{"id":1302,"date":"2023-07-26T23:09:57","date_gmt":"2023-07-26T23:09:57","guid":{"rendered":"https:\/\/statorials.org\/cn\/tukey-%e6%b5%8b%e8%af%95-python\/"},"modified":"2023-07-26T23:09:57","modified_gmt":"2023-07-26T23:09:57","slug":"tukey-%e6%b5%8b%e8%af%95-python","status":"publish","type":"post","link":"https:\/\/statorials.org\/cn\/tukey-%e6%b5%8b%e8%af%95-python\/","title":{"rendered":"\u5982\u4f55\u5728 python \u4e2d\u6267\u884c tukey \u6d4b\u8bd5"},"content":{"rendered":"

<\/p>\n

\n

\u5355\u5411\u65b9\u5dee\u5206\u6790<\/a>\u7528\u4e8e\u786e\u5b9a\u4e09\u4e2a\u6216\u66f4\u591a\u72ec\u7acb\u7ec4\u7684\u5e73\u5747\u503c\u4e4b\u95f4\u662f\u5426\u5b58\u5728\u7edf\u8ba1\u663e\u7740\u5dee\u5f02\u3002<\/span><\/p>\n

\u5982\u679c\u65b9\u5dee\u5206\u6790\u8868\u7684\u603b\u4f53p \u503c<\/a>\u4f4e\u4e8e\u4e00\u5b9a\u7684\u663e\u7740\u6027\u6c34\u5e73\uff0c\u5219\u6211\u4eec\u6709\u8db3\u591f\u7684\u8bc1\u636e\u8868\u660e\u81f3\u5c11\u5176\u4e2d\u4e00\u4e2a\u7ec4\u5747\u503c\u4e0e\u5176\u4ed6\u5747\u503c\u4e0d\u540c\u3002<\/span><\/p>\n

\u7136\u800c\uff0c\u8fd9\u5e76\u6ca1\u6709\u544a\u8bc9\u6211\u4eec\u54ea\u4e9b<\/em>\u7fa4\u4f53\u5f7c\u6b64\u4e0d\u540c\u3002\u8fd9\u53ea\u662f\u544a\u8bc9\u6211\u4eec\u5e76\u975e\u6240\u6709\u7ec4\u7684\u5e73\u5747\u503c\u90fd\u662f\u76f8\u7b49\u7684\u3002\u4e3a\u4e86\u51c6\u786e\u5730\u4e86\u89e3\u54ea\u4e9b\u7ec4\u5f7c\u6b64\u4e0d\u540c\uff0c\u6211\u4eec\u9700\u8981\u6267\u884c\u4e8b\u540e\u6d4b\u8bd5<\/a>\u3002<\/span><\/p>\n

\u6700\u5e38\u7528\u7684\u4e8b\u540e\u68c0\u9a8c\u4e4b\u4e00\u662fTukey \u68c0\u9a8c<\/strong>\uff0c\u5b83\u5141\u8bb8\u6211\u4eec\u5728\u6bcf\u7ec4\u5747\u503c\u4e4b\u95f4\u8fdb\u884c\u6210\u5bf9\u6bd4\u8f83\uff0c\u540c\u65f6\u63a7\u5236\u65cf\u8bef\u5dee\u7387<\/a>\u3002<\/span><\/p>\n

\u672c\u6559\u7a0b\u63d0\u4f9b\u4e86\u5982\u4f55\u5728 Python \u4e2d\u6267\u884c Tukey \u6d4b\u8bd5\u7684\u5206\u6b65\u793a\u4f8b\u3002<\/span><\/p>\n

\u7b2c1\u6b65\uff1a\u52a0\u8f7d\u5fc5\u8981\u7684\u5305\u548c\u51fd\u6570<\/strong><\/span><\/h3>\n

\u9996\u5148\uff0c\u6211\u4eec\u5c06\u5728Python\u4e2d\u52a0\u8f7d\u5fc5\u8981\u7684\u5305\u548c\u51fd\u6570\uff1a<\/span><\/p>\n

 import<\/span> pandas as<\/span> pd\nimport<\/span> numpy as<\/span> np\nfrom<\/span> scipy. stats<\/span> import<\/span> f_oneway\nfrom<\/span> statsmodels. stats<\/span> . multicomp<\/span> import<\/span> pairwise_tukeyhsd<\/strong><\/span><\/pre>\n
\u7b2c 2 \u6b65\uff1a\u62df\u5408\u65b9\u5dee\u5206\u6790\u6a21\u578b<\/strong><\/span><\/h3>\n
\u4ee5\u4e0b\u4ee3\u7801\u5c55\u793a\u4e86\u5982\u4f55\u521b\u5efa\u4e00\u4e2a\u5305\u542b\u4e09\u7ec4\uff08A\u3001B \u548c C\uff09\u7684\u5047\u6570\u636e\u96c6\uff0c\u5e76\u5bf9\u6570\u636e\u62df\u5408\u5355\u5411\u65b9\u5dee\u5206\u6790\u6a21\u578b\u4ee5\u786e\u5b9a\u6bcf\u7ec4\u7684\u5e73\u5747\u503c\u662f\u5426\u76f8\u7b49\uff1a<\/span><\/p>\n
 #enter data for three groups\n<\/span>a = [85, 86, 88, 75, 78, 94, 98, 79, 71, 80]\nb = [91, 92, 93, 90, 97, 94, 82, 88, 95, 96]\nc = [79, 78, 88, 94, 92, 85, 83, 85, 82, 81]\n\n#perform one-way ANOVA\n<\/span>f_oneway(a, b, c)\n\nF_onewayResult(statistic=5.167774552944481, pvalue=0.012582197136592609)<\/strong><\/pre>\n
\u6211\u4eec\u53ef\u4ee5\u770b\u5230\u65b9\u5dee\u5206\u6790\u8868\u4e2d\u7684\u603b\u4f53 p \u503c\u4e3a0.01258<\/strong> \u3002<\/span><\/p>\n
\u7531\u4e8e\u8fd9\u4e2a\u6570\u5b57\u5c0f\u4e8e0.05\uff0c\u6211\u4eec\u6709\u8db3\u591f\u7684\u8bc1\u636e\u8868\u660e\u6bcf\u7ec4\u4e2d\u7684\u5e73\u5747\u503c\u5e76\u4e0d\u76f8\u7b49\u3002<\/span><\/p>\n
\u56e0\u6b64\uff0c\u6211\u4eec\u53ef\u4ee5\u8fdb\u884c Tukey \u68c0\u9a8c\u6765\u51c6\u786e\u786e\u5b9a\u54ea\u4e9b\u7ec4\u5747\u503c\u4e0d\u540c\u3002<\/span><\/p>\n
\u7b2c 3 \u6b65\uff1a\u6267\u884c Tukey \u6d4b\u8bd5<\/strong><\/span><\/h3>\n
\u8981\u5728Python\u4e2d\u6267\u884cTukey\u6d4b\u8bd5\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528statsmodels<\/strong>\u5e93\u4e2d\u7684pairwise_tukeyhsd()<\/strong>\u51fd\u6570\uff1a<\/span><\/p>\n
 #create DataFrame to hold data\n<\/span>df = pd. DataFrame<\/span> ({'score': [85, 86, 88, 75, 78, 94, 98, 79, 71, 80,\n                             91, 92, 93, 90, 97, 94, 82, 88, 95, 96,\n                             79, 78, 88, 94, 92, 85, 83, 85, 82, 81],\n                   'group': np. repeat<\/span> (['a', 'b', 'c'], repeats= 10<\/span> )}) \n\n# perform Tukey's test\n<\/span>tukey = pairwise_tukeyhsd(endog=df['score'],\n                          groups=df['group'],\n                          alpha= 0.05<\/span> )\n\n#display results\n<\/span>print<\/span> (tukey)\n\n Multiple Comparison of Means - Tukey HSD, FWER=0.05 \n==================================================== ===\ngroup1 group2 meandiff p-adj lower upper reject\n-------------------------------------------------- ---\n     ab 8.4 0.0158 1.4272 15.3728 True\n     ac 1.3 0.8864 -5.6728 8.2728 False\n     bc -7.1 0.0453 -14.0728 -0.1272 True\n-------------------------------------------------- ---<\/strong><\/pre>\n
\u4ee5\u4e0b\u662f\u5982\u4f55\u89e3\u91ca\u7ed3\u679c\uff1a<\/span><\/span><\/p>\n