w=cov(p);
>> [e,v]=eig(w)
e =
0.1745 0.0464 -0.8247 -0.0598 0.3313 -0.4170
-0.0163 -0.0029 0.4217 -0.6721 0.4985 -0.3488
0.0065 0.0055 0.3182 0.7380 0.4817 -0.3491
0.8184 0.1726 0.0654 -0.0059 0.2877 0.4618
-0.2120 -0.7656 -0.1396 0.0027 0.4090 0.4268
-0.5044 0.6180 -0.1302 -0.0002 0.3995 0.4325
v =
0.1526 0 0 0 0 0
0 0.1992 0 0 0 0
0 0 0.3226 0 0 0
0 0 0 0.4572 0 0
0 0 0 0 1.1332 0
0 0 0 0 0 3.7352
>>result= p*e
result =
0.2287 0.2175 0.2303 0.6621 -0.2899 1.8096
0.5734 -0.5691 0.1343 0.0469 -0.9495 -1.3500
0.4247 -0.2699 -0.0565 -0.7086 -2.7841 0.1246
0.7863 -0.2544 -0.4901 0.3537 -0.4877 -0.4106
0.6236 -0.0313 -0.0128 0.6155 0.4366 0.7842
0.0080 -0.1394 0.1016 -0.3495 -0.3640 -1.1998
-0.3532 -0.2878 0.6607 -0.0892 -2.2474 -1.0365
-0.0340 -0.7334 -0.8750 -0.7119 -0.4259 0.8986
-0.4590 -0.9110 0.3774 -0.9194 -0.6251 -3.3897
0.0704 -0.1649 0.4111 0.3366 0.1572 -3.4531
-0.0672 -0.1591 0.5883 0.5833 0.0237 -1.0316
0.0396 -0.3472 0.6628 -1.4935 -2.1219 -0.8291
0.3935 -0.5296 -0.7720 0.3591 -2.0459 -1.5344
0.0805 -0.2446 0.7823 1.7032 -1.7042 -2.1538
0.1575 -0.5518 0.2999 -0.5985 1.8450 0.2156
-0.5680 -0.7977 -0.6141 0.6093 -0.1471 2.1642
0.6503 0.0750 0.6337 -0.3597 -0.2268 -1.6013
0.0814 -0.1168 -0.9051 0.4303 -0.8855 -1.1868
-0.6151 -0.3798 0.8338 1.0057 0.0199 1.1357
-0.2512 -0.9218 -0.4521 0.5877 0.1416 0.9573
0.1688 0.0512 -0.8082 1.2628 0.5917 -2.0017
0.1186 -0.1453 0.4028 -0.6265 0.7335 0.6471
-0.6599 0.7454 -0.7825 0.7373 0.7285 0.0897
0.3809 0.1680 0.3292 -0.4212 -0.0440 2.5180
-0.0563 -0.7064 0.7727 1.0198 -0.0937 -1.6085
-0.2219 -0.3412 0.4504 0.9396 -1.4414 -0.0787
-0.4948 -0.5016 -0.4580 0.9469 0.3262 -2.9517
-0.2585 0.4904 0.4591 -0.0827 0.8402 -0.7823
0.1345 0.2634 -0.7183 0.1636 -0.3524 -2.7627
-0.2376 0.3184 0.8414 1.0305 -0.2952 -2.8581
-0.0686 -0.0762 -1.0825 0.0314 -0.0085 -1.6254
-0.8539 -0.0449 0.4577 -0.6847 0.6747 -1.8761
-0.6910 -0.2791 0.1706 0.9146 -0.5454 2.9810
-0.2720 0.4703 0.7879 0.1592 1.4822 0.2725
0.1616 0.1510 -0.1161 -0.2522 -2.7273 0.9014
0.2939 0.0516 0.3815 -0.3118 0.5856 -0.6158
0.0591 -0.5864 -0.1913 0.5617 0.7977 1.6287
0.1761 0.0519 -0.6685 -0.2763 0.7225 2.7530
0.5016 -0.0704 -0.2156 -0.0261 0.5904 1.5914
-0.0915 0.0738 -0.6434 -0.9216 1.1584 1.7949
-0.0171 0.3464 0.5986 0.9876 1.4701 3.3343
0.5885 -0.2531 0.2394 -0.4505 2.2241 0.5813
-0.3220 -0.0934 -0.2130 -0.4372 1.5018 0.0418
-0.2759 -0.6776 -0.7200 -0.0515 -0.6999 -1.7958
-0.2474 0.0365 0.4545 -0.6169 1.1813 1.7564
-0.0023 -0.3438 0.1037 0.3744 1.1419 -1.8710
0.2961 1.1905 -0.4076 0.8947 1.4033 -1.9164
-0.5358 -0.5475 0.1650 0.6540 -0.0046 -0.4663
-0.7222 -0.1424 -0.1187 -0.6225 0.7018 -2.6594
0.4877 0.5497 0.9439 -0.6675 0.1996 1.6182
0.1394 0.0236 -0.2964 0.9698 1.9586 -0.9112
-0.3727 0.5540 0.4776 -0.5436 0.4018 -2.1319
-0.2102 0.1315 0.7387 -0.6327 -0.6206 0.7813
0.0639 0.4618 0.1728 0.5125 -1.7728 1.9625
-0.3954 0.0384 0.2160 -0.2761 0.1758 -0.4140
0.3557 0.1117 1.4957 0.5230 -0.1038 1.0013
0.0205 -0.5161 -0.0134 -0.1120 -1.7875 1.2916
0.0456 -0.0006 -0.5963 -0.6021 0.5226 4.4178
0.0694 0.1692 0.3223 0.7353 -1.3567 2.9253
-0.2184 0.6774 -0.1134 1.1745 -1.3587 2.1732
0.7528 -0.2057 -0.6126 0.8189 1.9827 0.2337
0.5502 -1.0285 0.7067 0.5168 0.0704 0.9230
-0.2066 -0.0587 -0.2499 -0.8777 0.5968 4.4617
-0.2067 0.3109 0.5672 -0.5926 0.2796 -2.1093
0.5129 0.7724 0.4749 -0.4039 -0.1404 1.2830
-0.7304 0.1764 0.2731 -0.9490 -0.2182 -0.6209
0.0630 0.4184 0.1952 -0.9746 -0.3067 -0.4219
-0.3776 -0.0195 -0.7614 0.5754 0.1631 -0.5925
0.3049 -0.5775 0.8082 -0.7865 -1.0371 -0.2708
0.0049 0.1479 0.0678 -0.7343 0.5638 -2.0426
-0.1352 0.3216 -0.1037 -0.1078 -0.4204 -1.3769
0.6360 0.1709 -0.8886 -0.7195 -1.5723 1.8818
0.1022 0.1649 0.9183 0.8798 0.2859 -1.6591
0.6669 -0.2043 -0.1077 -0.2996 0.5718 -1.2660
0.4545 0.4046 -0.3773 0.5053 -0.1306 -2.9127
-0.1389 0.1479 -0.0867 -0.7366 0.0996 0.8047
0.3839 -0.5413 -0.0238 -0.4166 1.2844 -1.7476
0.8658 -0.1247 0.4726 0.4933 0.4113 1.1502
-0.2337 -0.2149 0.4255 -0.8846 0.2680 0.1141
-0.1521 0.9720 0.3005 -1.2637 -1.0167 -3.4092
-0.2515 0.2820 -0.5813 -0.1593 -0.4511 -0.2550
-0.2934 -0.3913 0.5622 -0.2847 1.4599 1.6504
0.3382 0.2144 -0.3575 0.2122 0.9634 -1.3680
-0.6642 0.0631 -1.1403 -0.2469 -0.5742 -0.9168
0.0007 1.0448 -0.3873 0.6533 -1.5150 -0.6674
0.1825 0.2161 -0.5192 0.0775 1.1203 -3.9396
0.6583 -0.0843 -0.9287 -0.8541 -1.2838 0.4580
-0.1505 0.2164 0.5061 -0.7150 0.8049 0.4397
0.4932 0.9623 -0.3342 -0.9965 0.0839 -2.5340
-0.5966 0.6068 -0.3004 -0.1627 -1.0670 1.0677
-0.2516 1.1793 -0.1864 0.9679 -1.5835 0.7254
0.1070 -0.0306 -0.2205 0.6508 -0.8961 2.8852
-0.2084 0.1598 -1.1293 0.1698 -0.0857 4.2944
0.0279 -0.0402 -0.7743 0.1262 1.9864 -3.0947
-0.0433 -0.1845 -0.6908 -0.8297 0.6059 1.1804
-0.3411 0.4666 0.8149 0.3049 0.7929 4.5720
-0.0992 -0.2656 -0.2453 -0.7739 -0.6688 1.2265
-0.8115 -0.1451 -0.5384 -0.2927 0.4179 1.3257
0.0448 -0.0380 -0.1062 0.1608 1.2730 1.9506
0.1354 0.0519 0.2023 -0.0906 0.6607 1.9280
[pc1, score1, variance1, t21]=princomp(p)
pc1 =
0.4170 -0.3313 -0.0598 0.8247 -0.0464 -0.1745
0.3488 -0.4985 -0.6721 -0.4217 0.0029 0.0163
0.3491 -0.4817 0.7380 -0.3182 -0.0055 -0.0065
-0.4618 -0.2877 -0.0059 -0.0654 -0.1726 -0.8184
-0.4268 -0.4090 0.0027 0.1396 0.7656 0.2120
-0.4325 -0.3995 -0.0002 0.1302 -0.6180 0.5044
score1 =
-1.8096 0.2899 0.6621 -0.2303 -0.2175 -0.2287
1.3501 0.9495 0.0469 -0.1343 0.5691 -0.5734
-0.1246 2.7841 -0.7086 0.0565 0.2699 -0.4247
0.4106 0.4877 0.3537 0.4901 0.2544 -0.7863
-0.7842 -0.4366 0.6155 0.0129 0.0313 -0.6236
1.1998 0.3640 -0.3495 -0.1016 0.1394 -0.0080
1.0365 2.2474 -0.0892 -0.6607 0.2878 0.3532
-0.8986 0.4259 -0.7119 0.8751 0.7334 0.0340
3.3897 0.6251 -0.9194 -0.3774 0.9110 0.4590
3.4531 -0.1572 0.3366 -0.4111 0.1649 -0.0704
1.0316 -0.0237 0.5833 -0.5883 0.1591 0.0672
0.8291 2.1219 -1.4935 -0.6628 0.3472 -0.0396
1.5344 2.0459 0.3591 0.7720 0.5296 -0.3935
2.1538 1.7042 1.7032 -0.7823 0.2446 -0.0805
-0.2156 -1.8450 -0.5985 -0.2999 0.5518 -0.1575
-2.1642 0.1471 0.6093 0.6141 0.7977 0.5680
1.6013 0.2268 -0.3597 -0.6336 -0.0750 -0.6503
1.1868 0.8855 0.4303 0.9051 0.1168 -0.0814
-1.1357 -0.0199 1.0057 -0.8338 0.3798 0.6151
-0.9573 -0.1416 0.5877 0.4521 0.9218 0.2512
2.0017 -0.5917 1.2628 0.8082 -0.0512 -0.1688
-0.6471 -0.7335 -0.6265 -0.4028 0.1453 -0.1186
-0.0897 -0.7285 0.7373 0.7825 -0.7454 0.6599
-2.5180 0.0440 -0.4212 -0.3292 -0.1680 -0.3809
1.6085 0.0937 1.0198 -0.7727 0.7064 0.0563
0.0787 1.4414 0.9396 -0.4504 0.3412 0.2219
2.9517 -0.3262 0.9469 0.4580 0.5016 0.4948
0.7823 -0.8402 -0.0827 -0.4591 -0.4904 0.2585
2.7627 0.3524 0.1636 0.7183 -0.2634 -0.1345
2.8581 0.2952 1.0305 -0.8414 -0.3184 0.2376
1.6254 0.0085 0.0314 1.0825 0.0762 0.0686
1.8761 -0.6747 -0.6847 -0.4577 0.0449 0.8539
-2.9810 0.5454 0.9146 -0.1706 0.2791 0.6910
-0.2725 -1.4822 0.1592 -0.7879 -0.4703 0.2720
-0.9014 2.7273 -0.2522 0.1161 -0.1510 -0.1616
0.6158 -0.5856 -0.3118 -0.3815 -0.0516 -0.2939
-1.6287 -0.7977 0.5617 0.1913 0.5864 -0.0591
-2.7530 -0.7225 -0.2763 0.6685 -0.0519 -0.1761
-1.5914 -0.5904 -0.0261 0.2156 0.0704 -0.5016
-1.7949 -1.1584 -0.9216 0.6434 -0.0738 0.0915
-3.3343 -1.4701 0.9876 -0.5986 -0.3464 0.0171
-0.5813 -2.2241 -0.4505 -0.2394 0.2531 -0.5885
-0.0418 -1.5018 -0.4372 0.2130 0.0934 0.3220
1.7958 0.6999 -0.0515 0.7200 0.6776 0.2759
-1.7564 -1.1813 -0.6169 -0.4545 -0.0365 0.2474
1.8710 -1.1420 0.3744 -0.1037 0.3438 0.0023
1.9164 -1.4033 0.8947 0.4077 -1.1905 -0.2961
0.4663 0.0046 0.6540 -0.1650 0.5475 0.5358
2.6594 -0.7018 -0.6225 0.1187 0.1424 0.7222
-1.6182 -0.1996 -0.6675 -0.9439 -0.5497 -0.4877
0.9112 -1.9586 0.9698 0.2964 -0.0236 -0.1394
2.1319 -0.4018 -0.5436 -0.4775 -0.5540 0.3727
-0.7813 0.6206 -0.6327 -0.7387 -0.1315 0.2102
-1.9625 1.7728 0.5125 -0.1728 -0.4618 -0.0639
0.4140 -0.1758 -0.2761 -0.2160 -0.0384 0.3954
-1.0013 0.1038 0.5230 -1.4957 -0.1117 -0.3557
-1.2916 1.7875 -0.1120 0.0134 0.5161 -0.0205
-4.4178 -0.5226 -0.6021 0.5963 0.0006 -0.0456
-2.9253 1.3567 0.7353 -0.3223 -0.1692 -0.0694
-2.1732 1.3587 1.1745 0.1134 -0.6774 0.2184
-0.2337 -1.9827 0.8189 0.6126 0.2057 -0.7528
-0.9230 -0.0704 0.5168 -0.7067 1.0285 -0.5502
-4.4617 -0.5968 -0.8777 0.2499 0.0587 0.2066
2.1093 -0.2796 -0.5926 -0.5672 -0.3109 0.2067
-1.2830 0.1404 -0.4039 -0.4749 -0.7724 -0.5129
0.6209 0.2182 -0.9490 -0.2731 -0.1764 0.7304
0.4219 0.3067 -0.9746 -0.1952 -0.4184 -0.0630
0.5925 -0.1631 0.5754 0.7614 0.0195 0.3776
0.2708 1.0371 -0.7865 -0.8082 0.5775 -0.3049
2.0426 -0.5638 -0.7343 -0.0678 -0.1479 -0.0049
1.3769 0.4204 -0.1078 0.1037 -0.3216 0.1352
-1.8818 1.5723 -0.7195 0.8886 -0.1709 -0.6360
1.6591 -0.2859 0.8798 -0.9183 -0.1649 -0.1022
1.2660 -0.5718 -0.2996 0.1077 0.2043 -0.6669
2.9127 0.1306 0.5053 0.3773 -0.4046 -0.4545
-0.8047 -0.0996 -0.7366 0.0867 -0.1479 0.1389
1.7476 -1.2844 -0.4166 0.0238 0.5413 -0.3839
-1.1502 -0.4113 0.4933 -0.4726 0.1247 -0.8658
-0.1141 -0.2680 -0.8846 -0.4255 0.2149 0.2337
3.4092 1.0167 -1.2637 -0.3005 -0.9720 0.1521
0.2550 0.4511 -0.1593 0.5813 -0.2820 0.2515
-1.6504 -1.4599 -0.2847 -0.5622 0.3913 0.2934
1.3680 -0.9635 0.2122 0.3575 -0.2144 -0.3382
0.9168 0.5742 -0.2469 1.1403 -0.0631 0.6642
0.6674 1.5150 0.6533 0.3873 -1.0448 -0.0007
3.9396 -1.1203 0.0775 0.5192 -0.2161 -0.1825
-0.4580 1.2838 -0.8541 0.9287 0.0843 -0.6583
-0.4397 -0.8049 -0.7150 -0.5061 -0.2164 0.1505
2.5340 -0.0839 -0.9965 0.3342 -0.9623 -0.4932
-1.0677 1.0670 -0.1628 0.3004 -0.6068 0.5966
-0.7254 1.5835 0.9679 0.1864 -1.1793 0.2516
-2.8852 0.8961 0.6508 0.2205 0.0306 -0.1070
-4.2944 0.0857 0.1698 1.1293 -0.1598 0.2084
3.0947 -1.9864 0.1262 0.7743 0.0402 -0.0279
-1.1804 -0.6059 -0.8297 0.6908 0.1845 0.0433
-4.5720 -0.7929 0.3049 -0.8149 -0.4666 0.3411
-1.2265 0.6688 -0.7739 0.2453 0.2656 0.0992
-1.3257 -0.4179 -0.2927 0.5384 0.1451 0.8115
-1.9506 -1.2730 0.1608 0.1062 0.0380 -0.0448
-1.9280 -0.6607 -0.0906 -0.2023 -0.0519 -0.1354
variance1 =
3.7352
1.1332
0.4572
0.3226
0.1992
0.1526
t21 =
2.6544
5.1254
9.5004
5.6509
3.7154
0.8995
7.3490
6.5665
11.2589
4.1548
2.2593
11.0134
8.8767
12.3898
5.7697
8.5627
5.0595
4.1255
7.9177
6.3317
7.0949
2.1466
9.2015
3.5158
7.3526
5.3019
7.9057
3.1001
4.2777
7.6602
4.4023
7.8076
8.0815
5.5342
7.2476
1.6475
3.8245
4.2590
2.8052
5.2698
8.7322
7.6685
3.2727
5.7118
3.9381
3.0214
12.6772
4.4649
6.7393
7.5484
6.0671
5.1635
3.4467
5.5689
1.4164
8.7029
4.6340
7.3749
5.5952
8.5665
10.0405
9.6591
7.8194
3.7910
6.2334
5.9991
3.2313
3.5753
6.6308
2.7012
1.3612
9.5069
5.3216
4.0743
5.4616
1.6287
5.0918
6.7186
2.9296
12.6917
2.1138
5.0998
2.7951
7.5916
9.0240
6.5640
8.6564
2.9193
10.4871
5.8287
11.9074
4.0942
9.3728
7.9523
3.8652
10.2683
2.7127
6.1325
2.5606
1.6588
原来Spss在计算PCA的时候已经做了标准化处理,因为我在Matlab下用元数据和标准化的数据计算的不一样,但是标准化后的数据计算结果却和Matlab里面的特征值和特征向量一样,但是为什么有一个符号的差别?而主成分得分却完全不一样?
今天和学长商讨了一下,原来Spss并没有提供专门的PCA分析模块。只是因子分析需要建立在PCA的基础上而已。但是我在Matlab中一步步按照书上给的步骤去计算缺的的结果和Matlab自带的函数有点差异的时候,觉得是特征向量的时候出现了问题,又看了一下线性代数才找到答案。
这也是我喜欢Matlab的原因,我可以去模拟,去对比,在这个过程之后发现问题,然后解决,看自己缺少那些知识,然后自己去弥补…… ,看来线代知识不够扎实,还需要努力,努力……