{"id":478852,"date":"2023-08-09T09:39:10","date_gmt":"2023-08-09T09:39:10","guid":{"rendered":""},"modified":"2023-09-05T11:17:41","modified_gmt":"2023-09-05T11:17:41","slug":"seasonal-decomposition-of-a-time-series-stl","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/cn\/wiki\/seasonal-decomposition-of-a-time-series-stl\/","title":{"rendered":"\u65f6\u95f4\u5e8f\u5217\u7684\u5b63\u8282\u6027\u5206\u89e3 (STL)"},"content":{"rendered":"<h2>\u4ecb\u7ecd<\/h2>\n<p>\u65f6\u95f4\u5e8f\u5217\u7684\u5b63\u8282\u6027\u5206\u89e3 (STL) \u662f\u4e00\u79cd\u5f3a\u5927\u7684\u7edf\u8ba1\u6280\u672f\uff0c\u7528\u4e8e\u5c06\u65f6\u95f4\u5e8f\u5217\u5206\u89e3\u4e3a\u5176\u57fa\u672c\u7ec4\u6210\u90e8\u5206\uff1a\u8d8b\u52bf\u3001\u5b63\u8282\u6027\u548c\u4f59\u6570\u3002\u6b64\u65b9\u6cd5\u53ef\u4ee5\u6df1\u5165\u4e86\u89e3\u6570\u636e\u4e2d\u5b58\u5728\u7684\u4e0d\u540c\u65f6\u95f4\u6a21\u5f0f\uff0c\u6709\u52a9\u4e8e\u66f4\u597d\u5730\u7406\u89e3\u548c\u5206\u6790\u65f6\u95f4\u5e8f\u5217\u4e2d\u7684\u8d8b\u52bf\u3001\u5468\u671f\u6027\u53d8\u5316\u548c\u4e0d\u89c4\u5219\u6ce2\u52a8\u3002\u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u6df1\u5165\u7814\u7a76\u4e86\u65f6\u95f4\u5e8f\u5217\u7684\u5b63\u8282\u6027\u5206\u89e3 (STL) \u7684\u5386\u53f2\u3001\u673a\u5236\u3001\u7c7b\u578b\u3001\u5e94\u7528\u548c\u672a\u6765\u524d\u666f\uff0c\u63a2\u7d22\u4e86\u5b83\u4e0e\u4ee3\u7406\u670d\u52a1\u5668\u9886\u57df\u7684\u76f8\u5173\u6027\u3002<\/p>\n<h2>\u8d77\u6e90\u548c\u65e9\u671f\u63d0\u53ca<\/h2>\n<p>\u5206\u89e3\u65f6\u95f4\u5e8f\u5217\u4ee5\u53d1\u73b0\u5176\u56fa\u6709\u6210\u5206\u7684\u6982\u5ff5\u53ef\u4ee5\u8ffd\u6eaf\u5230\u51e0\u5341\u5e74\u524d\u3002\u65e9\u671f\u7684\u65b9\u6cd5\uff0c\u4f8b\u5982\u79fb\u52a8\u5e73\u5747\u7ebf\u548c\u6307\u6570\u5e73\u6ed1\uff0c\u4e3a\u6700\u7ec8\u5f00\u53d1\u66f4\u590d\u6742\u7684\u6280\u672f\uff08\u5982 STL\uff09\u5960\u5b9a\u4e86\u57fa\u7840\u3002STL \u7684\u8d77\u6e90\u53ef\u4ee5\u8ffd\u6eaf\u5230 1990 \u5e74\u7531 Cleveland\u3001Cleveland\u3001McRae \u548c Terpenning \u53d1\u8868\u7684\u4e00\u7bc7\u9898\u4e3a\u201c\u65f6\u95f4\u5e8f\u5217\u5206\u89e3\uff1a\u8d1d\u53f6\u65af\u6846\u67b6\u201d\u7684\u8bba\u6587\u3002\u8fd9\u9879\u5de5\u4f5c\u4ecb\u7ecd\u4e86\u57fa\u4e8e Loess (STL) \u7684\u5b63\u8282\u6027\u8d8b\u52bf\u5206\u89e3\u7a0b\u5e8f\uff0c\u4f5c\u4e3a\u4e00\u79cd\u5206\u6790\u65f6\u95f4\u5e8f\u5217\u6570\u636e\u7684\u5f3a\u5927\u800c\u7075\u6d3b\u7684\u65b9\u6cd5\u3002<\/p>\n<h2>\u63ed\u79d8\u673a\u5236<\/h2>\n<h3>\u5185\u90e8\u7ed3\u6784\u548c\u529f\u80fd<\/h3>\n<p>\u65f6\u95f4\u5e8f\u5217\u5b63\u8282\u5206\u89e3\uff08STL\uff09\u7684\u5185\u90e8\u7ed3\u6784\u6d89\u53ca\u4e09\u4e2a\u4e3b\u8981\u90e8\u5206\uff1a<\/p>\n<ol>\n<li>\n<p><strong>\u8d8b\u52bf\u6210\u5206<\/strong>\uff1a\u8fd9\u53ef\u4ee5\u6355\u6349\u65f6\u95f4\u5e8f\u5217\u6570\u636e\u4e2d\u7684\u957f\u671f\u53d8\u5316\u6216\u8fd0\u52a8\u3002\u5b83\u662f\u901a\u8fc7\u5e94\u7528\u7a33\u5065\u5c40\u90e8\u56de\u5f52\u6280\u672f (Loess) \u6765\u5e73\u6ed1\u6ce2\u52a8\u5e76\u8bc6\u522b\u6f5c\u5728\u8d8b\u52bf\u800c\u83b7\u5f97\u7684\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u5b63\u8282\u6027\u56e0\u7d20<\/strong>\uff1a\u5b63\u8282\u6027\u6210\u5206\u63ed\u793a\u4e86\u65f6\u95f4\u5e8f\u5217\u4e2d\u4ee5\u56fa\u5b9a\u95f4\u9694\u51fa\u73b0\u7684\u91cd\u590d\u6a21\u5f0f\u3002\u5b83\u662f\u901a\u8fc7\u5bf9\u4e0d\u540c\u5b63\u8282\u5468\u671f\u4e2d\u6bcf\u4e2a\u5bf9\u5e94\u65f6\u95f4\u70b9\u7684\u8d8b\u52bf\u504f\u5dee\u53d6\u5e73\u5747\u503c\u800c\u5f97\u51fa\u7684\u3002<\/p>\n<\/li>\n<li>\n<p><strong>\u6b8b\u5dee\uff08\u4f59\u6570\uff09\u90e8\u5206<\/strong>\uff1a\u6b8b\u5dee\u6210\u5206\u8868\u793a\u4e0d\u80fd\u5f52\u56e0\u4e8e\u8d8b\u52bf\u6216\u5b63\u8282\u6027\u7684\u4e0d\u89c4\u5219\u548c\u4e0d\u53ef\u9884\u6d4b\u7684\u53d8\u5316\u3002\u5b83\u662f\u901a\u8fc7\u4ece\u539f\u59cb\u65f6\u95f4\u5e8f\u5217\u4e2d\u51cf\u53bb\u8d8b\u52bf\u548c\u5b63\u8282\u6027\u6210\u5206\u6765\u8ba1\u7b97\u7684\u3002<\/p>\n<\/li>\n<\/ol>\n<h3>\u4e3b\u8981\u7279\u70b9\u548c\u4f18\u52bf<\/h3>\n<ul>\n<li><strong>\u7075\u6d3b\u6027<\/strong>\uff1aSTL \u9002\u7528\u4e8e\u5404\u79cd\u65f6\u95f4\u5e8f\u5217\u6570\u636e\u7c7b\u578b\uff0c\u9002\u5e94\u4e0d\u89c4\u5219\u95f4\u9694\u7684\u89c2\u6d4b\u5e76\u5904\u7406\u7f3a\u5931\u7684\u6570\u636e\u70b9\u3002<\/li>\n<li><strong>\u9c81\u68d2\u6027<\/strong>\uff1aSTL \u4e2d\u4f7f\u7528\u7684\u7a33\u5065 Loess \u5e73\u6ed1\u6280\u672f\u51cf\u5c11\u4e86\u5f02\u5e38\u503c\u548c\u566a\u58f0\u6570\u636e\u5bf9\u5206\u89e3\u8fc7\u7a0b\u7684\u5f71\u54cd\u3002<\/li>\n<li><strong>\u53ef\u89e3\u91ca\u6027<\/strong>\uff1a\u5c06\u65f6\u95f4\u5e8f\u5217\u5206\u89e3\u4e3a\u4e0d\u540c\u7684\u90e8\u5206\u6709\u52a9\u4e8e\u89e3\u91ca\u548c\u7406\u89e3\u9a71\u52a8\u6570\u636e\u7684\u4e0d\u540c\u6a21\u5f0f\u3002<\/li>\n<li><strong>\u5b63\u8282\u6027\u68c0\u6d4b<\/strong>\uff1aSTL \u5728\u63d0\u53d6\u5b63\u8282\u6027\u6a21\u5f0f\u65b9\u9762\u7279\u522b\u6709\u6548\uff0c\u5373\u4f7f\u5b83\u4eec\u662f\u975e\u6574\u6570\u5e76\u4e14\u6d89\u53ca\u591a\u4e2a\u9891\u7387\u3002<\/li>\n<\/ul>\n<h2>STL \u7684\u7c7b\u578b<\/h2>\n<p>STL \u53ef\u6839\u636e\u5176\u53d8\u4f53\u548c\u5e94\u7528\u8fdb\u884c\u5206\u7c7b\u3002\u4ee5\u4e0b\u5217\u51fa\u4e86\u4e00\u4e9b\u5e38\u89c1\u7c7b\u578b\uff1a<\/p>\n<ul>\n<li><strong>\u6807\u51c6 STL<\/strong>\uff1a\u5982\u524d\u6240\u8ff0\uff0cSTL \u7684\u57fa\u672c\u5f62\u5f0f\u5c06\u65f6\u95f4\u5e8f\u5217\u5206\u89e3\u4e3a\u8d8b\u52bf\u3001\u5b63\u8282\u548c\u6b8b\u5dee\u6210\u5206\u3002<\/li>\n<li><strong>\u4fee\u6539\u540e\u7684 STL<\/strong>\uff1aSTL \u7684\u53d8\u4f53\uff0c\u7ed3\u5408\u4e86\u989d\u5916\u7684\u5e73\u6ed1\u6280\u672f\u6216\u8c03\u6574\u6765\u6ee1\u8db3\u6570\u636e\u7684\u7279\u5b9a\u7279\u5f81\u3002<\/li>\n<\/ul>\n<h2>\u5e94\u7528\u548c\u6311\u6218<\/h2>\n<h3>\u5229\u7528 STL<\/h3>\n<p>STL \u53ef\u5e94\u7528\u4e8e\u5404\u4e2a\u9886\u57df\uff1a<\/p>\n<ul>\n<li><strong>\u7ecf\u6d4e\u4e0e\u91d1\u878d<\/strong>\uff1a\u5206\u6790\u7ecf\u6d4e\u6307\u6807\u3001\u80a1\u7968\u4ef7\u683c\u548c\u91d1\u878d\u5e02\u573a\u8d8b\u52bf\u3002<\/li>\n<li><strong>\u73af\u5883\u79d1\u5b66<\/strong>\uff1a\u7814\u7a76\u6c14\u5019\u6a21\u5f0f\u3001\u6c61\u67d3\u6c34\u5e73\u548c\u751f\u6001\u6ce2\u52a8\u3002<\/li>\n<li><strong>\u96f6\u552e\u548c\u9500\u552e<\/strong>\uff1a\u4e86\u89e3\u6d88\u8d39\u8005\u884c\u4e3a\u3001\u9500\u552e\u8d8b\u52bf\u548c\u5b63\u8282\u6027\u8d2d\u7269\u6a21\u5f0f\u3002<\/li>\n<\/ul>\n<h3>\u6311\u6218\u4e0e\u89e3\u51b3\u65b9\u6848<\/h3>\n<ul>\n<li><strong>\u7f3a\u5931\u6570\u636e<\/strong>\uff1aSTL \u7531\u4e8e\u5176\u9002\u5e94\u6027\u800c\u80fd\u591f\u5f88\u597d\u5730\u5904\u7406\u7f3a\u5931\u6570\u636e\uff0c\u4f46\u5728\u5206\u89e3\u4e4b\u524d\u8f93\u5165\u7f3a\u5931\u503c\u53ef\u4ee5\u4ea7\u751f\u66f4\u597d\u7684\u7ed3\u679c\u3002<\/li>\n<li><strong>\u8fc7\u62df\u5408<\/strong>\uff1a\u8fc7\u5ea6\u5e73\u6ed1\u53ef\u80fd\u5bfc\u81f4\u8fc7\u5ea6\u62df\u5408\u8d8b\u52bf\u548c\u5b63\u8282\u6027\u6210\u5206\u3002\u4ea4\u53c9\u9a8c\u8bc1\u6280\u672f\u53ef\u4ee5\u7f13\u89e3\u6b64\u95ee\u9898\u3002<\/li>\n<li><strong>\u590d\u6742\u7684\u5b63\u8282\u6027<\/strong>\uff1a\u5bf9\u4e8e\u590d\u6742\u7684\u5b63\u8282\u6027\u6a21\u5f0f\uff0c\u53ef\u80fd\u9700\u8981 STL \u7684\u9ad8\u7ea7\u53d8\u4f53\u6216\u66ff\u4ee3\u65b9\u6cd5\u3002<\/li>\n<\/ul>\n<h2>\u5bf9\u6bd4\u5206\u6790<\/h2>\n<p>\u5728\u672c\u8282\u4e2d\uff0c\u6211\u4eec\u5c06\u65f6\u95f4\u5e8f\u5217\u7684\u5b63\u8282\u5206\u89e3 (STL) \u4e0e\u7c7b\u4f3c\u672f\u8bed\u8fdb\u884c\u6bd4\u8f83\uff1a<\/p>\n<table>\n<thead>\n<tr>\n<th>\u5b66\u671f<\/th>\n<th>\u4f18\u70b9<\/th>\n<th>\u5c40\u9650\u6027<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>\u79fb\u52a8\u5e73\u5747\u7ebf<\/td>\n<td>\u7b80\u5355\u3001\u6613\u4e8e\u5b9e\u65bd<\/td>\n<td>\u5e73\u6ed1\u5904\u7406\u53ef\u80fd\u4f1a\u5ffd\u7565\u7ec6\u5fae\u5dee\u522b<\/td>\n<\/tr>\n<tr>\n<td>\u6307\u6570\u5e73\u6ed1<\/td>\n<td>\u8003\u8651\u5230\u6700\u8fd1\u7684\u6570\u636e\uff0c\u7b80\u5355\u6027<\/td>\n<td>\u5ffd\u7565\u5b63\u8282\u548c\u8d8b\u52bf\u56e0\u7d20<\/td>\n<\/tr>\n<tr>\n<td>\u963f\u91cc\u739b<\/td>\n<td>\u5904\u7406\u5404\u79cd\u65f6\u95f4\u5e8f\u5217\u7ec4\u4ef6<\/td>\n<td>\u590d\u6742\u53c2\u6570\u8c03\u6574<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>\u672a\u6765\u5c55\u671b<\/h2>\n<p>\u968f\u7740\u6280\u672f\u7684\u8fdb\u6b65\uff0c\u65f6\u95f4\u5e8f\u5217\u5b63\u8282\u6027\u5206\u89e3 (STL) \u7684\u6f5c\u529b\u4e5f\u5728\u4e0d\u65ad\u589e\u5f3a\u3002\u7ed3\u5408\u673a\u5668\u5b66\u4e60\u6280\u672f\u3001\u81ea\u52a8\u53c2\u6570\u8c03\u6574\u548c\u5904\u7406\u66f4\u591a\u6837\u5316\u7684\u6570\u636e\u7c7b\u578b\u53ef\u80fd\u4f1a\u589e\u5f3a\u5176\u529f\u80fd\u3002<\/p>\n<h2>\u4ee3\u7406\u670d\u52a1\u5668\u548c STL<\/h2>\n<p>\u4ee3\u7406\u670d\u52a1\u5668\u4e0e\u65f6\u95f4\u5e8f\u5217\u5b63\u8282\u6027\u5206\u89e3\u4e4b\u95f4\u7684\u5173\u7cfb\u5728\u4e8e\u6570\u636e\u6536\u96c6\u548c\u5206\u6790\u3002\u4ee3\u7406\u670d\u52a1\u5668\u6709\u52a9\u4e8e\u4ece\u5404\u79cd\u6765\u6e90\u6536\u96c6\u65f6\u95f4\u5e8f\u5217\u6570\u636e\uff0c\u7136\u540e\u53ef\u4ee5\u5bf9\u8fd9\u4e9b\u6570\u636e\u8fdb\u884c STL \u5904\u7406\uff0c\u4ee5\u53d1\u73b0\u9690\u85cf\u7684\u6a21\u5f0f\u3001\u8d8b\u52bf\u548c\u5468\u671f\u6027\u884c\u4e3a\u3002\u901a\u8fc7\u8bc6\u522b\u7f51\u7edc\u4f7f\u7528\u6a21\u5f0f\uff0c\u50cf OneProxy \u8fd9\u6837\u7684\u4ee3\u7406\u670d\u52a1\u5668\u63d0\u4f9b\u5546\u53ef\u4ee5\u4f18\u5316\u5176\u670d\u52a1\u3001\u9884\u6d4b\u9ad8\u5cf0\u4f7f\u7528\u671f\u5e76\u63d0\u9ad8\u6574\u4f53\u6027\u80fd\u3002<\/p>\n<h2>\u76f8\u5173\u94fe\u63a5<\/h2>\n<p>\u6709\u5173\u65f6\u95f4\u5e8f\u5217\u5b63\u8282\u6027\u5206\u89e3 (STL) \u7684\u66f4\u591a\u4fe1\u606f\uff0c\u8bf7\u8003\u8651\u63a2\u7d22\u4ee5\u4e0b\u8d44\u6e90\uff1a<\/p>\n<ul>\n<li><a href=\"https:\/\/www.jstor.org\/stable\/2686915\" target=\"_new\" rel=\"noopener nofollow\">Cleveland \u7b49\u4eba 1990 \u5e74\u5173\u4e8e STL \u7684\u8bba\u6587<\/a><\/li>\n<li><a href=\"https:\/\/otexts.com\/fpp3\/stl.html\" target=\"_new\" rel=\"noopener nofollow\">Hyndman \u7684 STL \u6587\u6863<\/a><\/li>\n<li><a href=\"https:\/\/www.itl.nist.gov\/div898\/handbook\/pmc\/section4\/pmc4.htm\" target=\"_new\" rel=\"noopener nofollow\">\u65f6\u95f4\u5e8f\u5217\u5206\u6790\u7b80\u4ecb<\/a><\/li>\n<\/ul>\n<p>\u603b\u4e4b\uff0c\u65f6\u95f4\u5e8f\u5217\u7684\u5b63\u8282\u5206\u89e3 (STL) \u662f\u4e00\u79cd\u901a\u7528\u65b9\u6cd5\uff0c\u53ef\u4ee5\u63ed\u793a\u65f6\u95f4\u5e8f\u5217\u6570\u636e\u4e2d\u7684\u9690\u85cf\u6210\u5206\uff0c\u6709\u52a9\u4e8e\u589e\u5f3a\u5404\u4e2a\u9886\u57df\u7684\u7406\u89e3\u548c\u5206\u6790\u3002\u5b83\u7684\u9002\u5e94\u6027\u3001\u7a33\u5065\u6027\u548c\u53ef\u89e3\u91ca\u6027\u4f7f\u5176\u6210\u4e3a\u63ed\u793a\u65f6\u95f4\u6a21\u5f0f\u548c\u534f\u52a9\u6570\u636e\u9a71\u52a8\u51b3\u7b56\u8fc7\u7a0b\u7684\u5b9d\u8d35\u5de5\u5177\u3002<\/p>","protected":false},"featured_media":470433,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-478852","wiki","type-wiki","status-publish","has-post-thumbnail","hentry"],"acf":{"faq_title":"Frequently Asked Questions about <mark>Seasonal Decomposition of a Time Series (STL) - Unveiling Temporal Patterns<\/mark>","faq_items":[{"question":"What is Seasonal Decomposition of a Time Series (STL)?","answer":"<p>Seasonal Decomposition of a Time Series (STL) is a statistical technique that breaks down time series data into its fundamental components: trend, seasonal variations, and irregular fluctuations. This process offers insights into the underlying patterns within the data, aiding in better analysis and understanding.<\/p>"},{"question":"How does STL work internally?","answer":"<p>STL utilizes three main components:<\/p><ol><li><strong>Trend Component<\/strong>: Captures long-term changes by smoothing the data using Loess regression.<\/li><li><strong>Seasonal Component<\/strong>: Reveals recurring patterns by averaging deviations from the trend within seasonal cycles.<\/li><li><strong>Residual Component<\/strong>: Represents unpredictable variations by subtracting the trend and seasonal components from the original data.<\/li><\/ol>"},{"question":"What are the advantages of using STL?","answer":"<p>STL boasts several benefits:<\/p><ul><li><strong>Flexibility<\/strong>: Accommodates various data types and irregular observations.<\/li><li><strong>Robustness<\/strong>: Robust Loess smoothing mitigates the impact of noisy data.<\/li><li><strong>Interpretability<\/strong>: Breaks down data into understandable components.<\/li><li><strong>Seasonality Detection<\/strong>: Effectively extracts complex seasonality patterns.<\/li><\/ul>"},{"question":"What are the applications of STL?","answer":"<p>STL finds applications in multiple fields:<\/p><ul><li><strong>Economics and Finance<\/strong>: Analyzing market trends and economic indicators.<\/li><li><strong>Environmental Science<\/strong>: Studying climate and ecological fluctuations.<\/li><li><strong>Retail and Sales<\/strong>: Understanding consumer behavior and sales patterns.<\/li><\/ul>"},{"question":"How does STL compare with similar methods?","answer":"<p>In comparison to moving averages, exponential smoothing, and ARIMA models, STL offers more comprehensive insights into different components of time series data, including trend, seasonality, and residuals.<\/p>"},{"question":"How can STL be improved in the future?","answer":"<p>Advancements in machine learning and automated parameter tuning could enhance STL's capabilities, making it even more adaptable to diverse data types and patterns.<\/p>"},{"question":"What's the connection between proxy servers and STL?","answer":"<p>Proxy servers assist in gathering time series data, which can be analyzed using STL to uncover hidden patterns. For instance, OneProxy utilizes STL to optimize its services, predict usage patterns, and improve overall performance.<\/p>"},{"question":"Where can I find more information about STL?","answer":"<p>For additional resources on STL, you can refer to the following links:<\/p><ul><li><a href=\"https:\/\/www.jstor.org\/stable\/2686915\" target=\"_new\">Cleveland et al.'s 1990 paper on STL<\/a><\/li><li><a href=\"https:\/\/otexts.com\/fpp3\/stl.html\" target=\"_new\">Hyndman's STL Documentation<\/a><\/li><li><a href=\"https:\/\/www.itl.nist.gov\/div898\/handbook\/pmc\/section4\/pmc4.htm\" target=\"_new\">Introduction to Time Series Analysis<\/a><\/li><\/ul>"}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki\/478852","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki"}],"about":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/types\/wiki"}],"version-history":[{"count":0,"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki\/478852\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/media\/470433"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/media?parent=478852"}],"curies":[{"name":"\u53ef\u6e7f\u6027\u7c89\u5242","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}