#r #loops #dplyr
Вопрос:
мы разработали цикл для получения терцилей нескольких переменных. Моя конечная цель состоит в том, чтобы создать terciles в соответствии с одной переменной, а затем сравнить (используя t.тест независимых групп) terciles, созданные для остальных переменных. Проблема в том, что у меня слишком много переменных, чтобы выполнять это вручную, поэтому я разработал цикл для перебора переменных, создания терцилей всех переменных и сравнения всех терцилей переменных. Я сделал это вручную с несколькими переменными, и результаты не совпадают с результатами, полученными с помощью кода цикла. Я проходил через это много раз, консультировался со статистиком моей исследовательской группы, но мы не знаем, что происходит
Небольшой фрагмент базы данных
samplelt;-structure(list(paciente = structure(c(6363, 6052, 6519, 6371, 6555, 6185, 6002, 6155, 6287, 6217), format.spss = "F5.0"), sexo_s1 = structure(c(1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L), .Label = c("Hombre", "Mujer" ), label = "Sexo", class = "factor"), edad_s1 = structure(c(66, 63, 72, 64, 72, 64, 70, 73, 63, 65), label = "Edad", format.spss = "F3.0"), peso1_v00 = structure(c(84.4, 76.2, 88.3, 122, 72, 86.4, 78, 79, 65.5, 98.8), label = "Peso: 1a determinación", format.spss = "F5.1"), cintura1_v00 = structure(c(104.5, 101, 107.5, 128.5, 107, 109.5, 105.5, 109, 97, 118.5), label = "Cintura: 1a determinación", format.spss = "F5.1"), tasis2_e_v00 = structure(c(155, 131, 148, 147, 136, 154, 130, 154, 147, 139), label = "TA: tensión arterial 2: sistólica", format.spss = "F4.0"), tadias2_e_v00 = structure(c(98, 76, 83, 84, 73, 80, 64, 80, 82, 78), label = "TA: tensión arterial 2: diastólica", format.spss = "F4.0"), p17_total_v00 = structure(c(10, 8, 10, 10, 10, 5, 11, 9, 8, 5), label = "Cuestionario de 17 puntos: Suma de puntuación de P17", format.spss = "F3.0"), geaf_tot_v00 = structure(c(1048.95, 4195.8, 4615.38, 3356.64, 839.16, 1608.39, 2958.04, 10209.79, 4335.66, 157.34), label = "AF: Gasto energético en actividad física total (MET•min/sem)", format.spss = "F8.2"), glucosa_v00 = structure(c(97, 122, 109, 201, 143, 139, 95, 110, 101, 181), label = "Analítica: Glucosa en mg/dL", format.spss = "F4.0"), albumi_v00 = structure(c(4.61, 4.52, 4.44, 4.48, 4.75, 4.87, 4.66, 4.86, 4.75, 4.99), label = "Analítica: Albúmina en g/dL", format.spss = "F6.2"), coltot_v00 = structure(c(221, 218, 130, 261, 190, 221, 199, 185, 233, 232), label = "Analítica: Colesterol total en mg/dL", format.spss = "F4.0"), hdl_v00 = structure(c(52, 54, 43, 42, 50, 67, 90, 50, 43, 51), label = "Analítica: Colesterol HDL en mg/dL", format.spss = "F4.0"), ldl_calc_v00 = structure(c(148, 135, 75, 173, 128, 133, 84, 109, 134, 144), label = "Analítica: LDL calculado en mg/dL si triglilt;=300", format.spss = "F4.0"), trigli_v00 = structure(c(103, 144, 58, 232, 60, 106, 126, 131, 282, 186), label = "Analítica: Triglicéridos en mg/dL", format.spss = "F5.0"), hba1c_v00 = structure(c(5.87, NA, 5.76, 7.98, 6.38, 7.01, NA, 6.51, 5.95, 9.01), label = "Analítica: Hemoglobina glicosilada (HbA1c %)", format.spss = "F5.2"), peso1_v66 = structure(c(76.6, 74.2, 82.2, 115, 64, 73.5, 74.4, 75.5, 59.5, 100), label = "Peso: 1a determinación", format.spss = "F5.1"), cintura1_v66 = structure(c(97.5, 99, 100, 122.5, 99, 101, 97, 104.5, 82.5, 119.5), label = "Cintura: 1a determinación", format.spss = "F5.1"), tasis2_e_v66 = structure(c(133, 129, 144, 160, 122, 123, 130, 155, 139, 153), label = "TA: tensión arterial 2: sistólica", format.spss = "F4.0"), tadias2_e_v66 = structure(c(87, 75, 77, 86, 68, 53, 64, 81, 73, 89), label = "TA: tensión arterial 2: diastólica", format.spss = "F4.0", display_width = 13L), p17_total_v66 = structure(c(12, 12, 12, 13, 11, 15, 14, 9, 15, 12), label = "Cuestionario de 17 puntos: Suma total de P17", format.spss = "F3.0"), geaf_tot_v66 = structure(c(4615.38, 0, 3461.54, 3356.64, 2097.9, 5132.87, 5118.88, 8111.89, 6772.03, 209.79), label = "AF: Gasto energético en actividad física total (MET•min/sem)", format.spss = "F8.2"), glucosa_v66 = structure(c(96, 107, 111, 173, 107, 98, 88, 118, 97, 185), label = "Analítica: Glucosa en mg/dL", format.spss = "F4.0"), albumi_v66 = structure(c(4.5, 4.93, 4.41, 4.42, 4.82, 4.54, 4.8, 4.46, 4.64, 4.84), label = "Analítica: Albúmina en g/dL", format.spss = "F6.2"), coltot_v66 = structure(c(215, 226, 156, 235, 154, 210, 283, 182, 225, 171), label = "Analítica: Colesterol total en mg/dL", format.spss = "F4.0"), hdl_v66 = structure(c(54, 65, 54, 40, 51, 73, 88, 58, 46, 37), label = "Analítica: Colesterol HDL en mg/dL", format.spss = "F4.0"), ldl_calc_v66 = structure(c(147, 133, 89, 156, 94, 123, 175, 106, 137, 102), label = "Analítica: LDL calculado en mg/dL si triglilt;=300", format.spss = "F4.0"), trigli_v66 = structure(c(72, 138, 63, 197, 47, 72, 99, 89, 209, 160), label = "Analítica: Triglicéridos en mg/dL", format.spss = "F5.0"), hba1c_v66 = structure(c(5.67, NA, 5.54, 8.05, 5.5, 5.95, NA, 6.17, 5.75, 8.98), label = "Analítica: Hemoglobina glicosilada (HbA1c %)", format.spss = "F5.2"), peso1_v01 = structure(c(75.2, 72, 82.4, 116, 63, 73.5, 72.4, 79, 58.5, 100), label = "Peso: 1a determinación", format.spss = "F5.1"), cintura1_v01 = structure(c(97.5, 98, 100, 122.5, 99, 101, 96, 106, 88.5, 119.5), label = "Cintura: 1a determinación", format.spss = "F5.1"), tasis2_e_v01 = structure(c(130, 137, 137, 183, 122, 152, 138, 139, 147, 154), label = "TA: tensión arterial 2: sistólica", format.spss = "F4.0"), tadias2_e_v01 = structure(c(84, 75, 72, 97, 71, 63, 72, 72, 60, 80), label = "TA: tensión arterial 2: diastólica", format.spss = "F4.0"), p17_total_v01 = structure(c(14, 11, 12, 10, 14, 15, 14, 11, 13, 12), label = "Cuestionario de 17 puntos: Suma total de P17", format.spss = "F3.0"), geaf_tot_v01 = structure(c(1678.32, 0, 4713.29, 559.44, 2769.23, 3212.12, 6853.15, 3776.22, 5841.49, 1048.95), label = "AF: Gasto energético en actividad física total (MET•min/sem)", format.spss = "F8.2"), glucosa_v01 = structure(c(93, 116, 100, 200, 112, 109, 105, 118, 94, 242), label = "Analítica: Glucosa en mg/dL", format.spss = "F4.0"), albumi_v01 = structure(c(4.57, 4.42, 4.68, 4.36, 4.98, 4.74, 4.87, 4.8, 4.81, 4.88), label = "Analítica: Albúmina en g/dL", format.spss = "F6.2"), coltot_v01 = structure(c(198, 236, 158, 270, 181, 187, 213, 204, 226, 192), label = "Analítica: Colesterol total en mg/dL", format.spss = "F4.0"), hdl_v01 = structure(c(58, 59, 48, 74, 60, 60, 87, 52, 49, 37), label = "Analítica: Colesterol HDL en mg/dL", format.spss = "F4.0"), ldl_calc_v01 = structure(c(128, 160, 99, 168, 107, 109, 105, 130, 147, 125), label = "Analítica: LDL calculado en mg/dL si triglilt;=300", format.spss = "F4.0"), trigli_v01 = structure(c(62, 83, 53, 139, 71, 90, 105, 110, 148, 151), label = "Analítica: Triglicéridos en mg/dL", format.spss = "F5.0"), hba1c_v01 = structure(c(5.61, 6.48, 5.53, 8.26, 5.86, 6.4, 5.26, 6.5, 5.7, 9.62), label = "Analítica: Hemoglobina glicosilada (HbA1c %)", format.spss = "F5.2"), i_hucpeptide_v00 = structure(c(704.96, NA, 675.43, 913.16, 1325.4, 840.98, NA, 1932.23, 459.83, 422.15), label = "Hu C-peptide (72) IMIM S'han substituit en les següents var els codis de inf i sup a limit de detecció per el limit inf i sup de detecció", format.spss = "F9.2", display_width = 13L), i_hucpeptide_v66 = structure(c(510.07, NA, 824.39, 926.34, 1199.51, 488.01, NA, 1461.11, 346.92, 679.09), label = "Hu C-peptide (72) IMIM", format.spss = "F9.2", display_width = 13L), i_hucpeptide_v01 = structure(c(432.38, NA, 737.66, 707.55, 1057.83, 699.08, NA, 1512.69, 345.69, 356.67), label = "Hu C-peptide (72) IMIM", format.spss = "F9.2", display_width = 12L), i_hughrelin_v00 = structure(c(1823.83, NA, 1050.11, 424.25, 198.06, 534.27, NA, 709.73, 117.69, 420.37), label = "Hu Ghrelin (26) IMIM", format.spss = "F7.2", display_width = 10L), i_hughrelin_v66 = structure(c(1407.04, NA, 746.93, 423.13, 207.63, 464.17, NA, 728.57, 113.23, 463.65), label = "Hu Ghrelin (26) IMIM", format.spss = "F7.2", display_width = 13L), i_hughrelin_v01 = structure(c(1133.96, NA, 670.23, 405.11, 260.24, 418.79, NA, 533.78, 122.07, 220.22), label = "Hu Ghrelin (26) IMIM", format.spss = "F7.2", display_width = 11L), i_hugip_v00 = structure(c(2.67, NA, 2.67, 2.67, 2.67, 2.67, NA, 2.67, 2.67, 2.67), label = "Hu GIP (14) IMIM", format.spss = "F9.2", display_width = 9L), i_hugip_v66 = structure(c(2.67, NA, 2.67, 2.67, 256.21, 2.67, NA, 2.67, 2.67, 2.67), label = "Hu GIP (14) IMIM", format.spss = "F9.2", display_width = 9L), i_hugip_v01 = structure(c(2.67, NA, 2.67, 24.74, 1165.16, 2.67, NA, 2.67, 2.67, 2.67), label = "Hu GIP (14) IMIM", format.spss = "F9.2", display_width = 9L), i_huglp1_v00 = structure(c(14.14, NA, 14.14, 216.2, 116.16, 228.14, NA, 359.48, 14.14, 219.02), label = "Hu GLP-1 (27) IMIM", format.spss = "F9.2", display_width = 9L), i_huglp1_v66 = structure(c(14.14, NA, 14.14, 202.5, 92.49, 278.55, NA, 400.16, 14.14, 274.62), label = "Hu GLP-1 (27) IMIM", format.spss = "F9.2", display_width = 9L), i_huglp1_v01 = structure(c(14.14, NA, 14.14, 202.5, 56.41, 303.77, NA, 451.91, 14.14, 58.55), label = "Hu GLP-1 (27) IMIM", format.spss = "F9.2", display_width = 9L), i_huglucagon_v00 = structure(c(273.5, NA, 231.41, 491.4, 542.39, 489.35, NA, 525.39, 241.55, 362.72), label = "Hu Glucagon (15) IMIM", format.spss = "F9.2", display_width = 11L), i_huglucagon_v66 = structure(c(94.97, NA, 276.26, 456.39, 306.42, 288.62, NA, 523.49, 143.14, 440.22), label = "Hu Glucagon (15) IMIM", format.spss = "F9.2", display_width = 11L), i_huglucagon_v01 = structure(c(182.57, NA, 233.95, 522.65, 10.48, 409.99, NA, 511.95, 216.47, 326.51), label = "Hu Glucagon (15) IMIM", format.spss = "F9.2", display_width = 9L), i_huinsulin_v00 = structure(c(97.94, NA, 171.33, 286.66, 390.29, 221.06, NA, 668.14, 125.36, 349.99), label = "Hu Insulin (12) IMIM", format.spss = "F7.2", display_width = 10L), i_huinsulin_v66 = structure(c(64.73, NA, 236.01, 255.05, 284.71, 73.24, NA, 392.19, 64.75, 381.42), label = "Hu Insulin (12) IMIM", format.spss = "F7.2", display_width = 9L), i_huinsulin_v01 = structure(c(52.52, NA, 213.4, 703.51, 247.48, 147.22, NA, 521.07, 98.66, 298.72), label = "Hu Insulin (12) IMIM", format.spss = "F7.2"), i_huleptin_v00 = structure(c(3493.7, NA, 1965.55, 4767.39, 5122.91, 12320.55, NA, 5367.22, 5217.35, 4682.33), label = "Hu Leptin (78) IMIM", format.spss = "F9.2", display_width = 9L), i_huleptin_v66 = structure(c(1779.33, NA, 1410.07, 3977.58, 3645.73, 3608.76, NA, 4489.67, 3499.88, 5136.43), label = "Hu Leptin (78) IMIM", format.spss = "F9.2", display_width = 9L), i_huleptin_v01 = structure(c(1865.4, NA, 1312.5, 8371.63, 2128.98, 6921.89, NA, 3754.42, 3092.53, 3921.64), label = "Hu Leptin (78) IMIM", format.spss = "F9.2", display_width = 9L), i_hupai1_v00 = structure(c(1581.8, NA, 1442.88, 3209.36, 2349.08, 3202.1, NA, 3177.94, 1463.04, 1701.4), label = "Hu PAI-1 (61) IMIM", format.spss = "F7.2"), i_hupai1_v66 = structure(c(1625.45, NA, 1093.24, 2152.24, 2083.31, 982.35, NA, 2245.81, 1611.27, 2645.45), label = "Hu PAI-1 (61) IMIM", format.spss = "F7.2"), i_hupai1_v01 = structure(c(1726.35, NA, 1166.53, 2511.45, 2268.52, 1592.08, NA, 2560.71, 1936.33, 2500.51), label = "Hu PAI-1 (61) IMIM", format.spss = "F7.2"), i_huresistin_v00 = structure(c(4292.62, NA, 3951.76, 4101.48, 6430.17, 5599.94, NA, 4855.32, 2144.19, 2421.1), label = "Hu Resistin (65) IMIM", format.spss = "F8.2", display_width = 9L), i_huresistin_v66 = structure(c(3201.72, NA, 4774.83, 4500.78, 7574.37, 4403.32, NA, 3224.09, 2102.65, 2003.5), label = "Hu Resistin (65) IMIM", format.spss = "F8.2", display_width = 7L), i_huresistin_v01 = structure(c(3872.84, NA, 4595.27, 3581.62, 9521.7, 4225.4, NA, 3150.62, 2093.1, 2048.76), label = "Hu Resistin (65) IMIM", format.spss = "F8.2", display_width = 6L), i_huvisfatin_v00 = structure(c(8.64, NA, 2.06, 560.32, 1498.58, 1356.01, NA, 632.07, 315.62, 461.86), label = "Hu Visfatin (22) IMIM", format.spss = "F9.2", display_width = 6L), i_huvisfatin_v66 = structure(c(8.64, NA, 8.64, 472.64, 683.91, 8.64, NA, 486.94, 8.64, 477.56), label = "Hu Visfatin (22) IMIM", format.spss = "F9.2", display_width = 6L), i_huvisfatin_v01 = structure(c(8.64, NA, 8.64, 2113.05, 1415.55, 800.08, NA, 155.08, 8.64, 108), label = "Hu Visfatin (22) IMIM", format.spss = "F9.2", display_width = 10L), col_rema_v00 = structure(c(21, 29, 12, 46, 12, 21, 25, 26, 56, 37), format.spss = "F8.2", display_width = 14L), col_rema_v66 = structure(c(14, 28, 13, 39, 9, 14, 20, 18, 42, 32), format.spss = "F8.2", display_width = 14L), col_rema_v01 = structure(c(12, 17, 11, 28, 14, 18, 21, 22, 30, 30), format.spss = "F8.2", display_width = 14L), homa_v00 = structure(c(422.230222222222, NA, 829.998666666667, 2560.82933333333, 2480.50977777778, 1365.65955555556, NA, 3266.46222222222, 562.727111111111, 2815.47511111111), format.spss = "F8.2", display_width = 10L), homa_v66 = structure(c(276.181333333333, NA, 1164.316, 1961.05111111111, 1353.95422222222, 319.000888888889, NA, 2056.81866666667, 279.144444444444, 3136.12), format.spss = "F8.2", display_width = 10L), homa_v01 = structure(c(217.082666666667, NA, 948.444444444444, 6253.42222222222, 1231.90044444444, 713.199111111111, NA, 2732.72266666667, 412.179555555556, 3212.89955555556), format.spss = "F8.2", display_width = 10L), d_homa_v66 = structure(c(-146.048888888889, NA, 334.317333333333, -599.778222222222, -1126.55555555556, -1046.65866666667, NA, -1209.64355555556, -283.582666666667, 320.644888888889 ), format.spss = "F8.2", display_width = 12L), d_homa_v01 = structure(c(-205.147555555556, NA, 118.445777777778, 3692.59288888889, -1248.60933333333, -652.460444444444, NA, -533.739555555555, -150.547555555556, 397.424444444444), format.spss = "F8.2", display_width = 12L), d_hughrelin_v66 = structure(c(-416.79, NA, -303.18, -1.12, 9.56999999999999, -70.1, NA, 18.84, -4.45999999999999, 43.28 ), format.spss = "F8.2", display_width = 18L), d_hughrelin_v01 = structure(c(-689.87, NA, -379.88, -19.14, 62.18, -115.48, NA, -175.95, 4.38, -200.15 ), format.spss = "F8.2", display_width = 18L), d_huinsulin_v66 = structure(c(-33.21, NA, 64.68, -31.61, -105.58, -147.82, NA, -275.95, -60.61, 31.43), format.spss = "F8.2", display_width = 17L), d_huinsulin_v01 = structure(c(-45.42, NA, 42.07, 416.85, -142.81, -73.84, NA, -147.07, -26.7, -51.27 ), format.spss = "F8.2", display_width = 17L), d_hucpeptide_v66 = structure(c(-194.89, NA, 148.96, 13.1800000000001, -125.89, -352.97, NA, -471.12, -112.91, 256.94), format.spss = "F8.2", display_width = 18L), d_hucpeptide_v01 = structure(c(-272.58, NA, 62.23, -205.61, -267.57, -141.9, NA, -419.54, -114.14, -65.48), format.spss = "F8.2", display_width = 18L), d_huglucagon_v66 = structure(c(-178.53, NA, 44.85, -35.01, -235.97, -200.73, NA, -1.89999999999998, -98.41, 77.5), format.spss = "F8.2", display_width = 18L), d_huglucagon_v01 = structure(c(-90.93, NA, 2.53999999999999, 31.25, -531.91, -79.36, NA, -13.44, -25.08, -36.21), format.spss = "F8.2", display_width = 18L), d_huleptin_v66 = structure(c(-1714.37, NA, -555.48, -789.81, -1477.18, -8711.79, NA, -877.55, -1717.47, 454.1), format.spss = "F8.2", display_width = 16L), d_huleptin_v01 = structure(c(-1628.3, NA, -653.05, 3604.24, -2993.93, -5398.66, NA, -1612.8, -2124.82, -760.69), format.spss = "F8.2", display_width = 16L), d_huresistin_v66 = structure(c(-1090.9, NA, 823.07, 399.3, 1144.2, -1196.62, NA, -1631.23, -41.54, -417.6), format.spss = "F8.2", display_width = 18L), d_huresistin_v01 = structure(c(-419.78, NA, 643.51, -519.86, 3091.53, -1374.54, NA, -1704.7, -51.0900000000001, -372.34 ), format.spss = "F8.2", display_width = 18L), d_huvisfatin_v66 = structure(c(0, NA, 6.58, -87.6800000000001, -814.67, -1347.37, NA, -145.13, -306.98, 15.7), format.spss = "F8.2", display_width = 18L), d_huvisfatin_v01 = structure(c(0, NA, 6.58, 1552.73, -83.03, -555.93, NA, -476.99, -306.98, -353.86), format.spss = "F8.2", display_width = 18L), d_glucosa_v66 = structure(c(-1, -15, 2, -28, -36, -41, -7, 8, -4, 4), format.spss = "F8.2", display_width = 15L), d_glucosa_v01 = structure(c(-4, -6, -9, -1, -31, -30, 10, 8, -7, 61), format.spss = "F8.2", display_width = 15L), d_coltot_v66 = structure(c(-6, 8, 26, -26, -36, -11, 84, -3, -8, -61), format.spss = "F8.2", display_width = 14L), d_coltot_v01 = structure(c(-23, 18, 28, 9, -9, -34, 14, 19, -7, -40), format.spss = "F8.2", display_width = 14L), d_hdl_v66 = structure(c(2, 11, 11, -2, 1, 6, -2, 8, 3, -14), format.spss = "F8.2", display_width = 11L), d_hdl_v01 = structure(c(6, 5, 5, 32, 10, -7, -3, 2, 6, -14 ), format.spss = "F8.2", display_width = 11L), d_ldl_calc_v66 = structure(c(-1, -2, 14, -17, -34, -10, 91, -3, 3, -42), format.spss = "F8.2", display_width = 16L), d_ldl_calc_v01 = structure(c(-20, 25, 24, -5, -21, -24, 21, 21, 13, -19), format.spss = "F8.2", display_width = 16L), d_col_rema_v66 = structure(c(-7, -1, 1, -7, -3, -7, -5, -8, -14, -5), format.spss = "F8.2", display_width = 16L), d_col_rema_v01 = structure(c(-9, -12, -1, -18, 2, -3, -4, -4, -26, -7), format.spss = "F8.2", display_width = 16L), d_trigli_v66 = structure(c(-31, -6, 5, -35, -13, -34, -27, -42, -73, -26), format.spss = "F8.2", display_width = 14L), d_trigli_v01 = structure(c(-41, -61, -5, -93, 11, -16, -21, -21, -134, -35), format.spss = "F8.2", display_width = 14L), d_hba1c_v66 = structure(c(-0.2, NA, -0.22, 0.0700000000000003, -0.88, -1.06, NA, -0.34, -0.2, -0.0299999999999994), format.spss = "F8.2", display_width = 13L), d_hba1c_v01 = structure(c(-0.26, NA, -0.23, 0.279999999999999, -0.52, -0.609999999999999, NA, -0.00999999999999979, -0.25, 0.609999999999999), format.spss = "F8.2", display_width = 13L), d_tasis2_e_v66 = structure(c(-22, -2, -4, 13, -14, -31, 0, 1, -8, 14), format.spss = "F8.2", display_width = 16L), d_tasis2_e_v01 = structure(c(-25, 6, -11, 36, -14, -2, 8, -15, 0, 15), format.spss = "F8.2", display_width = 16L), d_tadias2_e_v66 = structure(c(-11, -1, -6, 2, -5, -27, 0, 1, -9, 11), format.spss = "F8.2", display_width = 17L), d_tadias2_e_v01 = structure(c(-14, -1, -11, 13, -2, -17, 8, -8, -22, 2), format.spss = "F8.2", display_width = 17L), d_peso1_v66 = structure(c(-7.80000000000001, -2, -6.09999999999999, -7, -8, -12.9, -3.59999999999999, -3.5, -6, 1.2), format.spss = "F8.2", display_width = 13L), d_peso1_v01 = structure(c(-9.2, -4.2, -5.89999999999999, -6, -9, -12.9, -5.59999999999999, 0, -7, 1.2), format.spss = "F8.2", display_width = 13L), d_cintura1_v66 = structure(c(-7, -2, -7.5, -6, -8, -8.5, -8.5, -4.5, -14.5, 1), format.spss = "F8.2", display_width = 16L), d_cintura1_v01 = structure(c(-7, -3, -7.5, -6, -8, -8.5, -9.5, -3, -8.5, 1), format.spss = "F8.2", display_width = 16L), d_geaf_tot_v66 = structure(c(3566.43, -4195.8, -1153.84, 0, 1258.74, 3524.48, 2160.84, -2097.9, 2436.37, 52.45), format.spss = "F8.2", display_width = 16L), d_geaf_tot_v01 = structure(c(629.37, -4195.8, 97.9099999999999, -2797.2, 1930.07, 1603.73, 3895.11, -6433.57, 1505.83, 891.61 ), format.spss = "F8.2", display_width = 16L), d_p17_total_v66 = structure(c(2, 4, 2, 3, 1, 10, 3, 0, 7, 7), format.spss = "F8.2", display_width = 11L), d_p17_total_v01 = structure(c(4, 3, 2, 0, 4, 10, 3, 2, 5, 7), format.spss = "F8.2"), d_hupai1_v66 = structure(c(43.6500000000001, NA, -349.64, -1057.12, -265.77, -2219.75, NA, -932.13, 148.23, 944.05), format.spss = "F8.2", display_width = 13L), d_hupai1_v01 = structure(c(144.55, NA, -276.35, -697.91, -80.5599999999999, -1610.02, NA, -617.23, 473.29, 799.11), format.spss = "F8.2", display_width = 13L), d_hugip_v66 = structure(c(0, NA, 0, 0, 253.54, 0, NA, 0, 0, 0), format.spss = "F8.2", display_width = 13L), d_hugip_v01 = structure(c(0, NA, 0, 22.07, 1162.49, 0, NA, 0, 0, 0), format.spss = "F8.2", display_width = 13L), d_huglp1_v66 = structure(c(0, NA, 0, -13.7, -23.67, 50.41, NA, 40.68, 0, 55.6), format.spss = "F8.2", display_width = 13L), d_huglp1_v01 = structure(c(0, NA, 0, -13.7, -59.75, 75.63, NA, 92.43, 0, -160.47), format.spss = "F8.2", display_width = 13L), ln_trigli_v00 = structure(c(4.63472898822964, 4.969813299576, 4.06044301054642, 5.44673737166631, 4.0943445622221, 4.66343909411207, 4.83628190695148, 4.87519732320115, 5.64190707093811, 5.2257466737132 ), label = "Analítica: Triglicéridos en mg/dL", format.spss = "F5.0"), ln_trigli_v66 = structure(c(4.27666611901606, 4.92725368515721, 4.14313472639153, 5.28320372873799, 3.85014760171006, 4.27666611901606, 4.59511985013459, 4.48863636973214, 5.34233425196481, 5.07517381523383 ), label = "Analítica: Triglicéridos en mg/dL", format.spss = "F5.0"), ln_trigli_v01 = structure(c(4.12713438504509, 4.4188406077966, 3.97029191355212, 4.93447393313069, 4.26267987704132, 4.49980967033027, 4.65396035015752, 4.70048036579242, 4.99721227376411, 5.01727983681492 ), label = "Analítica: Triglicéridos en mg/dL", format.spss = "F5.0"), ln_homa_v00 = structure(c(6.04555071556718, NA, 6.72142409436365, 7.84808644334377, 7.81621937359094, 7.21939278180313, NA, 8.09146278899802, 6.33279480567865, 7.94288630470217), format.spss = "F8.2", display_width = 10L), ln_homa_v66 = structure(c(5.62105765481488, NA, 7.05988906911122, 7.58123588965634, 7.21078464361132, 5.76519388926651, NA, 7.62891573149717, 5.63172936987266, 8.05074164604432), format.spss = "F8.2", display_width = 10L), ln_homa_v01 = structure(c(5.38027823337748, NA, 6.85482321564537, 8.74088414843216, 7.11631333274751, 6.56976063964933, NA, 7.91305370498932, 6.02145906886522, 8.07492909673972), format.spss = "F8.2", display_width = 10L), ln_hba1c_v00 = structure(c(1.76985463384001, NA, 1.7509374747078, 2.07693841146172, 1.8531680973567, 1.9473377010465, NA, 1.87333945622048, 1.78339121955754, 2.19833507162025), label = "Analítica: Hemoglobina glicosilada (HbA1c %)", format.spss = "F5.2"), ln_hba1c_v66 = structure(c(1.73518911773966, NA, 1.71199450075919, 2.08567209143047, 1.70474809223843, 1.78339121955754, NA, 1.8196988379173, 1.74919985480926, 2.19499988231411), label = "Analítica: Hemoglobina glicosilada (HbA1c %)", format.spss = "F5.2"), ln_hba1c_v01 = structure(c(1.72455071953461, 1.86872051036418, 1.71018781553424, 2.11142458753289, 1.76814960358892, 1.85629799036563, 1.66013102674962, 1.87180217690159, 1.7404661748405, 2.26384426467762 ), label = "Analítica: Hemoglobina glicosilada (HbA1c %)", format.spss = "F5.2"), ln_geaf_tot_v00 = structure(c(6.95554494281799, 8.34183930393788, 8.4371494837422, 8.11869575262367, 6.73240139150378, 7.38298895764493, 7.99228216582975, 9.23110234287667, 8.37462912676087, 5.0584090689011 ), label = "AF: Gasto energético en actividad física total (MET•min/sem)", format.spss = "F8.2"), ln_geaf_tot_v66 = structure(c(8.4371494837422, -Inf, 8.14946885573527, 8.11869575262367, 7.64869212337793, 8.5434202359197, 8.54069094410428, 9.00108616558123, 8.82055617324912, 5.34610703038388), label = "AF: Gasto energético en actividad física total (MET•min/sem)", format.spss = "F8.2"), ln_geaf_tot_v01 = structure(c(7.42554857206372, -Inf, 8.45814145696367, 6.32693628339561, 7.92632458219889, 8.07468643426916, 8.83246367957041, 8.23647878828005, 8.67274118026667, 6.95554494281799), label = "AF: Gasto energético en actividad física total (MET•min/sem)", format.spss = "F8.2")), row.names = c(NA, -10L), class = c("tbl_df", "tbl", "data.frame")) Ручной метод заключается в создании терцилей одной переменной d_cintura1_v66 = разница в окружности талии между исходным уровнем и 6 месяцами. После этого нам нужно отфильтровать и провести анализ (представьте, что вы делаете это для всех переменных всех комбинаций: 1-й терцил против 2-го, 1-й против 3-го, 2-й против 3-го).
sample %gt;% dplyr::select(paciente, matches(c("_v00", "_v01", "_v66"))) %gt;% mutate(terciles_d_cintura1_v66 = ntile(.$d_cintura1_v66,3)) %gt;% dplyr::select(paciente, matches("_v66")) %gt;% pivot_longer(!c(paciente, terciles_d_cintura1_v66)) %gt;% dplyr::filter(terciles_d_cintura1_v66 == "1" | terciles_d_cintura1_v66 == "2") %gt;% dplyr::filter(str_detect(name, "d_")) %gt;% mutate(terciles_d_cintura1_v66 = factor(terciles_d_cintura1_v66)) %gt;% pivot_wider(names_from= terciles_d_cintura1_v66, values_from=value) %gt;% select(-paciente) %gt;% group_by(name) %gt;% do(tidy(t.test(.$"1", .$"2", na.rm = TRUE))) %gt;% dplyr::ungroup() My loop has the appearance below, I have noticed that changing the order of colvars and rowvars has signficance value (I wast told that this did not affect because iterate searching string)
Clarification: I ommited all variables with _v01 in the loop which are related the same way but 12 months intervention but I need to do it as well Clarification 2: the temp object I don’t really understand its function. It is something thought up by my colleague
colvars lt;- c("d_peso1_v66","d_homa_v66", "d_hughrelin_v66", "d_huinsulin_v66", "d_hucpeptide_v66", "d_huglucagon_v66", "d_huleptin_v66", "d_huresistin_v66", "d_huvisfatin_v66", "d_hupai1_v66","d_huglp1_v66", "d_hugip_v66", "d_glucosa_v66", "d_coltot_v66","d_hdl_v66", "d_ldl_calc_v66","d_col_rema_v66","d_trigli_v66","d_hba1c_v66","d_tasis2_e_v66","d_tadias2_e_v66","d_cintura1_v66","d_geaf_tot_v66","d_p17_total_v66") # Variables which should be added to the table. # The "for" loop works with the visit determined by colvars[i]. rowvars lt;- c("peso1", "homa", "i_hughrelin", "i_huinsulin", "i_hucpeptide", "i_huglucagon", "i_huleptin", "i_huresistin", "i_huvisfatin", "i_hupai1", "i_huglp1", "i_hugip", "glucosa", "coltot", "hdl", "ldl_calc", "col_rema", "trigli", "hba1c", "tasis2_e", "tadias2_e", "cintura1", "geaf_tot", "p17_total") #loop for(i in 1:length(colvars)){ # Settle variables to work with. var lt;- colvars[i] visita lt;- substr(var, nchar(var)-3, nchar(var)) rvars lt;- paste0("d_", rowvars, visita) rvars lt;- sub("d_i_", "d_", rvars) P1 lt;- sample%gt;% dplyr::select(paciente, all_of(var), rvars) %gt;% mutate(temp = ntile(eval(parse(text=var)) ,3)) %gt;% pivot_longer(!c(paciente, temp)) %gt;% dplyr::filter(temp == "1" | temp == "2") %gt;% mutate(temp = factor(temp)) %gt;% pivot_wider(names_from= temp, values_from=value) %gt;% select(-paciente) %gt;% group_by(name) %gt;% do(tidy(t.test(.$"1", .$"2", na.rm = TRUE))) %gt;% dplyr::ungroup() %gt;% pull(p.value) P1 lt;- ifelse(P1 lt; 2.2e-16, "lt; 2.2e-16", ifelse(P1 lt; 0.001, "lt; 0.001", sprintf("%.3f", round(P1, digits = 3)))) # Groups to be compared 1st tercile vs 3rd tercile P2 lt;- sample%gt;% dplyr::select(paciente, all_of(var), rvars) %gt;% mutate(temp = ntile(eval(parse(text=var)) ,3)) %gt;% pivot_longer(!c(paciente, temp)) %gt;% dplyr::filter(temp == "1" | temp == "3") %gt;% mutate(temp = factor(temp)) %gt;% pivot_wider(names_from= temp, values_from=value) %gt;% select(-paciente) %gt;% group_by(name) %gt;% do(tidy(t.test(.$"1", .$"3", na.rm = TRUE))) %gt;% dplyr::ungroup() %gt;% pull(p.value) P2 lt;- ifelse(P2 lt; 2.2e-16, "lt; 2.2e-16", ifelse(P2 lt; 0.001, "lt; 0.001", sprintf("%.3f", round(P2, digits = 3)))) # Groups to be compared 2nd tercile vs 3rd tercile P3 lt;- sample%gt;% dplyr::select(paciente, all_of(var), rvars) %gt;% mutate(temp = ntile(eval(parse(text=var)) ,3)) %gt;% pivot_longer(!c(paciente, temp)) %gt;% dplyr::filter(temp == "2" | temp == "3") %gt;% mutate(temp = factor(temp)) %gt;% pivot_wider(names_from= temp, values_from=value) %gt;% select(-paciente) %gt;% group_by(name) %gt;% do(tidy(t.test(.$"2", .$"3", na.rm = TRUE))) %gt;% dplyr::ungroup() %gt;% pull(p.value) P3 lt;- ifelse(P3 lt; 2.2e-16, "lt; 2.2e-16", ifelse(P3 lt; 0.001, "lt; 0.001", sprintf("%.3f", round(P3, digits = 3)))) Plt;- cbind(P1, P2, P3) # Makes the table tab lt;- cbind(P) rownames(tab) lt;- rvars colnames(tab) lt;- c("1st vs 2nd","1st vs 3rd","2nd vs 3rd") # Exports the table to excel write.csv2(tab, paste0("terciles of sample ",var,".csv")) } Заранее спасибо