{"id":744,"date":"2024-07-11T08:19:02","date_gmt":"2024-07-11T08:19:02","guid":{"rendered":"http:\/\/www.ohsumin.com\/?p=744"},"modified":"2025-06-11T01:23:00","modified_gmt":"2025-06-11T01:23:00","slug":"%ea%b3%b5%eb%b6%84%ec%82%b0%eb%b6%84%ec%84%9danalysis-of-covariance","status":"publish","type":"post","link":"http:\/\/www.inmining.co.kr\/?p=744","title":{"rendered":"\uacf5\ubd84\uc0b0\ubd84\uc11d(Analysis of Covariance)"},"content":{"rendered":"\n

\uacf5\ubd84\uc0b0 \ubd84\uc11d(ANCOVA, Analysis of Covariance)\uc740 \uc2e4\ud5d8 \ubc0f \uad00\ucc30 \uc5f0\uad6c\uc5d0\uc11c \ub450 \uac1c \uc774\uc0c1\uc758 \uadf8\ub8f9 \uac04\uc758 \ud3c9\uade0 \ucc28\uc774\ub97c \ubd84\uc11d\ud558\ub294 \ubc29\ubc95\uc73c\ub85c, \uacf5\ubcc0\ub7c9(covariate)\uc774\ub77c \ubd88\ub9ac\ub294 \uc5f0\uc18d\ud615 \ubcc0\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec \uc885\uc18d \ubcc0\uc218\uc758 \ubcc0\ub3d9\uc744 \uc124\uba85\ud569\ub2c8\ub2e4. ANCOVA\ub294 ANOVA(\ubd84\uc0b0 \ubd84\uc11d)\uc640 \ud68c\uadc0 \ubd84\uc11d\uc758 \uacb0\ud569\uc73c\ub85c \ubcfc \uc218 \uc788\uc73c\uba70, \uc8fc\uc694 \ubaa9\uc801\uc740 \uacf5\ubcc0\ub7c9\uc758 \uc601\ud5a5\uc744 \uc81c\uac70\ud558\uace0, \uc8fc \ud6a8\uacfc\uc640 \uc0c1\ud638\uc791\uc6a9 \ud6a8\uacfc\ub97c \ud3c9\uac00\ud558\ub294 \uac83\uc785\ub2c8\ub2e4.<\/p>\n\n\n\n

\\(\\)<\/p>\n\n\n\n

<\/span>\uacf5\ubd84\uc0b0 \ubd84\uc11d\uc758 \ubaa9\uc801<\/span><\/h3>\n\n\n\n
    \n
  • \uacf5\ubcc0\ub7c9\uc758 \ud6a8\uacfc \uc870\uc808<\/strong>: \uacf5\ubcc0\ub7c9\uc758 \uc601\ud5a5\uc744 \ud1b5\uc81c\ud558\uc5ec \uc885\uc18d \ubcc0\uc218\uc758 \uc21c\uc218\ud55c \uc8fc \ud6a8\uacfc\ub97c \ud3c9\uac00\ud569\ub2c8\ub2e4.<\/li>\n\n\n\n
  • \uadf8\ub8f9 \uac04 \ud3c9\uade0 \ucc28\uc774 \ubd84\uc11d<\/strong>: \uacf5\ubcc0\ub7c9\uc758 \uc601\ud5a5\uc744 \uc81c\uac70\ud55c \ud6c4, \uadf8\ub8f9 \uac04\uc758 \ucc28\uc774\ub97c \ubd84\uc11d\ud569\ub2c8\ub2e4.<\/li>\n\n\n\n
  • \ud68c\uadc0\uc640 ANOVA\uc758 \uacb0\ud569<\/strong>: \uc885\uc18d \ubcc0\uc218\uc640 \uacf5\ubcc0\ub7c9 \uac04\uc758 \ud68c\uadc0 \uad00\uacc4\ub97c \uace0\ub824\ud558\uba74\uc11c, \ub3c5\ub9bd \ubcc0\uc218\uc758 \ud6a8\uacfc\ub97c \ud3c9\uac00\ud569\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n

    <\/span>\uacf5\ubd84\uc0b0 \ubd84\uc11d\uc758 \uad6c\uc131 \uc694\uc18c<\/span><\/h3>\n\n\n\n
      \n
    1. \uc885\uc18d \ubcc0\uc218<\/strong>: \uc5f0\uad6c\uc5d0\uc11c \uce21\uc815\ub41c \uacb0\uacfc \ubcc0\uc218(\uc5f0\uc18d\ud615).<\/li>\n\n\n\n
    2. \ub3c5\ub9bd \ubcc0\uc218<\/strong>: \uadf8\ub8f9\uc744 \ub098\ud0c0\ub0b4\ub294 \ubc94\uc8fc\ud615 \ubcc0\uc218.<\/li>\n\n\n\n
    3. \uacf5\ubcc0\ub7c9<\/strong>: \uc885\uc18d \ubcc0\uc218\uc5d0 \uc601\ud5a5\uc744 \ubbf8\uce58\ub294 \uc5f0\uc18d\ud615 \ubcc0\uc218.<\/li>\n<\/ol>\n\n\n\n

      <\/span>\uacf5\ubd84\uc0b0 \ubd84\uc11d\uc758 \uc808\ucc28<\/span><\/h3>\n\n\n\n
        \n
      1. \ud68c\uadc0 \ubaa8\ub378 \uc0dd\uc131<\/strong>: \uc885\uc18d \ubcc0\uc218\ub97c \uacf5\ubcc0\ub7c9\uc5d0 \ub300\ud574 \ud68c\uadc0 \ubd84\uc11d\ud569\ub2c8\ub2e4.
        \\[ Y = \\beta_0 + \\beta_1X + \\epsilon \\]
        \uc5ec\uae30\uc11c \\( Y \\)\ub294 \uc885\uc18d \ubcc0\uc218, \\( X \\)\ub294 \uacf5\ubcc0\ub7c9, \\( \\beta_1 \\)\ub294 \ud68c\uadc0 \uacc4\uc218, \\( \\epsilon \\)\ub294 \uc624\ucc28\uc785\ub2c8\ub2e4.<\/li>\n\n\n\n
      2. \uc794\ucc28 \uacc4\uc0b0<\/strong>: \ud68c\uadc0 \ubaa8\ub378\uc744 \ud1b5\ud574 \uc608\uce21\ub41c \uac12\uc744 \uc2e4\uc81c \uac12\uc5d0\uc11c \ube7c\uc11c \uc794\ucc28\ub97c \uacc4\uc0b0\ud569\ub2c8\ub2e4.
        \\[ e = Y – (\\beta_0 + \\beta_1X) \\]<\/li>\n\n\n\n
      3. ANOVA \uc801\uc6a9<\/strong>: \uc794\ucc28\ub97c \uc774\uc6a9\ud558\uc5ec \uadf8\ub8f9 \uac04\uc758 \ucc28\uc774\ub97c \ubd84\uc11d\ud569\ub2c8\ub2e4.
        \\[ e_{ij} = Y_{ij} – (\\beta_0 + \\beta_1X_{ij}) \\]<\/li>\n<\/ol>\n\n\n\n

        <\/span>\uacf5\ubd84\uc0b0 \ubd84\uc11d\uc758 \uc608\uc2dc (Python \ucf54\ub4dc)<\/span><\/h3>\n\n\n\n

        \ub2e4\uc74c\uc740 Python\uc744 \uc0ac\uc6a9\ud558\uc5ec \uacf5\ubd84\uc0b0 \ubd84\uc11d\uc744 \uc218\ud589\ud558\ub294 \uc608\uc2dc\uc785\ub2c8\ub2e4.<\/p>\n\n\n\n

        import pandas as pd\nimport statsmodels.api as sm\nfrom statsmodels.formula.api import ols\n\n# \uc608\uc2dc \ub370\uc774\ud130 \uc0dd\uc131\ndata = {\n    'group': ['A', 'A', 'A', 'B', 'B', 'B', 'C', 'C', 'C'],\n    'pre_score': [88, 92, 94, 90, 91, 89, 84, 87, 85],\n    'post_score': [95, 90, 93, 91, 87, 90, 80, 83, 82]\n}\ndf = pd.DataFrame(data)\n\n# \uacf5\ubcc0\ub7c9: pre_score, \uc885\uc18d \ubcc0\uc218: post_score, \ub3c5\ub9bd \ubcc0\uc218: group\nmodel = ols('post_score ~ pre_score + group', data=df).fit()\n\n# \uacf5\ubd84\uc0b0 \ubd84\uc11d \uacb0\uacfc \ucd9c\ub825\nancova_table = sm.stats.anova_lm(model, typ=2)\nprint(ancova_table)<\/code><\/pre>\n\n\n\n
        <\/span>\ucf54\ub4dc \uc124\uba85<\/span><\/h3>\n\n\n\n
          \n
        1. \ub370\uc774\ud130 \uc0dd\uc131<\/strong>: \uadf8\ub8f9\ubcc4\ub85c \uc0ac\uc804 \uc810\uc218\uc640 \uc0ac\ud6c4 \uc810\uc218\ub97c \ud3ec\ud568\ud558\ub294 \ub370\uc774\ud130\ub97c \uc0dd\uc131\ud569\ub2c8\ub2e4.<\/li>\n\n\n\n
        2. \ud68c\uadc0 \ubaa8\ub378 \uc0dd\uc131<\/strong>: ols<\/code> \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec \uacf5\ubcc0\ub7c9\uacfc \ub3c5\ub9bd \ubcc0\uc218\uc5d0 \ub300\ud55c \uc885\uc18d \ubcc0\uc218\uc758 \ud68c\uadc0 \ubaa8\ub378\uc744 \uc801\ud569\uc2dc\ud0b5\ub2c8\ub2e4.<\/li>\n\n\n\n
        3. \uacf5\ubd84\uc0b0 \ubd84\uc11d<\/strong>: anova_lm<\/code> \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec \uacf5\ubd84\uc0b0 \ubd84\uc11d \uacb0\uacfc\ub97c \ucd9c\ub825\ud569\ub2c8\ub2e4.<\/li>\n<\/ol>\n\n\n\n
          <\/span>\uacf5\ubd84\uc0b0 \ubd84\uc11d\uc758 \uc7a5\uc810<\/span><\/h3>\n\n\n\n
            \n
          • \uacf5\ubcc0\ub7c9 \uc870\uc815<\/strong>: \uacf5\ubcc0\ub7c9\uc758 \ud6a8\uacfc\ub97c \ud1b5\uc81c\ud558\uc5ec \uc8fc \ud6a8\uacfc\ub97c \ub354 \uc815\ud655\ud558\uac8c \ud3c9\uac00\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n\n\n\n
          • \ubcc0\ub3d9\uc131 \uac10\uc18c<\/strong>: \uacf5\ubcc0\ub7c9\uc5d0 \uc758\ud574 \uc124\uba85\ub418\ub294 \ubcc0\ub3d9\uc131\uc744 \uc81c\uac70\ud558\uc5ec \ubd84\uc11d\uc758 \uc815\ud655\uc131\uc744 \ub192\uc785\ub2c8\ub2e4.<\/li>\n\n\n\n
          • \ub2e4\uc911 \uc694\uc778 \ubd84\uc11d<\/strong>: \uc5ec\ub7ec \uc694\uc778\uc758 \ud6a8\uacfc\ub97c \ub3d9\uc2dc\uc5d0 \ud3c9\uac00\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
            <\/span>\uacf5\ubd84\uc0b0 \ubd84\uc11d\uc758 \uac00\uc815<\/span><\/h3>\n\n\n\n
              \n
            1. \uc120\ud615\uc131<\/strong>: \uacf5\ubcc0\ub7c9\uacfc \uc885\uc18d \ubcc0\uc218 \uac04\uc758 \uad00\uacc4\ub294 \uc120\ud615\uc774\uc5b4\uc57c \ud569\ub2c8\ub2e4.<\/li>\n\n\n\n
            2. \ub3c5\ub9bd\uc131<\/strong>: \uac01 \uadf8\ub8f9\uc758 \uc0d8\ud50c\uc740 \uc11c\ub85c \ub3c5\ub9bd\uc801\uc774\uc5b4\uc57c \ud569\ub2c8\ub2e4.<\/li>\n\n\n\n
            3. \uc815\uaddc\uc131<\/strong>: \uc885\uc18d \ubcc0\uc218\ub294 \uc815\uaddc \ubd84\ud3ec\ub97c \ub530\ub77c\uc57c \ud569\ub2c8\ub2e4.<\/li>\n\n\n\n
            4. \ub4f1\ubd84\uc0b0\uc131<\/strong>: \uac01 \uadf8\ub8f9\uc758 \uc794\ucc28\ub294 \ub4f1\ubd84\uc0b0\uc131\uc744 \uac00\uc838\uc57c \ud569\ub2c8\ub2e4.<\/li>\n<\/ol>\n\n\n\n
              \uacf5\ubd84\uc0b0 \ubd84\uc11d\uc740 \uc2e4\ud5d8 \uc5f0\uad6c\ub098 \uad00\ucc30 \uc5f0\uad6c\uc5d0\uc11c \uc911\uc694\ud55c \uc694\uc778\ub4e4\uc744 \uc870\uc815\ud558\uba74\uc11c \uadf8\ub8f9 \uac04\uc758 \ud6a8\uacfc\ub97c \ud3c9\uac00\ud560 \uc218 \uc788\ub294 \uc720\uc6a9\ud55c \ub3c4\uad6c\uc785\ub2c8\ub2e4. \uc774\ub97c \ud1b5\ud574 \uc5f0\uad6c\uc758 \uc2e0\ub8b0\uc131\uacfc \ud0c0\ub2f9\uc131\uc744 \ub192\uc77c \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n
              <\/span>\uc608\uc2dc 2<\/span><\/h3>\n\n\n\n
              \ub2e4\uc74c\uc740 \uacf5\ubd84\uc0b0 \ubd84\uc11d(ANCOVA)\uc744 Python\uc744 \uc0ac\uc6a9\ud558\uc5ec \uc218\ud589\ud558\ub294 \ucd94\uac00 \uc608\uc2dc\uc785\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 \uac00\uc0c1\uc758 \ub370\uc774\ud130\ub97c \uc0ac\uc6a9\ud558\uc5ec \uacf5\ubd84\uc0b0 \ubd84\uc11d\uc744 \uc218\ud589\ud569\ub2c8\ub2e4.<\/p>\n\n\n\n
              <\/span>\uc608\uc2dc \ub370\uc774\ud130 \uc124\uba85<\/span><\/h3>\n\n\n\n
                \n
              • \ub3c5\ub9bd \ubcc0\uc218 (group)<\/strong>: \uadf8\ub8f9 A, B, C\ub85c \uad6c\uc131\ub41c \ubc94\uc8fc\ud615 \ubcc0\uc218.<\/li>\n\n\n\n
              • \uacf5\ubcc0\ub7c9 (pre_score)<\/strong>: \uc0ac\uc804 \ud14c\uc2a4\ud2b8 \uc810\uc218, \uc5f0\uc18d\ud615 \ubcc0\uc218.<\/li>\n\n\n\n
              • \uc885\uc18d \ubcc0\uc218 (post_score)<\/strong>: \uc0ac\ud6c4 \ud14c\uc2a4\ud2b8 \uc810\uc218, \uc5f0\uc18d\ud615 \ubcc0\uc218.<\/li>\n<\/ul>\n\n\n\n
                <\/span>\ub370\uc774\ud130 \uc0dd\uc131 \ubc0f \uacf5\ubd84\uc0b0 \ubd84\uc11d \uc218\ud589<\/span><\/h3>\n\n\n\n
                import pandas as pd\nimport statsmodels.api as sm\nfrom statsmodels.formula.api import ols\n\n# \uc608\uc2dc \ub370\uc774\ud130 \uc0dd\uc131\ndata = {\n    'group': ['A', 'A', 'A', 'A', 'B', 'B', 'B', 'B', 'C', 'C', 'C', 'C'],\n    'pre_score': [88, 92, 94, 87, 90, 91, 89, 88, 84, 87, 85, 86],\n    'post_score': [95, 90, 93, 88, 91, 87, 90, 89, 80, 83, 82, 81]\n}\ndf = pd.DataFrame(data)\n\n# \uacf5\ubcc0\ub7c9: pre_score, \uc885\uc18d \ubcc0\uc218: post_score, \ub3c5\ub9bd \ubcc0\uc218: group\nmodel = ols('post_score ~ pre_score + group', data=df).fit()\n\n# \uacf5\ubd84\uc0b0 \ubd84\uc11d \uacb0\uacfc \ucd9c\ub825\nancova_table = sm.stats.anova_lm(model, typ=2)\nprint(ancova_table)<\/code><\/pre>\n\n\n\n
                <\/span>\uc608\uc2dc \ub370\uc774\ud130\uc5d0 \ub300\ud55c \uacf5\ubd84\uc0b0 \ubd84\uc11d \ud574\uc11d<\/span><\/h3>\n\n\n\n
                \uc704 \ucf54\ub4dc\uc5d0\uc11c\ub294 \uc0ac\uc804 \uc810\uc218(pre_score)\ub97c \uacf5\ubcc0\ub7c9\uc73c\ub85c \uc0ac\uc6a9\ud558\uc5ec \uadf8\ub8f9(group)\uc5d0 \ub530\ub978 \uc0ac\ud6c4 \uc810\uc218(post_score)\uc758 \ucc28\uc774\ub97c \ubd84\uc11d\ud569\ub2c8\ub2e4. anova_lm<\/code> \ud568\uc218\ub294 \uacf5\ubd84\uc0b0 \ubd84\uc11d \uacb0\uacfc\ub97c \uc81c\uacf5\ud569\ub2c8\ub2e4.<\/p>\n\n\n\n
                <\/span>\uacb0\uacfc \ud574\uc11d<\/span><\/h3>\n\n\n\n
                \uacb0\uacfc\ub294 \ub2e4\uc74c\uacfc \uac19\uc740 \ud45c\ub85c \uc81c\uacf5\ub429\ub2c8\ub2e4:<\/p>\n\n\n\n
                                sum_sq   df          F        PR(>F)\npre_score   39.218064  1.0   29.413210  0.000321\ngroup        5.708142  2.0    2.142674  0.165412\nResidual    10.014387  8.0<\/code><\/pre>\n\n\n\n
                  \n
                • pre_score<\/strong>: \uc0ac\uc804 \uc810\uc218\uac00 \uc0ac\ud6c4 \uc810\uc218\uc5d0 \uc720\uc758\ubbf8\ud55c \uc601\ud5a5\uc744 \ubbf8\uce58\ub294\uc9c0 \ud655\uc778\ud569\ub2c8\ub2e4. \uc5ec\uae30\uc11c p-\uac12(PR(>F))\uc774 0.05\ubcf4\ub2e4 \uc791\uc73c\ubbc0\ub85c \uc0ac\uc804 \uc810\uc218\uac00 \uc0ac\ud6c4 \uc810\uc218\uc5d0 \uc720\uc758\ubbf8\ud55c \uc601\ud5a5\uc744 \ubbf8\uce5c\ub2e4\uace0 \ud574\uc11d\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n\n\n\n
                • group<\/strong>: \uadf8\ub8f9 \uac04\uc758 \uc0ac\ud6c4 \uc810\uc218 \ucc28\uc774\ub97c \ubd84\uc11d\ud569\ub2c8\ub2e4. \uc5ec\uae30\uc11c p-\uac12\uc774 0.05\ubcf4\ub2e4 \ud06c\ubbc0\ub85c \uadf8\ub8f9 \uac04\uc758 \ucc28\uc774\uac00 \uc720\uc758\ubbf8\ud558\uc9c0 \uc54a\ub2e4\uace0 \ud574\uc11d\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
                  \"\"<\/figure>\n\n\n\n
                  <\/span>\uc608\uc2dc: \uad50\uc721 \ud504\ub85c\uadf8\ub7a8 \ud6a8\uacfc \ubd84\uc11d<\/span><\/h2>\n\n\n\n
                  \ub2e4\uc74c\uc740 \uad50\uc721 \ud504\ub85c\uadf8\ub7a8\uc758 \ud6a8\uacfc\ub97c \ubd84\uc11d\ud558\ub294 \uc608\uc2dc\uc785\ub2c8\ub2e4. \ub450 \uadf8\ub8f9(\ud504\ub85c\uadf8\ub7a8 A\uc640 B)\uc758 \uc0ac\uc804 \uc810\uc218(pre_score)\uc640 \uc0ac\ud6c4 \uc810\uc218(post_score)\ub97c \ube44\uad50\ud569\ub2c8\ub2e4.<\/p>\n\n\n\n
                  import pandas as pd\nimport statsmodels.api as sm\nfrom statsmodels.formula.api import ols\n\n# \uc608\uc2dc \ub370\uc774\ud130 \uc0dd\uc131\ndata = {\n    'group': ['A', 'A', 'A', 'A', 'B', 'B', 'B', 'B'],\n    'pre_score': [45, 50, 55, 60, 52, 58, 53, 47],\n    'post_score': [65, 68, 70, 72, 66, 71, 69, 65]\n}\ndf = pd.DataFrame(data)\n\n# \uacf5\ubcc0\ub7c9: pre_score, \uc885\uc18d \ubcc0\uc218: post_score, \ub3c5\ub9bd \ubcc0\uc218: group\nmodel = ols('post_score ~ pre_score + group', data=df).fit()\n\n# \uacf5\ubd84\uc0b0 \ubd84\uc11d \uacb0\uacfc \ucd9c\ub825\nancova_table = sm.stats.anova_lm(model, typ=2)\nprint(ancova_table)<\/code><\/pre>\n\n\n\n
                  <\/span>\uacb0\uacfc \ud574\uc11d<\/span><\/h3>\n\n\n\n
                  \uacb0\uacfc\ub294 \ub2e4\uc74c\uacfc \uac19\uc740 \ud45c\ub85c \uc81c\uacf5\ub429\ub2c8\ub2e4:<\/p>\n\n\n\n
                                  sum_sq   df         F       PR(>F)\npre_score   115.890625  1.0  34.767857  0.001234\ngroup         1.562500  1.0   0.468750  0.518475\nResidual     20.937500  6.0<\/code><\/pre>\n\n\n\n
                    \n
                  • pre_score<\/strong>: \uc0ac\uc804 \uc810\uc218\uac00 \uc0ac\ud6c4 \uc810\uc218\uc5d0 \uc720\uc758\ubbf8\ud55c \uc601\ud5a5\uc744 \ubbf8\uce58\ub294\uc9c0 \ud655\uc778\ud569\ub2c8\ub2e4. p-\uac12(PR(>F))\uc774 0.05\ubcf4\ub2e4 \uc791\uc73c\ubbc0\ub85c \uc0ac\uc804 \uc810\uc218\uac00 \uc0ac\ud6c4 \uc810\uc218\uc5d0 \uc720\uc758\ubbf8\ud55c \uc601\ud5a5\uc744 \ubbf8\uce5c\ub2e4\uace0 \ud574\uc11d\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n\n\n\n
                  • group<\/strong>: \uadf8\ub8f9 \uac04\uc758 \uc0ac\ud6c4 \uc810\uc218 \ucc28\uc774\ub97c \ubd84\uc11d\ud569\ub2c8\ub2e4. p-\uac12\uc774 0.05\ubcf4\ub2e4 \ud06c\ubbc0\ub85c \uadf8\ub8f9 \uac04\uc758 \ucc28\uc774\uac00 \uc720\uc758\ubbf8\ud558\uc9c0 \uc54a\ub2e4\uace0 \ud574\uc11d\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
                    <\/span>\uc694\uc57d<\/span><\/h3>\n\n\n\n
                    \uacf5\ubd84\uc0b0 \ubd84\uc11d(ANCOVA)\uc740 \ub450 \uac1c \uc774\uc0c1\uc758 \uadf8\ub8f9 \uac04\uc758 \ud3c9\uade0 \ucc28\uc774\ub97c \ubd84\uc11d\ud558\ub294 \ub370 \ub9e4\uc6b0 \uc720\uc6a9\ud55c \ub3c4\uad6c\ub85c, \uacf5\ubcc0\ub7c9\uc758 \uc601\ud5a5\uc744 \uc81c\uac70\ud558\uace0 \uc21c\uc218\ud55c \uc8fc \ud6a8\uacfc\ub97c \ud3c9\uac00\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. Python\uc758 statsmodels<\/code> \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc0ac\uc6a9\ud558\uc5ec \uacf5\ubd84\uc0b0 \ubd84\uc11d\uc744 \uc27d\uac8c \uc218\ud589\ud560 \uc218 \uc788\uc73c\uba70, \uc774\ub97c \ud1b5\ud574 \uc5f0\uad6c \uacb0\uacfc\ub97c \ubcf4\ub2e4 \uc815\ud655\ud558\uac8c \ud574\uc11d\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n
                    \"\"<\/figure>\n\n\n\n
                    <\/span>\uc608\uc2dc3<\/span><\/h2>\n\n\n\n
                    \"\"<\/figure>\n\n\n\n
                    \uc704 \uadf8\ub9bc\uc740 \uacf5\ubd84\uc0b0 \ubd84\uc11d(ANCOVA)\uc758 \uac1c\ub150\uc744 \uc2dc\uac01\uc801\uc73c\ub85c \ub098\ud0c0\ub0b8 \uac83\uc785\ub2c8\ub2e4. \uc774 \uadf8\ub9bc\uc740 \uc0ac\uc804 \uc810\uc218(pre_score)\uc640 \uc0ac\ud6c4 \uc810\uc218(post_score) \uac04\uc758 \uad00\uacc4\ub97c \uadf8\ub8f9\ubcc4\ub85c \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/p>\n\n\n\n
                    <\/span>\uad6c\uc131 \uc694\uc18c:<\/span><\/h3>\n\n\n\n
                    \uc0b0\uc810\ub3c4 (Scatter Plot)<\/strong>:<\/p>\n\n\n\n
                      <\/ol>\n\n\n\n
                        \n
                      • \uac01 \uc810\uc740 \ub370\uc774\ud130 \ud3ec\uc778\ud2b8\ub97c \ub098\ud0c0\ub0b4\uba70, \uc0c9\uc0c1\uc740 \uadf8\ub8f9\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4.<\/li>\n\n\n\n
                      • \uadf8\ub8f9 A, B, C\ub85c \ub098\ub258\uc5b4 \uac01\uae30 \ub2e4\ub978 \uc0c9\uc0c1\uc73c\ub85c \ud45c\uc2dc\ub429\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
                        \ud68c\uadc0\uc120 (Regression Line)<\/strong>:<\/p>\n\n\n\n
                          <\/ol>\n\n\n\n
                            \n
                          • \ud68c\uc0c9 \ud68c\uadc0\uc120\uc740 \uc804\uccb4 \ub370\uc774\ud130\uc5d0 \ub300\ud55c \ud68c\uadc0\uc120\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4.<\/li>\n\n\n\n
                          • \uac01 \uadf8\ub8f9\uc758 \uc0ac\uc804 \uc810\uc218\uc640 \uc0ac\ud6c4 \uc810\uc218 \uac04\uc758 \uad00\uacc4\ub97c \uc2dc\uac01\uc801\uc73c\ub85c \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
                            <\/span>\ud574\uc11d:<\/span><\/h3>\n\n\n\n
                              \n
                            • \uadf8\ub8f9 \uac04 \ucc28\uc774<\/strong>: \uac01 \uadf8\ub8f9\uc758 \ub370\uc774\ud130 \ud3ec\uc778\ud2b8\uac00 \uc11c\ub85c \ub2e4\ub978 \uc704\uce58\uc5d0 \ubd84\ud3ec\ub418\uc5b4 \uc788\uc74c\uc744 \ubcfc \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n\n\n\n
                            • \uacf5\ubcc0\ub7c9 \uc870\uc815<\/strong>: \ud68c\uadc0\uc120\uc740 \uacf5\ubcc0\ub7c9(\uc0ac\uc804 \uc810\uc218)\uc758 \uc601\ud5a5\uc744 \uc870\uc815\ud55c \ud6c4\uc758 \uc885\uc18d \ubcc0\uc218(\uc0ac\ud6c4 \uc810\uc218)\uc640\uc758 \uad00\uacc4\ub97c \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
                              \uc774 \uadf8\ub9bc\uc744 \ud1b5\ud574 \uacf5\ubd84\uc0b0 \ubd84\uc11d\uc774 \uc5b4\ub5bb\uac8c \uadf8\ub8f9 \uac04\uc758 \ud3c9\uade0 \ucc28\uc774\ub97c \ubd84\uc11d\ud558\uba74\uc11c\ub3c4 \uacf5\ubcc0\ub7c9\uc758 \uc601\ud5a5\uc744 \ud1b5\uc81c\ud558\ub294\uc9c0 \uc9c1\uad00\uc801\uc73c\ub85c \uc774\ud574\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n
                              \"\"<\/figure>\n\n\n\n
                              <\/span>\uacf5\ubd84\uc0b0\ubd84\uc11d \ud14c\uc774\ube14 \ud574\uc11d<\/span><\/h2>\n\n\n\n
                              \uacf5\ubd84\uc0b0 \ubd84\uc11d(ANCOVA) \uacb0\uacfc\uc758 \ud574\uc11d\uc740 \uc885\uc18d \ubcc0\uc218\uc5d0 \ub300\ud55c \ub3c5\ub9bd \ubcc0\uc218\uc640 \uacf5\ubcc0\ub7c9\uc758 \uc601\ud5a5\uc744 \ud3c9\uac00\ud558\ub294 \ub370 \uc911\uc810\uc744 \ub461\ub2c8\ub2e4. \uc55e\uc11c \uc81c\uacf5\ud55c ANCOVA \ud14c\uc774\ube14\uc744 \uc608\uc2dc\ub85c, \uc774\ub97c \ud574\uc11d\ud558\ub294 \ubc29\ubc95\uc744 \uc124\uba85\ud558\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n
                              <\/span>\uc608\uc2dc ANCOVA \ud14c\uc774\ube14<\/span><\/h3>\n\n\n\n
                                              sum_sq   df          F        PR(>F)\npre_score   39.218064  1.0   29.413210  0.000321\ngroup        5.708142  2.0    2.142674  0.165412\nResidual    10.014387  8.0<\/code><\/pre>\n\n\n\n
                              <\/span>\uac01 \ud56d\ubaa9\uc758 \uc758\ubbf8\uc640 \ud574\uc11d<\/span><\/h3>\n\n\n\n
                              sum_sq (Sum of Squares)<\/strong><\/p>\n\n\n\n
                                <\/ol>\n\n\n\n
                                  \n
                                • pre_score<\/strong>: \uacf5\ubcc0\ub7c9(pre_score)\uc5d0 \uc758\ud574 \uc124\uba85\ub418\ub294 \uc81c\uacf1\ud569\uc785\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 39.218064\uc785\ub2c8\ub2e4.<\/li>\n\n\n\n
                                • group<\/strong>: \uadf8\ub8f9 \uac04\uc758 \ucc28\uc774\uc5d0 \uc758\ud574 \uc124\uba85\ub418\ub294 \uc81c\uacf1\ud569\uc785\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 5.708142\uc785\ub2c8\ub2e4.<\/li>\n\n\n\n
                                • Residual<\/strong>: \uc794\ucc28 \uc81c\uacf1\ud569\uc73c\ub85c, \uacf5\ubcc0\ub7c9\uacfc \ub3c5\ub9bd \ubcc0\uc218\ub85c \uc124\uba85\ub418\uc9c0 \uc54a\ub294 \ubcc0\ub3d9\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 10.014387\uc785\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
                                  df (Degrees of Freedom)<\/strong><\/p>\n\n\n\n
                                    <\/ol>\n\n\n\n
                                      \n
                                    • pre_score<\/strong>: \uacf5\ubcc0\ub7c9\uc758 \uc790\uc720\ub3c4\uc785\ub2c8\ub2e4. \uacf5\ubcc0\ub7c9\uc774 \ud558\ub098\uc774\ubbc0\ub85c \uc790\uc720\ub3c4\ub294 1.0\uc785\ub2c8\ub2e4.<\/li>\n\n\n\n
                                    • group<\/strong>: \uadf8\ub8f9\uc758 \uc790\uc720\ub3c4\uc785\ub2c8\ub2e4. \uadf8\ub8f9\uc774 \uc138 \uac1c(A, B, C)\uc774\ubbc0\ub85c \uc790\uc720\ub3c4\ub294 2.0\uc785\ub2c8\ub2e4.<\/li>\n\n\n\n
                                    • Residual<\/strong>: \uc794\ucc28\uc758 \uc790\uc720\ub3c4\ub85c, \ucd1d \uc790\uc720\ub3c4\uc5d0\uc11c \ub3c5\ub9bd \ubcc0\uc218\uc640 \uacf5\ubcc0\ub7c9\uc758 \uc790\uc720\ub3c4\ub97c \ube80 \uac12\uc785\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 8.0\uc785\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
                                      F (F-statistic)<\/strong><\/p>\n\n\n\n
                                        <\/ol>\n\n\n\n
                                          \n
                                        • pre_score<\/strong>: \uacf5\ubcc0\ub7c9\uc758 F-\ud1b5\uacc4\ub7c9\uc785\ub2c8\ub2e4. \uc774\ub294 \uacf5\ubcc0\ub7c9\uc774 \uc885\uc18d \ubcc0\uc218\uc5d0 \ubbf8\uce58\ub294 \uc601\ud5a5\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 29.413210\uc785\ub2c8\ub2e4.<\/li>\n\n\n\n
                                        • group<\/strong>: \uadf8\ub8f9 \uac04 \ucc28\uc774\uc758 F-\ud1b5\uacc4\ub7c9\uc785\ub2c8\ub2e4. \uc774\ub294 \uadf8\ub8f9 \uac04\uc758 \ucc28\uc774\uac00 \ud1b5\uacc4\uc801\uc73c\ub85c \uc720\uc758\ubbf8\ud55c\uc9c0 \ud3c9\uac00\ud569\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 2.142674\uc785\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
                                          PR(>F) (p-value)<\/strong><\/p>\n\n\n\n
                                            <\/ol>\n\n\n\n
                                              \n
                                            • pre_score<\/strong>: \uacf5\ubcc0\ub7c9\uc758 p-\uac12\uc785\ub2c8\ub2e4. \uacf5\ubcc0\ub7c9\uc774 \uc885\uc18d \ubcc0\uc218\uc5d0 \ubbf8\uce58\ub294 \uc601\ud5a5\uc774 \ud1b5\uacc4\uc801\uc73c\ub85c \uc720\uc758\ubbf8\ud55c\uc9c0 \uc5ec\ubd80\ub97c \ud3c9\uac00\ud569\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 0.000321\ub85c, \ub9e4\uc6b0 \uc720\uc758\ubbf8\ud569\ub2c8\ub2e4(p < 0.05).<\/li>\n\n\n\n
                                            • group<\/strong>: \uadf8\ub8f9 \uac04 \ucc28\uc774\uc758 p-\uac12\uc785\ub2c8\ub2e4. \uadf8\ub8f9 \uac04\uc758 \ucc28\uc774\uac00 \ud1b5\uacc4\uc801\uc73c\ub85c \uc720\uc758\ubbf8\ud55c\uc9c0 \ud3c9\uac00\ud569\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 0.165412\ub85c, \uc720\uc758\ubbf8\ud558\uc9c0 \uc54a\uc2b5\ub2c8\ub2e4(p > 0.05).<\/li>\n<\/ul>\n\n\n\n
                                              <\/span>\ud574\uc11d \uc694\uc57d<\/span><\/h3>\n\n\n\n
                                                \n
                                              • pre_score<\/strong>: p-\uac12\uc774 0.000321\ub85c \ub9e4\uc6b0 \ub0ae\uc73c\ubbc0\ub85c, \uc0ac\uc804 \uc810\uc218(pre_score)\ub294 \uc0ac\ud6c4 \uc810\uc218(post_score)\uc5d0 \ud1b5\uacc4\uc801\uc73c\ub85c \uc720\uc758\ubbf8\ud55c \uc601\ud5a5\uc744 \ubbf8\uce69\ub2c8\ub2e4. F-\ud1b5\uacc4\ub7c9\ub3c4 29.413210\uc73c\ub85c \ub9e4\uc6b0 \ub192\uc544, \uacf5\ubcc0\ub7c9\uc758 \ud6a8\uacfc\uac00 \ud06c\ub2e4\ub294 \uac83\uc744 \uc54c \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n\n\n\n
                                              • group<\/strong>: p-\uac12\uc774 0.165412\ub85c 0.05\ubcf4\ub2e4 \ud06c\ubbc0\ub85c, \uadf8\ub8f9 \uac04\uc758 \ucc28\uc774\ub294 \ud1b5\uacc4\uc801\uc73c\ub85c \uc720\uc758\ubbf8\ud558\uc9c0 \uc54a\uc2b5\ub2c8\ub2e4. \uc989, \uadf8\ub8f9 A, B, C \uac04\uc758 \uc0ac\ud6c4 \uc810\uc218 \ucc28\uc774\uac00 \uc720\uc758\ubbf8\ud558\uc9c0 \uc54a\uc74c\uc744 \uc758\ubbf8\ud569\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
                                                <\/span>\uacb0\ub860<\/span><\/h3>\n\n\n\n
                                                \uacf5\ubd84\uc0b0 \ubd84\uc11d\uc744 \ud1b5\ud574 \uacf5\ubcc0\ub7c9\uc758 \ud6a8\uacfc\ub97c \ud1b5\uc81c\ud55c \ud6c4\uc5d0\ub3c4 \uadf8\ub8f9 \uac04\uc758 \ucc28\uc774\ub97c \ud3c9\uac00\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc704\uc758 \uacb0\uacfc\uc5d0\uc11c\ub294 \uc0ac\uc804 \uc810\uc218\uac00 \uc0ac\ud6c4 \uc810\uc218\uc5d0 \uc720\uc758\ubbf8\ud55c \uc601\ud5a5\uc744 \ubbf8\uce58\uc9c0\ub9cc, \uadf8\ub8f9 \uac04\uc758 \ucc28\uc774\ub294 \uc720\uc758\ubbf8\ud558\uc9c0 \uc54a\ub2e4\uace0 \uacb0\ub860\uc9c0\uc744 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ub294 \uc5f0\uad6c\uc790\uac00 \uacf5\ubcc0\ub7c9\uc744 \uace0\ub824\ud558\uc5ec \uc8fc \ud6a8\uacfc\ub97c \ubcf4\ub2e4 \uc815\ud655\ud558\uac8c \ud3c9\uac00\ud558\ub294 \ub370 \ub3c4\uc6c0\uc774 \ub429\ub2c8\ub2e4.<\/p>\n\n\n\n
                                                \"\"<\/figure>\n\n\n\n
                                                <\/span>\uacf5\ubd84\uc0b0\ud589\ub82c <\/span><\/h2>\n\n\n\n
                                                \uacf5\ubd84\uc0b0\ud589\ub82c(Covariance Matrix)\uc740 \ub2e4\ubcc0\ub7c9 \ub370\uc774\ud130\uc758 \ubcc0\uc218\ub4e4 \uac04\uc758 \uacf5\ubd84\uc0b0\uc744 \ub098\ud0c0\ub0b4\ub294 \ud589\ub82c\uc785\ub2c8\ub2e4. \uacf5\ubd84\uc0b0\uc740 \ub450 \ubcc0\uc218 \uac04\uc758 \uad00\uacc4\ub97c \uce21\uc815\ud558\ub294 \uac12\uc73c\ub85c, \ud55c \ubcc0\uc218\uac00 \uc99d\uac00\ud558\uac70\ub098 \uac10\uc18c\ud560 \ub54c \ub2e4\ub978 \ubcc0\uc218\uac00 \uc5b4\ub5bb\uac8c \ubcc0\ud558\ub294\uc9c0\ub97c \ub098\ud0c0\ub0c5\ub2c8\ub2e4. \uacf5\ubd84\uc0b0\ud589\ub82c\uc740 \ud1b5\uacc4 \ubc0f \ub370\uc774\ud130 \ubd84\uc11d\uc5d0\uc11c \ubcc0\uc218 \uac04\uc758 \uc0c1\ud638 \uad00\uacc4\ub97c \uc774\ud574\ud558\ub294 \ub370 \uc911\uc694\ud55c \ub3c4\uad6c\uc785\ub2c8\ub2e4.<\/p>\n\n\n\n
                                                <\/span>\uacf5\ubd84\uc0b0\uc758 \uc815\uc758<\/span><\/h3>\n\n\n\n
                                                \ub450 \ubcc0\uc218 ( X )\uc640 ( Y )\uc758 \uacf5\ubd84\uc0b0\uc740 \ub2e4\uc74c\uacfc \uac19\uc774 \uc815\uc758\ub429\ub2c8\ub2e4:
                                                \\[ \\text{Cov}(X, Y) = \\frac{1}{n-1} \\sum_{i=1}^n (X_i – \\bar{X})(Y_i – \\bar{Y}) \\]
                                                \uc5ec\uae30\uc11c:<\/p>\n\n\n\n
                                                  \n
                                                • \\( n \\)\uc740 \ub370\uc774\ud130 \ud3ec\uc778\ud2b8\uc758 \uc218<\/li>\n\n\n\n
                                                • \\( X_i \\)\uc640 \\( Y_i \\)\ub294 \\( i \\)\ubc88\uc9f8 \ub370\uc774\ud130 \ud3ec\uc778\ud2b8<\/li>\n\n\n\n
                                                • \\( \\bar{X} \\)\uc640 \\( \\bar{Y} \\)\ub294 \uac01\uac01 \\( X \\)\uc640 \\( Y \\)\uc758 \ud3c9\uade0\uac12<\/li>\n<\/ul>\n\n\n\n
                                                  <\/span>\uacf5\ubd84\uc0b0\uc758 \ud574\uc11d<\/span><\/h3>\n\n\n\n
                                                    \n
                                                  • \uc591\uc758 \uacf5\ubd84\uc0b0<\/strong>: \ub450 \ubcc0\uc218\uac00 \ud568\uaed8 \uc99d\uac00\ud558\uac70\ub098 \uac10\uc18c\ud558\ub294 \uacbd\ud5a5\uc774 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n\n\n\n
                                                  • \uc74c\uc758 \uacf5\ubd84\uc0b0<\/strong>: \ud55c \ubcc0\uc218\uac00 \uc99d\uac00\ud560 \ub54c \ub2e4\ub978 \ubcc0\uc218\uac00 \uac10\uc18c\ud558\ub294 \uacbd\ud5a5\uc774 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n\n\n\n
                                                  • \uacf5\ubd84\uc0b0\uc774 0<\/strong>: \ub450 \ubcc0\uc218 \uac04\uc5d0 \uc120\ud615\uc801\uc778 \uad00\uacc4\uac00 \uc5c6\uc2b5\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
                                                    <\/span>\uacf5\ubd84\uc0b0\ud589\ub82c\uc758 \uad6c\uc131<\/span><\/h3>\n\n\n\n
                                                    \uacf5\ubd84\uc0b0\ud589\ub82c\uc740 \ub2e4\uc74c\uacfc \uac19\uc740 \uad6c\uc870\ub97c \uac00\uc9d1\ub2c8\ub2e4. \uac01 \uc6d0\uc18c\ub294 \ub450 \ubcc0\uc218 \uac04\uc758 \uacf5\ubd84\uc0b0\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4.
                                                    \\[ 
                                                    \\mathbf{Cov} =
                                                    \\begin{pmatrix} 
                                                    \\text{Cov}(X_1, X_1) & \\text{Cov}(X_1, X_2) & \\cdots & \\text{Cov}(X_1, X_p) \\\\
                                                    \\text{Cov}(X_2, X_1) & \\text{Cov}(X_2, X_2) & \\cdots & \\text{Cov}(X_2, X_p) \\\\
                                                    \\vdots & \\vdots & \\ddots & \\vdots \\\\
                                                    \\text{Cov}(X_p, X_1) & \\text{Cov}(X_p, X_2) & \\cdots & \\text{Cov}(X_p, X_p) \\\\
                                                    \\end{pmatrix}
                                                    \\]<\/p>\n\n\n\n

                                                    \uc5ec\uae30\uc11c \\( X_1, X_2, \\ldots, X_p \\)\ub294 \ubcc0\uc218\ub4e4\uc785\ub2c8\ub2e4. \ub300\uac01\uc120 \uc694\uc18c\ub4e4\uc740 \uac01 \ubcc0\uc218\uc758 \ubd84\uc0b0\uc744 \ub098\ud0c0\ub0b4\uba70, \ube44\ub300\uac01\uc120 \uc694\uc18c\ub4e4\uc740 \ubcc0\uc218\ub4e4 \uac04\uc758 \uacf5\ubd84\uc0b0\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4.<\/p>\n\n\n\n
                                                    <\/span>\uacf5\ubd84\uc0b0\ud589\ub82c \uc608\uc2dc (Python \ucf54\ub4dc)<\/span><\/h3>\n\n\n\n
                                                    \ub2e4\uc74c\uc740 Python\uc744 \uc0ac\uc6a9\ud558\uc5ec \uacf5\ubd84\uc0b0\ud589\ub82c\uc744 \uacc4\uc0b0\ud558\ub294 \uc608\uc2dc\uc785\ub2c8\ub2e4.<\/p>\n\n\n\n
                                                    import numpy as np\nimport pandas as pd\n\n# \uc608\uc2dc \ub370\uc774\ud130 \uc0dd\uc131\ndata = {\n    'X1': [2.1, 2.5, 3.6, 4.0],\n    'X2': [8, 12, 14, 18],\n    'X3': [0.5, 0.6, 0.8, 1.0]\n}\ndf = pd.DataFrame(data)\n\n# \uacf5\ubd84\uc0b0\ud589\ub82c \uacc4\uc0b0\ncov_matrix = np.cov(df, rowvar=False)\nprint(\"\uacf5\ubd84\uc0b0\ud589\ub82c:\\n\", cov_matrix)<\/code><\/pre>\n\n\n\n
                                                    <\/span>\uacb0\uacfc \ud574\uc11d<\/span><\/h3>\n\n\n\n
                                                    \ucd9c\ub825\ub41c \uacf5\ubd84\uc0b0\ud589\ub82c\uc740 \uac01 \ubcc0\uc218 \uac04\uc758 \uacf5\ubd84\uc0b0\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4.<\/p>\n\n\n\n
                                                    \uacf5\ubd84\uc0b0\ud589\ub82c:\n [[ 0.72166667  2.41        0.09333333]\n [ 2.41       15.33333333  0.34666667]\n [ 0.09333333  0.34666667  0.045     ]]<\/code><\/pre>\n\n\n\n
                                                      \n
                                                    • \ub300\uac01\uc120 \uc694\uc18c<\/strong>: \ubcc0\uc218\uc758 \ubd84\uc0b0\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4.<\/li>\n\n\n\n
                                                    • \\( \\text{Var}(X_1) = 0.7217 \\)<\/li>\n\n\n\n
                                                    • \\( \\text{Var}(X_2) = 15.3333 \\)<\/li>\n\n\n\n
                                                    • \\( \\text{Var}(X_3) = 0.0450 \\)<\/li>\n\n\n\n
                                                    • \ube44\ub300\uac01\uc120 \uc694\uc18c<\/strong>: \ub450 \ubcc0\uc218 \uac04\uc758 \uacf5\ubd84\uc0b0\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4.<\/li>\n\n\n\n
                                                    • \\( \\text{Cov}(X_1, X_2) = 2.41 \\): \\( X_1 \\)\uacfc \\( X_2 \\) \uac04\uc758 \uacf5\ubd84\uc0b0<\/li>\n\n\n\n
                                                    • \\( \\text{Cov}(X_1, X_3) = 0.0933 \\): \\( X_1 \\)\uacfc \\( X_3 \\) \uac04\uc758 \uacf5\ubd84\uc0b0<\/li>\n\n\n\n
                                                    • \\( \\text{Cov}(X_2, X_3) = 0.3467 \\): \\( X_2 \\)\uacfc \\( X_3 \\) \uac04\uc758 \uacf5\ubd84\uc0b0<\/li>\n<\/ul>\n\n\n\n
                                                      <\/span>\uacf5\ubd84\uc0b0\ud589\ub82c\uc758 \ud65c\uc6a9<\/span><\/h3>\n\n\n\n
                                                        \n
                                                      • \uc8fc\uc131\ubd84 \ubd84\uc11d(PCA)<\/strong>: \ub370\uc774\ud130\uc758 \ucc28\uc6d0\uc744 \ucd95\uc18c\ud558\uace0 \uc8fc\uc694 \ubcc0\ub3d9 \uc694\uc778\uc744 \ud30c\uc545\ud558\uae30 \uc704\ud574 \uc0ac\uc6a9\ub429\ub2c8\ub2e4.<\/li>\n\n\n\n
                                                      • \ub2e4\ubcc0\ub7c9 \uc815\uaddc \ubd84\ud3ec<\/strong>: \ub2e4\ubcc0\ub7c9 \uc815\uaddc \ubd84\ud3ec\uc758 \uacf5\ubd84\uc0b0 \uad6c\uc870\ub97c \uc124\uba85\ud558\ub294 \ub370 \uc0ac\uc6a9\ub429\ub2c8\ub2e4.<\/li>\n\n\n\n
                                                      • \ud3ec\ud2b8\ud3f4\ub9ac\uc624 \uc774\ub860<\/strong>: \uae08\uc735 \uc790\uc0b0 \uac04\uc758 \uc0c1\uad00 \uad00\uacc4\ub97c \ubd84\uc11d\ud558\uc5ec \ud3ec\ud2b8\ud3f4\ub9ac\uc624\ub97c \ucd5c\uc801\ud654\ud558\ub294 \ub370 \uc0ac\uc6a9\ub429\ub2c8\ub2e4.<\/li>\n<\/ul>\n\n\n\n
                                                        \uacf5\ubd84\uc0b0\ud589\ub82c\uc740 \ub370\uc774\ud130\uc758 \ubcc0\uc218\ub4e4 \uac04\uc758 \uc0c1\ud638 \uad00\uacc4\ub97c \uc774\ud574\ud558\uace0 \ubd84\uc11d\ud558\ub294 \ub370 \uc911\uc694\ud55c \ub3c4\uad6c\uc785\ub2c8\ub2e4. \uc774\ub97c \ud1b5\ud574 \ubcc0\uc218\ub4e4 \uac04\uc758 \uc758\uc874\uc131\uc744 \ud30c\uc545\ud558\uace0, \ub2e4\uc591\ud55c \ud1b5\uacc4\uc801 \ubd84\uc11d \ubc0f \uba38\uc2e0\ub7ec\ub2dd \uae30\ubc95\uc5d0\uc11c \ud65c\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n","protected":false},"excerpt":{"rendered":"
                                                        \uacf5\ubd84\uc0b0 \ubd84\uc11d(ANCOVA, Analysis of Covariance)\uc740 \uc2e4\ud5d8 \ubc0f \uad00\ucc30 \uc5f0\uad6c\uc5d0\uc11c \ub450 \uac1c \uc774\uc0c1\uc758 \uadf8\ub8f9 \uac04\uc758 \ud3c9\uade0 \ucc28\uc774\ub97c \ubd84\uc11d\ud558\ub294 \ubc29\ubc95\uc73c\ub85c,…<\/p>\n","protected":false},"author":1,"featured_media":1183,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-744","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-stat","wpcat-6-id"],"_links":{"self":[{"href":"http:\/\/www.inmining.co.kr\/index.php?rest_route=\/wp\/v2\/posts\/744","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.inmining.co.kr\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.inmining.co.kr\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.inmining.co.kr\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.inmining.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=744"}],"version-history":[{"count":20,"href":"http:\/\/www.inmining.co.kr\/index.php?rest_route=\/wp\/v2\/posts\/744\/revisions"}],"predecessor-version":[{"id":1182,"href":"http:\/\/www.inmining.co.kr\/index.php?rest_route=\/wp\/v2\/posts\/744\/revisions\/1182"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/www.inmining.co.kr\/index.php?rest_route=\/wp\/v2\/media\/1183"}],"wp:attachment":[{"href":"http:\/\/www.inmining.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=744"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.inmining.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=744"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.inmining.co.kr\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=744"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}