我正在尝试复制我在新数据集上学到的规范分析方法。我创建了一个带有 1 个分类预测变量（温度）、4 个连续预测变量（附加数据集中的 BM、Mass、SMR 和 AS）和 4 个响应变量（SDA 总、SDA 持续时间、SDA 峰值和 SDA 峰值时间）的 MANCOVA 模型）。该模型通过了 ANCOVA 和 MANOVA 的假设。这是删除了交互项的模型代码（它们不重要）：
lionfish.mancova.final<-manova(cbind(sqrt.SDA_integral,`SDA duration`,log.peak,log.peaktime)~Temperature+BM+Mass+SMR+AS, data=lionfish_data)
规范分析的目标是找出哪个预测因子推动了大部分响应。我被教导使用包找到由每个预测变量的第一个特征向量解释的模型变化的百分比candisc。使用
candiscList(lionfish.mancova.final)
其中列出每个预测变量的第一特征向量信息或
mancova.temp<-candisc(lionfish.mancova.final,term="Temperature")
mancova.temp$pct
它直接打印每个预测变量的第一个特征向量解释的百分比（在这种情况下为温度），每个预测变量解释的百分比始终为 100%。这显然没有发生，这在之前的数据集中也不是问题。关于为什么它会为每个预测变量的第一个特征向量报告 100% 的任何想法？提前感谢任何可以分享建议的人！
数据（从 CSV 复制）：
Fish,Date,Temperature,SMR end (hr),Mass,MMR,SMR,AS,RMR block min,BM,SDA_peak,SDA_peaktime,Fixed SDA end hour,SDA duration,SDA integral
1544,Mar 14-19,Low,24.7,227,263.8,55.58502519,208.2149748,70.51328101,4.3,168.3,5,113.6,88.9,3499.5
1545,Mar 14-19,Low,24.7,100,203.3,51.15976604,152.140234,88.54550957,3.6,167.8,2.9,65.1,40.4,2448.2
1541,Mar 14-19,Low,24.7,90,254.2,57.53883131,196.6611687,80.9416882,6.8,247.3,5.5,135.34,110.64,9587.5
1542,Mar 14-19,Low,24.7,98,259.3,48.95655884,210.3434412,72.16391583,3.6,188.5,3,135.34,110.64,5819.5
1543,Mar 14-19,Low,24.7,62,271.6,29.93112963,241.6688704,68.05718878,13.5,260.1,33,128.4,103.7,10868.8
1546,Mar 14-19,Low,24.7,91,240.2,63.8277889,176.3722111,75.31534816,3,189.9,0.5,65.1,40.4,1670.4
1541,Mar 21-26,Low,23,90,254.2,122.2637762,131.9362238,128.7860128,3.4,216.8,7.1,67.9,44.9,1448.7
1542,Mar 21-26,Low,23,98,259.3,76.61251742,182.6874826,99.27681948,1.6,178.1,3.5,92.3,69.3,2995.6
1543,Mar 21-26,Low,23,62,271.6,87.8949261,183.7050739,101.4613985,2.9,231.9,2,65.9,42.9,2252.5
1546,Mar 21-26,Low,23,91,240.2,94.72629332,145.4737067,103.8777369,9.8,269.6,2.5,84.3,61.3,4486.4
1696,Jun 29-Jul 7,Low,25.5,74.5,324,87.26157545,236.7384246,102.8344457,3.6,231.75,22.2,99.1,73.6,4835.7
1694,Jun 29-Jul 7,Low,25.5,70,299.7,76.99348356,222.7065164,95.56704067,5.1,226.62,7.2,91.1,65.6,4414.5
1693,Jun 29-Jul 7,Low,25.5,226.3,261.4,75.95940767,185.4405923,92.31355058,3,199.94,3,89.1,63.6,3404.65
1692,Jun 29-Jul 7,Low,46.7,141.5,270.8,83.85898147,186.9410185,96.81155237,2.4,180.48,6,89.1,42.4,1738.4
1691,Jun 29-Jul 7,Low,25.5,218,249.7,75.92790049,173.7720995,88.05633355,1.4,164.09,12.6,74.6,49.1,1317.2
1690,Jun 29-Jul 7,Low,25.5,187.5,261.8,79.22664204,182.573358,100.1478754,6.1,234.03,2.5,91.1,65.6,4827.6
1689,Jun 29-Jul 7,Low,25.5,85.5,275.6,87.38845731,188.2115427,103.862512,9.1,291.47,22.7,121.2,95.7,9134.9
1688,Jun 29-Jul 7,Low,25.5,111,257.6,79.78106848,177.8189315,89.49529046,6.5,253.84,4,89.1,63.6,5088.8
1673,Jul 8-13,High,26,229,222.8,117.8055028,104.9944972,134.9063456,5.8,246.7,6.6,126.6,100.6,4788.8
1671,Jul 8-13,High,26,181,256,122.8775872,133.1224128,137.2840714,5.4,262.1,5.1,72.9,46.9,3667.4
1670,Jul 8-13,High,26,217,246,114.796743,131.203257,130.5734965,1.8,196.2,2,52.9,26.9,989.1
1669,Jul 8-13,High,26,93,329,141.7096183,187.2903817,167.6722328,6.8,355.3,8.6,90.9,64.9,5262.1
1668,Jul 8-13,High,26,57,280.4,161.9566443,118.4433557,183.9718023,10.2,434.9,4.1,80.9,54.9,5770.6
1666,Jul 8-13,High,26,167,247.3,140.7646959,106.5353041,163.9397034,13.5,304.4,9.6,78.9,52.9,3978
1665,Jul 8-13,High,26,168,232.6,125.9586414,106.6413586,137.1149026,6.4,298.2,4.6,70.9,44.9,4016.5
1663,Jul 14-19,High,23.5,270,202.1,82.17449207,119.9255079,95.2014343,7.4,229.2,5,117,93.5,5634.2
1689,Jul 14-19,High,23.5,89.5,273.98,102.5626464,171.4173536,111.5290659,7.8,292.5,3.5,123.3,99.8,6285.6
1693,Jul 14-19,High,23.5,236.5,291.7,122.196061,169.503939,136.3122595,6.8,251.9,8.1,84.2,60.7,4493.5
1696,Jul 14-19,High,23.5,76,313.97,97.56856134,216.4014387,123.7317292,5,285.6,7.2,110.2,86.7,6327.3
1694,Jul 14-19,High,23.5,66,353.4,104.5609708,248.8390292,123.5321187,6.7,284.3,5,92.2,68.7,5350.1
1688,Jul 14-19,High,23.5,115,238,98.88968145,139.1103186,111.4421464,7.4,290.1,7.7,116.5,93,5502.7
1691,Jul 14-19,High,23.5,214.5,301,89.00250227,211.9974977,112.2052501,8.8,262.8,7.7,64.2,40.7,4173.3
untagged 1,Jul 20-24,High,25,43.5,261.4,137.3095495,124.0904505,151.6263175,13.8,456,8.1,99.3,74.3,11933.9
1680,Jul 20-25,High,25,323,157.3,87.10641649,70.19358351,94.0451836,7.1,179.8,1,69.3,44.3,2088.7
1682,Jul 20-25,High,25,241.5,198.6,99.07483092,99.52516908,106.9928424,8.4,266,6.1,107.3,82.3,5861.6
1686,Jul 20-25,High,25,176.5,284.5,109.6719638,174.8280362,115.200684,11.6,330.3,9.7,113.4,88.4,9332.4
1685,Jul 20-25,High,25,192,212.3,101.1924491,111.1075509,106.0441964,6,255.1,11.1,95.3,70.3,4732.3
1687,Jul 20-25,High,25,181.5,253.4,106.5658012,146.8341988,116.7643461,4.1,247.6,1,91.3,66.3,3840.5
1684,Jul 20-25,High,25,105,262.7,104.7064061,157.9935939,124.7503246,8.5,340.9,7.1,93.3,68.3,6681.3
1681,Jul 20-25,High,25,136.5,245.5038,111.3920692,134.1117308,120.3785521,8.6,306.6,5.6,113.4,88.4,6911.2