{ "cells": [ { "cell_type": "markdown", "id": "serial-gateway", "metadata": {}, "source": [ "# API Notes for Python Packages\n", "\n", "## [arch](https://arch.readthedocs.io/en/latest/)\n", "\n", "* Notation for GARCH(1, 1)\n", "\\begin{align*}\n", " r_t &= \\mu + \\epsilon_t \\\\\n", " \\epsilon_t &= \\sigma_t e_t \\\\\n", " \\sigma^2_t &= \\omega + \\alpha \\epsilon_{t-1}^2 + \\beta \\sigma^2_{t-1}\n", "\\end{align*}\n", "\n", "### [Fitting](https://arch.readthedocs.io/en/latest/univariate/introduction.html)\n", "\n", "### Simulation\n", "\n", "* [arch.univariate.GARCH(p=1, o=0, q=1, power=2.0)](https://arch.readthedocs.io/en/latest/univariate/generated/arch.univariate.GARCH.html)\n", " * $\\lambda$ 就是 `power`,預設值 2\n", "\\begin{align*}\n", "\\sigma_{t}^{\\lambda} = \\omega + \\sum_{i=1}^{p}\\alpha_{i}\\left|\\epsilon_{t-i}\\right|^{\\lambda} + \\sum_{j=1}^{o}\\gamma_{j}\\left|\\epsilon_{t-j}\\right|^{\\lambda} I\\left[\\epsilon_{t-j}<0\\right]+\\sum_{k=1}^{q}\\beta_{k}\\sigma_{t-k}^{\\lambda}\n", "\\end{align*}\n", "* [GARCH.simulate(parameters, nobs, rng, burn=500, initial_value=None)](https://arch.readthedocs.io/en/latest/univariate/generated/generated/arch.univariate.GARCH.simulate.html)\n", " * 根據 [source](https://arch.readthedocs.io/en/latest/_modules/arch/univariate/volatility.html#GARCH.simulate),`parameters` 要輸入 [$\\omega, \\alpha_{1}, \\alpha_{2}, \\ldots, \\alpha_{p}, \\gamma_{1}, \\gamma_{2}, \\ldots, \\gamma_{o}, \\beta_{1}, \\beta_{2}, \\ldots, \\beta_{q}$]\n", " * `rng` 是一個輸入 size 輸出隨機數列的函數,輸出用作 innovation $\\{e_t\\}$\n", " * 輸出的兩個數列分別是 $\\{\\epsilon_t\\}$ 和 $\\{\\sigma^2_t\\}$\n", "* ARCH(1) Simulation: " ] }, { "cell_type": "code", "execution_count": 8, "id": "aboriginal-opera", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "from arch.univariate import GARCH\n", "from scipy.stats import norm, t\n", "from pandas import Series\n", "import numpy as np\n", "import numpy.random\n", "\n", "numpy.random.seed(0)\n", "model = GARCH(1, 0, 0)\n", "y, variance = model.simulate([1, 0.5], 100, rng=lambda size: norm.rvs(size=size))\n", "\n", "Series(y).plot(style='.-')\n", "pass" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.12.3" } }, "nbformat": 4, "nbformat_minor": 5 }