Day4_Correlation_GS Tuan_2022
Nguyen Truong
6/10/2022
library(pacman)
p_load(tidyverse,ggplot2,GGally,readxl,ggfortify, magrittr)
#GGally: package for describe correlation between more than 2 variables (viec3)
#ggfortify: package for function autoplot()#Việc 1: Đọc dữ liệu nghiên cứu tim mạch ‘Framingham dataset.csv’ và gọi đối tượng ‘fmh’. Có những biến số liên quan đến bệnh tim mạch. Các biến liên quan: #‘age’: Tuổi #‘sex’: Giới tính (1/2) #‘sysbp’: systolic blood pressure #‘diasbp’: diastolic blood pressure #‘tot.chol’: Total cholesterol #‘heart.rate’: Nhịp tim #‘bmi’: Tỷ trọng cơ thể #‘smoker’: Hút thuốc lá (0/1) #‘diabetes’: Tiểu đường (0/1) #‘stroke’: Đột quỵ (0/1) #‘cvd’: Cardiovascular disease (0/1) #‘death’: Tử vong (0/1)
fmh=read.csv("/Users/osx/Desktop/Dataset /Framingham dataset.csv")#Việc 2:Kiểm tra mối tương quan giữa ‘bmi’ và ‘sysbp’. Thể hiện mối liên quan bằng biểu đồ tương quan (dùng ggplot) #viec 2: Kiểm tra mối tương quan giữa ‘bmi’ và ‘tot.chol’. Thể hiện mối liên quan bằng biểu đồ tương quan (dùng ggplot).
p1= ggplot(data=fmh, aes(bmi, sysbp)) + geom_point(aes(color=bmi)) +labs(title = "Correlation between bmi and sysbp", x="Boday Index Mass", y= "Systolic Blood Pressure") + theme(plot.title = element_text(hjust=0.5)) + geom_jitter(alpha=0.05)
p1## Warning: Removed 52 rows containing missing values (geom_point).
## Warning: Removed 52 rows containing missing values (geom_point).
p2=ggplot(data=fmh, aes(bmi,tot.chol)) + geom_point(aes(color=bmi)) + ggtitle("Correlation between bmi and tot.chol") + theme(plot.title = element_text(hjust=0.5))
p2## Warning: Removed 454 rows containing missing values (geom_point).
#Việc 3: Kiểm tra mối tương quan giữa các biến ‘age’, ‘bmi’, ‘sysbp’, ‘diasbp’, ‘tot.chol’, và ‘heart.rate’. Hãy vẽ một biểu đồ tương quan đa biến giữa các biến trên.
ggpairs(fmh[,c("tot.chol","age", "sysbp", "diasbp", "bmi", "heart.rate")]) + theme_bw()## Warning: Removed 409 rows containing non-finite values (stat_density).## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 409 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 409 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 409 rows containing missing values## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 454 rows containing missing values## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 413 rows containing missing values## Warning: Removed 409 rows containing missing values (geom_point).## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 52 rows containing missing values## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 6 rows containing missing values## Warning: Removed 409 rows containing missing values (geom_point).## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 52 rows containing missing values## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 6 rows containing missing values## Warning: Removed 409 rows containing missing values (geom_point).## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 52 rows containing missing values## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 6 rows containing missing values## Warning: Removed 454 rows containing missing values (geom_point).## Warning: Removed 52 rows containing missing values (geom_point).
## Warning: Removed 52 rows containing missing values (geom_point).
## Warning: Removed 52 rows containing missing values (geom_point).## Warning: Removed 52 rows containing non-finite values (stat_density).## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 54 rows containing missing values## Warning: Removed 413 rows containing missing values (geom_point).## Warning: Removed 6 rows containing missing values (geom_point).
## Warning: Removed 6 rows containing missing values (geom_point).
## Warning: Removed 6 rows containing missing values (geom_point).## Warning: Removed 54 rows containing missing values (geom_point).## Warning: Removed 6 rows containing non-finite values (stat_density).
#cong thuc ham ggpairs (data) + theme_bw()
#ham ggpairs mac dinh dung Pearson's, duong cheo trong ket qua chinh la distribution cua moi bien#Việc 4: Đọc dữ liệu ‘Insurance dataset.xlsx’ vào R và gọi đối tượng là ‘ins’ (dùng hàm ‘read_excel’ trong package ‘readxl’) #‘age’ Tuổi #‘sex’ Giới tính (male / female) #‘bmi’ Tỷ trọng cơ thể #‘children’ Số con #‘smoker’ Hút thuốc lá (yes / no) #‘region’ Vùng miền (northeast / northwest / southeast / southwest) #‘charge’ Tiền bảo hiểm ($)
ins= read_excel("/Users/osx/Desktop/Dataset /Insurance dataset.xlsx")
# Dùng mô hình hồi quy tuyến tính qua hàm ‘lm’ để đánh giá mối liên quan giữa ‘age’ và ‘charge’
m=lm(log(charge) ~ age, data=ins)
summary(m)##
## Call:
## lm(formula = log(charge) ~ age, data = ins)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3433 -0.4166 -0.3094 0.5000 2.1999
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7.744247 0.063336 122.27 <2e-16 ***
## age 0.034545 0.001521 22.71 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7813 on 1336 degrees of freedom
## Multiple R-squared: 0.2786, Adjusted R-squared: 0.2781
## F-statistic: 516 on 1 and 1336 DF, p-value: < 2.2e-16# intercept: 3165
# slope: 257.7
# R2: 0.09
# MSE:133440979
#Kiểm tra các giả định của mô hình hồi quy tuyến tính
autoplot(m)
#ham gop 4 cua so plot(m) vao 1 window
par(mfrow= c(2,2))
plot(m)
# tinh Mean Square Error (MSE)
#MSE trung binh phuong sai, trong mo hinh hoi quy, no la phuong sai cua Y sau khi hieu chinh cho X trong mô hình
# phuong sai cua Y: Var(Y) (la phuong sai của Y chua hieu chinh)
# khac biet giua MSE va Var(Y) chinh la phan tram ma mo hinh cua minh giai thich duoc
MSE2=mean(m$residual^2)
MSE2## [1] 0.6095021# cho ra nhieu gia tri MSE3 vi moi lan tien luong predict(m) cho ra nhieu gia tri
MSE3=((ins$charge - predict(m))^2)
MSE3## 1 2 3 4 5 6 7
## 284817042 2948729 19720265 482926396 14884207 14046053 67753580
## 8 9 10 11 12 13 14
## 52889012 40926577 835980071 7358811 772775453 3306230 122789426
## 15 16 17 18 19 20 21
## 1568404004 3344643 116376534 5696016 112205425 1356352142 174742754
## 22 23 24 25 26 27 28
## 17147512 1273839 1420759084 38376530 195757914 208568896 150282787
## 29 30 31 32 33 34 35
## 7654371 1497859112 1265728035 4795328 21896751 189342480 2619990998
## 36 37 38 39 40 41 42
## 2614796 243431993 5260865 1581280911 2319726975 9226337 24412923
## 43 44 45 46 47 48 49
## 39229135 39749703 36852361 425210764 11458159 12589800 159266413
## 50 51 52 53 54 55 56
## 1497704561 4852172 12754605 555020336 1423823650 64811404 2254991101
## 57 58 59 60 61 62 63
## 184895294 1176133385 539875219 35767635 73908198 20214506 909424325
## 64 65 66 67 68 69 70
## 17015049 216187285 3009578 202356898 40707613 34939661 311678994
## 71 72 73 74 75 76 77
## 274535159 46112830 137643364 142489057 59561192 128753219 15513098
## 78 79 80 81 82 83 84
## 2322576 7543354 43058056 19646152 62821355 1380617350 121534293
## 85 86 87 88 89 90 91
## 1586229484 444756688 1898277461 122400971 64277633 122609845 4074360
## 92 93 94 95 96 97 98
## 119520801 910539936 32718995 2235502404 14123859 146306208 104379732
## 99 100 101 102 103 104 105
## 501893053 250008024 38154914 13222742 455245406 956809676 24949368
## 106 107 108 109 110 111 112
## 308070759 5396879 14966544 8170299 2213289562 116978155 140937588
## 113 114 115 116 117 118 119
## 21508601 5742082 131762307 915073306 129312776 364773082 73820614
## 120 121 122 123 124 125 126
## 44587789 59769486 2880686 5058181 1563983422 102123980 11402486
## 127 128 129 130 131 132 133
## 291476382 92640575 1070947656 36885556 163984993 185137035 124411557
## 134 135 136 137 138 139 140
## 2637908 5996504 4610370 1570113 4150106 746006752 4657947
## 141 142 143 144 145 146 147
## 748951923 12123674 359617223 329390918 430031816 26311879 1657403249
## 148 149 150 151 152 153 154
## 97379430 119905118 3363990 26176141 60532019 40011873 398224022
## 155 156 157 158 159 160 161
## 49957519 48155780 450045395 240554336 1364672656 389664121 455374724
## 162 163 164 165 166 167 168
## 1306180370 109013276 26453373 25191608 108112539 23253563 37453761
## 169 170 171 172 173 174 175
## 7348866 23224958 179438609 65727390 2844047 27427150 8104636
## 176 177 178 179 180 181 182
## 2382858282 41561304 108711617 77685638 72746022 137502153 2635607
## 183 184 185 186 187 188 189
## 15975356 54911267 59631799 1913568085 15787386 28269111 45789588
## 190 191 192 193 194 195 196
## 24149065 157446125 23764437 4532836 144833119 1274875 2660691
## 197 198 199 200 201 202 203
## 31816633 72378070 92828339 221758606 4504052 78530600 169062190
## 204 205 206 207 208 209 210
## 1378282052 50947785 18740446 137675412 439956509 192405429 43572985
## 211 212 213 214 215 216 217
## 3887344 66481033 12454756 24938677 72432478 54208047 107041079
## 218 219 220 221 222 223 224
## 6125917 11453719 628665083 25035535 111414556 27506609 1209037351
## 225 226 227 228 229 230 231
## 380497552 143461080 7186602 586491635 54008022 84932601 55271016
## 232 233 234 235 236 237 238
## 195762192 2956283 151882100 44904746 377724657 2583737 19841590
## 239 240 241 242 243 244 245
## 300824038 51028266 1482487902 28571061 1235556971 51663620 871031631
## 246 247 248 249 250 251 252
## 598627670 159741451 3913909 3325858 16255510 164380324 2236853386
## 253 254 255 256 257 258 259
## 1958163410 18080074 1688198290 169981312 1928220265 29072839 132493770
## 260 261 262 263 264 265 266
## 1138515221 139887678 291618207 618034327 1311236872 418342493 2129064893
## 267 268 269 270 271 272 273
## 294822497 212601176 55230971 85989338 2927761 1835896816 52657400
## 274 275 276 277 278 279 280
## 92317333 6323020 94215621 7813687 4588013 166900786 96936339
## 281 282 283 284 285 286 287
## 498291361 2356089726 17878909 140884076 92474753 59795832 88804086
## 288 289 290 291 292 293 294
## 202956272 2293165625 675130863 10006508 410834852 1772715468 4614968
## 295 296 297 298 299 300 301
## 15190655 2877101 265346031 482650539 1500597002 85379315 45397337
## 302 303 304 305 306 307 308
## 618209036 150205323 18842115 159680973 377665098 406786932 17158219
## 309 310 311 312 313 314 315
## 142440561 59907535 71149267 2989356 1773697282 65852761 1213142556
## 316 317 318 319 320 321 322
## 94346816 77894630 108690124 54936711 21704026 23871379 608264601
## 323 324 325 326 327 328 329
## 1259023505 133554708 8164420 43442334 12625315 1827665394 2296141899
## 330 331 332 333 334 335 336
## 83448671 2352998090 594583446 180074497 135692220 366161498 190794766
## 337 338 339 340 341 342 343
## 147203905 193983068 1756416709 67622753 358975426 178014668 174432180
## 344 345 346 347 348 349 350
## 195214821 120291964 38135326 23825286 69307693 29910496 2648213
## 351 352 353 354 355 356 357
## 139733532 79613014 12570020 153660689 199506350 604850820 79830325
## 358 359 360 361 362 363 364
## 92370607 3344301 2557262 100678077 22487671 191437813 6704523
## 365 366 367 368 369 370 371
## 10061840 95431607 180112135 64125918 65723524 12065216 179699028
## 372 373 374 375 376 377 378
## 144470144 58220292 1301519378 1912948 324916095 468758812 1452957008
## 379 380 381 382 383 384 385
## 270462782 728519408 224937079 1788786490 431469532 34081827 68778351
## 386 387 388 389 390 391 392
## 1571158 140343439 916586006 10037323 21247551 115078577 4535495
## 393 394 395 396 397 398 399
## 80185902 86131440 88391430 56510899 72467309 274831013 224354769
## 400 401 402 403 404 405 406
## 2635110 85660411 65198389 215582097 105268073 10571497 129671959
## 407 408 409 410 411 412 413
## 17440761 72766072 44135718 16529136 2601574 383593589 208715856
## 414 415 416 417 418 419 420
## 25719992 4522006 53824187 83382656 345932998 207599837 837555354
## 421 422 423 424 425 426 427
## 2197669337 2170558859 1530077587 7391804 80262384 95639933 42850291
## 428 429 430 431 432 433 434
## 53514620 9979194 353292452 532435076 23987109 35527892 159475932
## 435 436 437 438 439 440 441
## 17933318 193488265 5045830 35021454 158331736 8344478 22367726
## 442 443 444 445 446 447 448
## 1374221063 1301949 799651802 681191745 53813745 161828488 130972980
## 449 450 451 452 453 454 455
## 34831455 22594580 56297642 16188231 3845681 3101461 21879371
## 456 457 458 459 460 461 462
## 474682868 140952110 139974022 112184813 58883277 107579250 489951003
## 463 464 465 466 467 468 469
## 231661733 124450510 2636193 380764490 174632949 159610351 541968498
## 470 471 472 473 474 475 476
## 4808069 6191942 4818489 3013920 435532548 643773262 832831053
## 477 478 479 480 481 482 483
## 1234746169 6379594 2328172 3296936 241655362 86401950 2604423
## 484 485 486 487 488 489 490
## 97427993 91271781 18820050 155394714 1551358 2388850803 109252755
## 491 492 493 494 495 496 497
## 3028900 600408759 4787813 157859059 321615311 3836065 24234273
## 498 499 500 501 502 503 504
## 64299056 67270113 181197820 1309640315 46623482 493222307 1058847688
## 505 506 507 508 509 510 511
## 35585135 46074783 6941983 9416464 9215110 131000997 138140581
## 512 513 514 515 516 517 518
## 6198792 87456551 1557250 444074216 128890771 768168541 70629977
## 519 520 521 522 523 524 525
## 27371853 14814371 657773931 15882840 97156483 29036576 1462022142
## 526 527 528 529 530 531 532
## 131658844 578464050 97052426 69448479 2888760 2368360516 196941667
## 533 534 535 536 537 538 539
## 166825732 368858264 191024466 36700210 35563258 77717495 67630297
## 540 541 542 543 544 545 546
## 747282424 38285518 9290017 192578995 4065441954 104487040 566335458
## 547 548 549 550 551 552 553
## 10628481 132913490 10272116 2102587052 179041484 15713891 167630815
## 554 555 556 557 558 559 560
## 124950280 319347365 14737633 69309892 15415526 1597958462 2683139
## 561 562 563 564 565 566 567
## 84355135 119122458 6176940 81889085 7800250 4494529 40506865
## 568 569 570 571 572 573 574
## 52527162 133251631 2087815517 14081083 4888871 22513660 999199371
## 575 576 577 578 579 580 581
## 174618880 149161044 2743977 3429538218 94381019 10226459 166518635
## 582 583 584 585 586 587 588
## 2660691 40286684 310372424 1523781 22759751 14843605 1930280475
## 589 590 591 592 593 594 595
## 185662055 35614328 140012651 70874534 6543546 235641989 32490043
## 596 597 598 599 600 601 602
## 77698097 58233902 31202577 55238657 1119734308 2639580 83990436
## 603 604 605 606 607 608 609
## 122342540 258411167 304871969 86008114 12602097 658897358 19592864
## 610 611 612 613 614 615 616
## 1539201720 72902967 43066236 4837059 45483144 3503017 1845603257
## 617 618 619 620 621 622 623
## 135686068 542755336 1185525114 114575611 13326628 1613887893 84139031
## 624 625 626 627 628 629 630
## 1197815731 146890321 13895886 45422253 128093290 128963372 1846781373
## 631 632 633 634 635 636 637
## 101531234 3877913 11275651 51326247 88018921 207388138 7293842
## 638 639 640 641 642 643 644
## 620313465 405628921 167430055 44320426 1074414555 172502307 19874501
## 645 646 647 648 649 650 651
## 353324043 102652030 37386833 67949658 2903142 154286346 95872517
## 652 653 654 655 656 657 658
## 111727772 68413085 72560297 149689073 608010967 11571438 16402787
## 659 660 661 662 663 664 665
## 696055190 206919158 41301204 492073235 26416546 1272459 730510566
## 666 667 668 669 670 671 672
## 1810604682 75585967 1599536529 2088519413 42134507 23317326 15483039
## 673 674 675 676 677 678 679
## 19278625 38144955 2133675077 52034402 155654485 2127119849 152618060
## 680 681 682 683 684 685 686
## 102968636 6639895 1522409 1607592866 97099279 22630360 126220771
## 687 688 689 690 691 692 693
## 59605358 29480806 687866655 1210886240 4391723 64944534 5540346
## 694 695 696 697 698 699 700
## 5496188 12740060 10192712 851291915 1621228744 120265591 12194577
## 701 702 703 704 705 706 707
## 4048476 90863295 90149996 28905883 79594352 28795606 1970552034
## 708 709 710 711 712 713 714
## 105165130 37263894 29811805 2955559 101964537 68916720 3904648
## 715 716 717 718 719 720 721
## 5997252 147310508 91346837 171683049 117475862 149374002 97341396
## 722 723 724 725 726 727 728
## 126674257 168207203 1574644 101942599 1674745039 44296018 277188248
## 729 730 731 732 733 734 735
## 4880720 45862606 374540369 101119875 17862065 89072974 195928315
## 736 737 738 739 740 741 742
## 91670214 1632967832 12080411 1309033133 1987083058 73877203 332618025
## 743 744 745 746 747 748 749
## 1870116430 14055223 77752510 98027590 137567800 2620778 73060425
## 750 751 752 753 754 755 756
## 9325675 381429516 3601981 201656495 139807790 293089358 25225048
## 757 758 759 760 761 762 763
## 63628118 531581572 29375827 1317648781 15344879 5800469 362216710
## 764 765 766 767 768 769 770
## 9376651 82551207 140017769 64857189 49581974 204749652 47944342
## 771 772 773 774 775 776 777
## 780165121 124126446 163531547 314711347 52599922 111323298 48686496
## 778 779 780 781 782 783 784
## 55340286 35110679 97224235 333078392 1296024 87921664 600778949
## 785 786 787 788 789 790 791
## 18850352 41026903 162087285 3643703 27048662 180850715 31957918
## 792 793 794 795 796 797 798
## 1547552 7416951 448856887 51845764 334965585 18125329 22191104
## 799 800 801 802 803 804 805
## 140147552 320254032 49526787 204601302 4387392 1504223442 3266467
## 806 807 808 809 810 811 812
## 59637919 810404759 4530434 1261445 10897821 88465061 40349293
## 813 814 815 816 817 818 819
## 121090266 19537959 31084169 3495009 8032618 12881332 547182758
## 820 821 822 823 824 825 826
## 3038932971 55303305 7141224 2603436 67403109 156594886 257895644
## 827 828 829 830 831 832 833
## 1918806827 431170269 1567229269 37312587 179127050 27640021 22193757
## 834 835 836 837 838 839 840
## 137691127 28820469 51138734 19300603 135676839 40874771 159072560
## 841 842 843 844 845 846 847
## 2303845 151638379 1296898169 757581563 101253502 2024922470 97282615
## 848 849 850 851 852 853 854
## 5902550 8793888 112190210 1388391718 199085567 1772606307 137360846
## 855 856 857 858 859 860 861
## 580688330 3485349 1678111766 249936427 331587839 120028079 2125623868
## 862 863 864 865 866 867 868
## 51008664 150308689 29692239 76964879 43444378 1283868 133781995
## 869 870 871 872 873 874 875
## 172127891 19211076 71374559 11449580 35494097 46782814 78887708
## 876 877 878 879 880 881 882
## 7190845 682825155 44154754 39351462 39726921 11796201 7731284
## 883 884 885 886 887 888 889
## 6642893 2138656116 23710795 388517411 740314658 27701147 2802587
## 890 891 892 893 894 895 896
## 142454236 859722684 52342703 108436962 1953046504 183470245 170407738
## 897 898 899 900 901 902 903
## 391597589 4898094 2644550 4447621 75332364 2368159770 21647096
## 904 905 906 907 908 909 910
## 65875097 159637465 20753027 23408597 58132335 229830100 305811128
## 911 912 913 914 915 916 917
## 6919734 1137329803 206581020 58029792 27548051 6075046 473719250
## 918 919 920 921 922 923 924
## 1229208911 169834835 27418561 180666824 180973360 30021688 18588964
## 925 926 927 928 929 930 931
## 38952644 641297953 8440003 144543216 181196323 39445865 8517189
## 932 933 934 935 936 937 938
## 38803014 101760414 53858620 21757957 149427291 1030371390 80222551
## 939 940 941 942 943 944 945
## 5269945 89833793 1239900 91013386 4880136 2624628 168298435
## 946 947 948 949 950 951 952
## 136059422 51135354 1523985946 40317183 396999652 132829298 2251824028
## 953 954 955 956 957 958 959
## 20415960 1520164093 400028595 14953062 1763152568 158793107 1683049945
## 960 961 962 963 964 965 966
## 809944085 7407690 11185934 209229120 90083632 700002311 22442870
## 967 968 969 970 971 972 973
## 573979870 56381494 10702050 73749215 114343904 24834850 6346945
## 974 975 976 977 978 979 980
## 3065782 5354501 260177416 60758254 8376765 94000185 23814878
## 981 982 983 984 985 986 987
## 650632758 20172858 368299427 281828046 24074966 57993796 70573729
## 988 989 990 991 992 993 994
## 802639332 20339265 212090216 11358704 50919723 102190921 29980118
## 995 996 997 998 999 1000 1001
## 269347756 63638651 54899660 192600214 42809094 27655296 301126106
## 1002 1003 1004 1005 1006 1007 1008
## 1187785746 3858776 450406384 74272910 19577454 19620930 620301513
## 1009 1010 1011 1012 1013 1014 1015
## 539766093 98966993 68221679 351881623 1337396399 76664849 28885025
## 1016 1017 1018 1019 1020 1021 1022
## 146778313 7294555 15834698 155892234 676545113 77248049 1266440659
## 1023 1024 1025 1026 1027 1028 1029
## 1780989419 2899054 73282056 4046966 270355612 465991813 96841784
## 1030 1031 1032 1033 1034 1035 1036
## 47182580 469500063 1972617499 17046511 188774033 167449286 146044042
## 1037 1038 1039 1040 1041 1042 1043
## 1404446458 1577378073 5028048 505586874 409087088 2877549 1120065658
## 1044 1045 1046 1047 1048 1049 1050
## 9939785 129605049 478366463 53521201 1979617613 12856262 1577533588
## 1051 1052 1053 1054 1055 1056 1057
## 64222132 206916797 86092228 640096129 11187642 112039205 68361818
## 1058 1059 1060 1061 1062 1063 1064
## 321126565 6112790 19836977 3892763 133275718 2397127152 42761231
## 1065 1066 1067 1068 1069 1070 1071
## 32491379 49509572 80439063 33043205 205633702 119229787 1589033407
## 1072 1073 1074 1075 1076 1077 1078
## 195008237 3614021 146096573 174094004 20738847 72965407 4383978
## 1079 1080 1081 1082 1083 1084 1085
## 1201553774 229571401 141031835 19762941 34185603 16545755 225296318
## 1086 1087 1088 1089 1090 1091 1092
## 361538603 116353027 128675316 94855328 111670117 1736114992 127168349
## 1093 1094 1095 1096 1097 1098 1099
## 12837468 1149145168 127461198 20728192 1991987873 2775983 530658474
## 1100 1101 1102 1103 1104 1105 1106
## 10358827 281146367 126424070 11990039 128902765 416632689 106694891
## 1107 1108 1109 1110 1111 1112 1113
## 80617445 109924201 8383605 73892294 132314300 1758979297 584262915
## 1114 1115 1116 1117 1118 1119 1120
## 28126670 5700429 116593393 84883828 1304362987 1464888762 32315244
## 1121 1122 1123 1124 1125 1126 1127
## 1166750807 69519425 2176396719 357014013 1672455065 202911125 104141857
## 1128 1129 1130 1131 1132 1133 1134
## 33960538 205906589 2960108 73499943 13577390 428461311 99630283
## 1135 1136 1137 1138 1139 1140 1141
## 386697446 122680330 57976860 10033977 13656500 1360896630 81695491
## 1142 1143 1144 1145 1146 1147 1148
## 63128688 734868234 40056040 92562207 127228669 2764762869 5076611
## 1149 1150 1151 1152 1153 1154 1155
## 116258333 35647298 4819649 149477309 1675433185 31601313 121127024
## 1156 1157 1158 1159 1160 1161 1162
## 52117250 1577229246 207865317 6008798 15848292 59567887 26165986
## 1163 1164 1165 1166 1167 1168 1169
## 359268950 4806902 51042356 27238331 120402076 20437008 21732289
## 1170 1171 1172 1173 1174 1175 1176
## 37250644 294819763 504872602 122853817 41586847 19582128 4604701
## 1177 1178 1179 1180 1181 1182 1183
## 570164715 42091029 8357595 374095702 58393724 8077592 6887392
## 1184 1185 1186 1187 1188 1189 1190
## 89075466 335611383 73865853 1403020002 191404767 473589545 172085562
## 1191 1192 1193 1194 1195 1196 1197
## 28287348 188137194 169244831 75026586 17017830 354580313 1108833404
## 1198 1199 1200 1201 1202 1203 1204
## 32383804 40761552 24264391 38312750 76106360 4189475 99093144
## 1205 1206 1207 1208 1209 1210 1211
## 331789327 26087037 1361670931 1475058177 411596494 152211182 28776534
## 1212 1213 1214 1215 1216 1217 1218
## 554787368 2869938 116581653 15581923 165937978 29230622 16397398
## 1219 1220 1221 1222 1223 1224 1225
## 1734911486 56672394 22178665 43354090 71118786 682110205 46913171
## 1226 1227 1228 1229 1230 1231 1232
## 22913192 43976632 51162792 112032634 142289305 3601423146 406381285
## 1233 1234 1235 1236 1237 1238 1239
## 155503376 128499707 72359860 7241082 208511688 149196526 48671336
## 1240 1241 1242 1243 1244 1245 1246
## 10431788 2233537223 2456957603 18384946 10003958 1271425 31434608
## 1247 1248 1249 1250 1251 1252 1253
## 82673542 36605994 2642562 1413660588 347443947 1520694 263231540
## 1254 1255 1256 1257 1258 1259 1260
## 250262771 19414951 41793870 130581633 127606955 903239088 103800063
## 1261 1262 1263 1264 1265 1266 1267
## 20569718 10682762 45711552 53707181 107360176 724501163 114379298
## 1268 1269 1270 1271 1272 1273 1274
## 1172752902 3504578 74063257 10783917 9079382 209354868 22449588
## 1275 1276 1277 1278 1279 1280 1281
## 290180969 119894105 7471715 18906791 504135064 17476624 68463681
## 1282 1283 1284 1285 1286 1287 1288
## 601540897 203778290 2930902 2246193937 72680807 13867532 29849408
## 1289 1290 1291 1292 1293 1294 1295
## 1469658929 50954022 50763424 1212450047 2270673 86351676 142119239
## 1296 1297 1298 1299 1300 1301 1302
## 3827285 2891903 18763880 27589651 7303117 3916703774 2181663159
## 1303 1304 1305 1306 1307 1308 1309
## 10241146 1430389805 451570269 6032159 259421225 460687375 1148670723
## 1310 1311 1312 1313 1314 1315 1316
## 47152948 48048669 20816669 20496809 1324172086 351828607 126876915
## 1317 1318 1319 1320 1321 1322 1323
## 2969682 1334248 379773018 51733629 29335311 789129395 168258766
## 1324 1325 1326 1327 1328 1329 1330
## 1926084670 17902017 172488432 49573233 87766893 501186968 106412953
## 1331 1332 1333 1334 1335 1336 1337
## 159250576 116367967 130008897 112170908 4829511 2629157 3997901
## 1338
## 848644805# co the dung ham anova
MSE1= anova(m)#Việc 5: Mô phỏng và lấy mẫu. Trong code dưới đây chúng ta sẽ mô phỏng một dân số (population) gồm 100 000 người (phut 2:16)
#việc 6: lựa chọn biến để thao tác trong data
# goi ten cac bien trong data fmh
names(fmh)## [1] "id" "sex" "tot.chol" "age" "sysbp"
## [6] "diasbp" "smoker" "cigs.day" "bmi" "diabetes"
## [11] "bpmed" "heart.rate" "glucose" "educ" "prev.chd"
## [16] "prev.ap" "prev.mi" "prev.stroke" "prev.hyp" "time"
## [21] "period" "hdlc" "ldlc" "death" "angina"
## [26] "hosp.mi" "mi.fchd" "any.chd" "stroke" "cvd"
## [31] "hypertension" "time.ap" "time.mi" "time.mi.1" "time.chd"
## [36] "time.stroke" "time.cvd" "time.dth" "time.hyp"# lay data trong 3 cot id, sex, age de lam viec
df1 = fmh[, c("id", "sex", "age")] # co dau "" voi id, sex, age hieu ten moi bien hieu la lable
head(df1)## id sex age
## 1 2448 1 39
## 2 2448 1 52
## 3 6238 2 46
## 4 6238 2 52
## 5 6238 2 58
## 6 9428 1 48df2= fmh[, c(1,2,4)] # 1,2,4: so thu tu cua moi bien trong data
head(df2)## id sex age
## 1 2448 1 39
## 2 2448 1 52
## 3 6238 2 46
## 4 6238 2 52
## 5 6238 2 58
## 6 9428 1 48df3= fmh %>% select(id, sex, age) # khong co dau "" voi id, sex, age vi o day la ten bien
head(df3)## id sex age
## 1 2448 1 39
## 2 2448 1 52
## 3 6238 2 46
## 4 6238 2 52
## 5 6238 2 58
## 6 9428 1 48#ket qua df1, df2, df3 nhu nhau