/peoplepopulationandcommunity/birthsdeathsandmarriages/deaths/datasets/monthlyfiguresondeathsregisteredbyareaofusualresidence). I manually downloaded this data for the years 2006-2022 and aggregated it into a single .csv file. I also added the average UK monthly temperature data as a predictor, obtained from the [average UK temperature from the Met Office](https://www.metoffice.gov.uk/research/climate/maps-and-data/uk-and-regional-series) dataset." ] }, { "cell_type": "code", "execution_count": 4, "id": "561b712e-afbb-4a9f-9ffe-c9e0350f79e1", "metadata": {}, "outputs": [], "source": [ "try:\n", " df = pd.read_csv(os.path.join(\"..\", \"data\", \"deaths_and_temps_england_wales.csv\"))\n", "except FileNotFoundError:\n", " df = pd.read_csv(pm.get_data(\"deaths_and_temps_england_wales.csv\"))\n", "\n", "df[\"date\"] = pd.to_datetime(df[\"date\"])\n", "df = df.set_index(\"date\")\n", "\n", "# split into separate dataframes for pre and post onset of COVID-19\n", "pre = df[df.index < \"2020\"]\n", "post = df[df.index >= \"2020\"]" ] }, { "cell_type": "markdown", "id": "4a95716e-50ab-49ed-83e1-8ceb168fbf91", "metadata": {}, "source": [ "## Visualise data" ] }, { "cell_type": "markdown", "id": "687a702f-810d-4c41-99a0-64535a651c50", "metadata": {}, "source": [ "### Reported deaths over time\n", "Plotting the time series shows that there is clear seasonality in the number of deaths, and we can also take a guess that there may be an increase in the average number of deaths per year." ] }, { "cell_type": "code", "execution_count": 5, "id": "844e7541-ae4a-4c0f-9068-5b8299ec7c5c", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "