Final Project for LIS4273
FinalStatsProjectRCode.R
Tyler House
2021-11-27
#Final
R stats Project
#This
project will be on the topic of heart disease predictors, and if certain
other.....
##
##set
directory and load the dataset and entitle heartdata
setwd("C:/users/Tyler/Desktop/FinalStatsProject")
heartdata <- read.csv("heart.csv")
##This
dataset is huge and I will select only samples of 100
##Most
doctors, other medical professionals and medical editorials will state that
most men and women in America in recent years
#tend to
have an increasing propensity to have heart disease after the age of 40 due to
a variety of factors and combinations of these factors
#the
purpose of this analysis is to employ a dataset that revolves around heart
disease while simultaneously listing off crucial vital sign data
#that would
be predictive of heart disease regardless of the Y/N column that
heartdata$HeartDisease is.
##My
hypothesis is that people from the ages of 40 onward will have greater heart
disease presence despite any other variables influence
#the causes
and circumstances of the relationship should be assumed to be unknown and
negated, all we know is that there could be a trend simply because data exists
##My
alternative hypothesis is that an increase in age or any health related metric
does not necessarily dictate a higher heart disease presence among men and
women above the age of 40
#Given that
I have some medical knowledge and took some time to review large chunks of the
data at a time and explore some metrics
#i
concluded that there is a good enough spread to take multiple samples and
achieve a high level of random selection.
#We want to
derive some values in order to start our analysis so, we will need the mean,
range and number of each of the columns
mean(heartdata$Age)
## [1] 53.51089
range(heartdata$Age)
## [1] 28 77
mean(heartdata$HeartDisease)
## [1] 0.5533769
range(heartdata$HeartDisease)
## [1] 0 1
mean(heartdata$Cholesterol)
## [1] 198.7996
range(heartdata$Cholesterol)
## [1] 0 603
#The
above values are calculated for every single observation in the dataset, now
lets take some samples!!
#we will
take 100 member samples for each of the three at random
#sub1 is
the initial constraint for the sample and that is to select only two columns
which is the presence of heart disease and the age of the person
#I want to
mention that sub1 will instrumental to the development of the compounded subset
that will define the data used to draw samples from
sub1 <- subset(heartdata, HeartDisease = 1 , select
= c(HeartDisease,Age)
)
#This
subset will be used to derive the samples, sub1 is the prensence of heart
disease for all entities in the dataset
##and
sampledata combines this with the constraint of all entities for the cleaned
data being over the age of 40, omitting over 300 entities.
uppersampledata <- subset(sub1, Age > 40, select
= c(HeartDisease,Age))
lowersampledata <- subset(sub1, Age < 40, select
= c(HeartDisease,Age))
print(uppersampledata)
## HeartDisease Age
## 2
1 49
## 4
1 48
## 5
0 54
## 7
0 45
## 8
0 54
## 10
0 48
## 12
1 58
## 14
1 49
## 15
0 42
## 16
0 54
## 18
0 43
## 19 1 60
## 21
0 43
## 22
0 44
## 23
0 49
## 24
1 44
## 27
0 53
## 28
0 52
## 29
0 53
## 30
0 51
## 31
1 53
## 32
0 56
## 33
1 54
## 34
1 41
## 35
0 43
## 37
1 65
## 38
0 41
## 39
0 48
## 40
0 48
## 41
0 54
## 42
1 54
## 44 0 52
## 45
1 43
## 46
0 59
## 48
0 50
## 50
1 41
## 51
1 50
## 52
1 47
## 53
0 45
## 54
0 41
## 55
0 52
## 56
0 51
## 58 1
58
## 59
0 54
## 60
1 52
## 61
0 49
## 62
0 43
## 63
0 45
## 64
1 46
## 65
0 50
## 67
0 45
## 69
1 52
## 70
0 44
## 71
1 57
## 72
0 44
## 73
1 52
## 74
0 44
## 75
1 55
## 76
0 46
## 79
0 52
## 80
1 49
## 81
0 55
## 82
0 54
## 83 1 63
## 84
0 52
## 85
1 56
## 86
1 66
## 87
1 65
## 88
0 53
## 89
1 43
## 90
0 55
## 91
0 49
## 93
0 52
## 94
1 48
## 96
1 58
## 97
0 43
## 99
0 56
## 100
0 41
## 101
1 65
## 102
0 51
## 105
1 46
## 106
0 57
## 107
0 48
## 109 0 50
## 111
0 59
## 112
1 57
## 113
0 47
## 115
0 49
## 118
1 59
## 121
1 47
## 122
0 52
## 123
0 46
## 124
1 58
## 125
0 58
## 126 0
54
## 128
0 48
## 129
0 54
## 130
0 42
## 132
1 46
## 133
1 56
## 134
1 56
## 135
0 61
## 136
1 49
## 137
0 43
## 139
1 54
## 140
1 43
## 141
1 52
## 142
1 50
## 143
1 47
## 144
0 53
## 145
1 56
## 147
0 42
## 148
0 43
## 149
0 50
## 150
1 54
## 152
0 48
## 154
0 55
## 155
0 41
## 156
1 56
## 158
0 49
## 159
1 44
## 160
0 54
## 161
1 59
## 162
1 49
## 163
0 47
## 164 0 42
## 165
0 52
## 166
1 46
## 167
1 50
## 168
0 48
## 169
0 58
## 170
0 58
## 173
0 53
## 174
0 49
## 175
1 52
## 176
1 43
## 177 1
54
## 178
0 59
## 180
0 46
## 181
1 52
## 182
0 51
## 183
1 52
## 184
0 46
## 185
0 54
## 186
1 58
## 187
0 58
## 188
1 41
## 189
0 50
## 190
1 53
## 191
0 46
## 192
0 50
## 193
0 48
## 194
0 45
## 195
0 41
## 196
0 62
## 197
0 49
## 198
0 42
## 199 1 53
## 200
0 57
## 201
0 47
## 202
0 46
## 203
0 42
## 205
0 56
## 206
0 50
## 210
1 54
## 211
1 48
## 212
1 50
## 213
0 56
## 214
0 56
## 215
1 47
## 218
0 54
## 219
0 55
## 221
1 46
## 222
1 51
## 223
0 48
## 225
0 55
## 226
1 50
## 227 0 53
## 229
0 41
## 234
0 41
## 235
0 54
## 237
1 41
## 238
1 55
## 239
1 48
## 240
1 48
## 241
0 55
## 242
1 54
## 243
1 55
## 244 0
43
## 245
1 48
## 246
0 54
## 247
1 54
## 248
1 48
## 249
1 45
## 250
1 49
## 251
1 44
## 252
1 48
## 253
0 61
## 254
0 62
## 255
1 55
## 256
0 53
## 257
0 55
## 259
0 51
## 260
0 55
## 261
0 46
## 262
0 54
## 263
1 46
## 264
1 59
## 265
1 47
## 266 0 54
## 267
1 52
## 269
1 54
## 270
0 47
## 271
0 45
## 273
1 55
## 274
0 55
## 275
0 45
## 276
0 59
## 277
1 51
## 278
1 52
## 279
0 57
## 280
0 54
## 281
0 60
## 282
1 49
## 283
0 51
## 284
0 55
## 285
0 42
## 286
0 51
## 287
0 59
## 288 0 53
## 289
0 48
## 291
0 48
## 292
0 47
## 293
0 53
## 294
1 65
## 296
1 61
## 297
1 50
## 298
1 57
## 299
1 51
## 300
1 47
## 301 1
60
## 302
0 55
## 303
1 53
## 304
1 62
## 305
1 51
## 306
1 51
## 307
1 55
## 308
0 53
## 309
1 58
## 310
1 57
## 311
0 65
## 312
1 60
## 313
1 41
## 315
0 53
## 316
1 74
## 317
1 57
## 318
1 56
## 319
1 61
## 320
1 68
## 321
1 59
## 322
1 63
## 324 1 62
## 325
1 46
## 326
1 42
## 327
0 45
## 328
1 59
## 329
1 52
## 330
1 60
## 331
1 60
## 332
1 56
## 335
1 51
## 336
1 62
## 337
0 72
## 338
1 63
## 339
1 63
## 340
1 64
## 341
1 43
## 342
1 64
## 343
1 61
## 344
1 52
## 345
1 51
## 346 1 69
## 347
1 59
## 348
1 48
## 349
1 69
## 351
1 53
## 352
1 43
## 353
1 56
## 354
1 58
## 355
1 55
## 356
1 67
## 357
1 46
## 358 1
53
## 360
1 53
## 361
1 62
## 362
1 47
## 363
1 56
## 364
1 56
## 365
0 56
## 366
1 64
## 367
1 61
## 368
1 68
## 369
1 57
## 370
1 63
## 371
1 60
## 372
1 66
## 373
1 63
## 374
1 59
## 375
1 61
## 376
1 73
## 377
1 47
## 378
1 65
## 379
1 70
## 380 1 50
## 381
1 60
## 382
1 50
## 383
1 43
## 385
1 54
## 386
1 61
## 387
1 42
## 388
1 53
## 389
1 55
## 390
1 61
## 391
1 51
## 392
1 70
## 393
1 61
## 395
1 57
## 397
1 62
## 398
1 58
## 399
1 52
## 400
1 61
## 401
1 50
## 402
1 51
## 403 1 65
## 404
1 52
## 405
1 47
## 407
1 57
## 408
1 62
## 409
1 59
## 410
1 53
## 411
1 62
## 412
1 54
## 413
1 56
## 414
1 56
## 415 1
54
## 416
1 66
## 417
1 63
## 418
0 44
## 419
1 60
## 420
1 55
## 421
0 66
## 422
0 66
## 423
1 65
## 424
0 60
## 425
1 60
## 426
1 60
## 427
0 56
## 428
1 59
## 429
1 62
## 430
1 63
## 431
1 57
## 432
0 62
## 433
1 63
## 434
1 46
## 435
0 63
## 436
0 60
## 437
1 58
## 438
1 64
## 439
1 63
## 440
0 74
## 441
1 52
## 442
1 69
## 443
1 51
## 444
1 60
## 445
1 56
## 446 1 55
## 447
1 54
## 448
1 77
## 449
1 63
## 450
1 55
## 451
1 52
## 452
1 64
## 453
1 60
## 454
0 60
## 455
1 58
## 456
0 59
## 457 1
61
## 459
1 61
## 460
0 41
## 461
1 57
## 462
1 63
## 463
1 59
## 464
0 51
## 465
1 59
## 466
0 42
## 467
1 55
## 468
0 63
## 469
1 62
## 470
0 56
## 471
1 53
## 472
1 68
## 473
1 53
## 474
1 60
## 475
0 62
## 476
1 59
## 477
0 51
## 478
1 61
## 479 1 57
## 480
1 56
## 481
1 58
## 482
1 69
## 483
1 67
## 484
1 58
## 485
1 65
## 486
1 63
## 487
0 55
## 488
1 57
## 489
0 65
## 490
1 54
## 491
1 72
## 492
1 75
## 493
1 49
## 494
1 51
## 495
1 60
## 496
1 64
## 497
0 58
## 498
1 61
## 499 1 67
## 500
1 62
## 501
1 65
## 502
1 63
## 503
1 69
## 504
0 51
## 505
1 62
## 506
1 55
## 507
1 75
## 509
1 67
## 510
1 58
## 511 0
60
## 512
1 63
## 514
1 62
## 515
1 43
## 516
0 63
## 517
1 68
## 518
1 65
## 519
1 48
## 520
1 63
## 521
0 64
## 522
1 61
## 523
1 50
## 524
1 59
## 525
0 55
## 526
0 45
## 527
1 65
## 528
0 61
## 529
1 49
## 530
1 72
## 531
1 50
## 532
1 64
## 533 1 55
## 534
1 63
## 535
1 59
## 536
1 56
## 537
1 62
## 538
1 74
## 539
1 54
## 540
0 57
## 541
1 62
## 542
1 76
## 543
1 54
## 544
1 70
## 545
0 61
## 546
0 48
## 547
1 48
## 548
1 61
## 549
1 66
## 550
0 68
## 551
1 55
## 552
0 62
## 553 1 71
## 554
1 74
## 555
0 53
## 556
1 58
## 557
0 75
## 558
1 56
## 559
1 58
## 560
1 64
## 561
0 54
## 562
0 54
## 563
0 59
## 564 1
55
## 565
1 57
## 566
1 61
## 567
0 41
## 568
1 71
## 570
1 55
## 571
1 56
## 572
1 69
## 573
1 64
## 574
1 72
## 575
1 69
## 576
1 56
## 577
1 62
## 578
1 67
## 579
1 57
## 580
1 69
## 581
1 51
## 582
1 48
## 583
1 69
## 584
0 69
## 585
1 64
## 586 1 57
## 587
1 53
## 589
1 67
## 590
1 74
## 591
0 63
## 592
0 58
## 593
1 61
## 594
1 64
## 595
1 58
## 596
1 60
## 597
1 57
## 598
0 55
## 599
1 55
## 600
1 56
## 601
0 57
## 602
1 61
## 603
1 61
## 604
1 74
## 605
0 68
## 606
0 51
## 607 1 62
## 608
1 53
## 609
1 62
## 610
1 46
## 611
1 54
## 612
0 62
## 613
1 55
## 614
0 58
## 615
1 62
## 616
1 70
## 617
0 67
## 618 1
57
## 619
0 64
## 620
0 74
## 621
0 65
## 622
1 56
## 623
1 59
## 624
1 60
## 625
1 63
## 626
0 59
## 627
0 53
## 628
0 44
## 629
1 61
## 630
0 57
## 631
0 71
## 632
1 46
## 633
1 53
## 634
0 64
## 636
1 67
## 637
0 48
## 638
0 43
## 639
0 47
## 640 0 54
## 641
0 48
## 642
0 46
## 643
0 51
## 644
1 58
## 645
0 71
## 646
1 57
## 647
0 66
## 649
1 59
## 650
1 50
## 651
1 48
## 652
1 61
## 653
1 59
## 654
0 42
## 655
0 48
## 657
0 62
## 658
0 44
## 659
0 46
## 660
1 59
## 661
0 58
## 662 1 49
## 663
1 44
## 664
1 66
## 665
1 65
## 666
1 42
## 667
0 52
## 668
0 65
## 669
0 63
## 670
0 45
## 671
0 41
## 672
1 61
## 673 0
60
## 674
1 59
## 675
1 62
## 676
0 57
## 677
1 51
## 678
0 44
## 679
0 60
## 680
0 63
## 681
1 57
## 682
0 51
## 683
1 58
## 684
0 44
## 685
1 47
## 686
1 61
## 687
0 57
## 688
0 70
## 689
0 76
## 690
0 67
## 691
1 45
## 692
0 45
## 694
0 42
## 695
0 56
## 696
1 58
## 698
1 58
## 699
0 41
## 700
0 57
## 701
0 42
## 702
0 62
## 703
0 59
## 704
0 41
## 705
1 50
## 706 0 59
## 707
1 61
## 708
1 54
## 709
1 54
## 710
1 52
## 711
1 47
## 712
0 66
## 713
1 58
## 714
0 64
## 715
0 50
## 716
0 44
## 717 1
67
## 718
0 49
## 719
1 57
## 720
1 63
## 721
1 48
## 722
0 51
## 723
1 60
## 724
1 59
## 725
0 45
## 726
1 55
## 727
0 41
## 728
1 60
## 729
0 54
## 730
0 42
## 731
0 49
## 732
1 46
## 733
1 56
## 734
0 66
## 735
1 56
## 736
1 49
## 737
1 54
## 738 1 57
## 739
0 65
## 740
0 54
## 741
0 54
## 742
1 62
## 743
0 52
## 744
0 52
## 745
1 60
## 746
1 63
## 747
1 66
## 748
0 42
## 749
1 64
## 750
0 54
## 751
0 46
## 752
0 67
## 753
1 56
## 755
0 57
## 756
1 64
## 757
0 59
## 758
1 50
## 759 0 51
## 760
1 54
## 761
1 53
## 762
1 52
## 764
1 58
## 765
0 41
## 766
0 41
## 767
0 50
## 768
0 54
## 769
0 64
## 770
0 51
## 771 0
46
## 772
1 55
## 773
0 45
## 774
0 56
## 775
1 66
## 777
1 62
## 778
0 55
## 779
1 58
## 780
0 43
## 781
0 64
## 782
0 50
## 783
0 53
## 784
0 45
## 785
1 65
## 786
0 69
## 787
1 69
## 788
1 67
## 789
0 68
## 791
1 62
## 792
1 51
## 793
1 46
## 794 1 67
## 795
0 50
## 796
0 42
## 797
1 56
## 798
1 41
## 799
0 42
## 800
0 53
## 801
0 43
## 802
1 56
## 803
0 52
## 804
0 62
## 805
1 70
## 806
0 54
## 807
1 70
## 808
0 54
## 810
0 48
## 811
0 55
## 812
0 58
## 813
0 54
## 814
0 69
## 815 1 77
## 816
0 68
## 817
1 58
## 818
1 60
## 819
1 51
## 820
1 55
## 821
0 52
## 822
0 60
## 823
0 58
## 824
1 64
## 826
1 59
## 827 0
51
## 828
0 43
## 829
1 58
## 831
0 41
## 832
0 63
## 833
0 51
## 834
0 54
## 835
0 44
## 836
1 54
## 837
1 65
## 838
0 57
## 839
1 63
## 841
0 41
## 842
1 62
## 843
1 43
## 844
0 58
## 845
0 52
## 846
1 61
## 848
0 45
## 849
1 52
## 850
0 62
## 851 1 62
## 852
0 53
## 853
1 43
## 854
0 47
## 855
0 52
## 856
1 68
## 858
0 53
## 859
1 62
## 860
0 51
## 861
1 60
## 862
1 65
## 863
0 65
## 864
1 60
## 865
1 60
## 866
1 54
## 867
0 44
## 868
1 44
## 869
0 51
## 870
0 59
## 871
0 71
## 872 0 61
## 873
1 55
## 874
1 64
## 875
0 43
## 876
0 58
## 877
1 60
## 878
1 58
## 879
0 49
## 880
1 48
## 881
0 52
## 882
0 44
## 883 0
56
## 884
0 57
## 885
1 67
## 886
0 53
## 887
0 52
## 888
1 43
## 889
1 52
## 890
1 59
## 891
0 64
## 892
0 66
## 894
1 57
## 895
0 58
## 896
1 57
## 897
0 47
## 898
1 55
## 900
1 61
## 901
1 58
## 902
1 58
## 903
0 58
## 904
0 56
## 905
0 56
## 906 1 67
## 907
0 55
## 908
1 44
## 909
1 63
## 910
1 63
## 911
0 41
## 912
1 59
## 913
1 57
## 914
1 45
## 915
1 68
## 916
1 57
## 917
1 57
print(lowersampledata)
## HeartDisease Age
## 3
0 37
## 6
0 39
## 9
1 37
## 11
0 37
## 13
0 39
## 17
1 38
## 20 1 36
## 26
0 36
## 36
0 32
## 43
0 35
## 47
0 37
## 49
0 36
## 57
1 31
## 66
0 37
## 68
0 32
## 77
1 32
## 78
0 35
## 92 0
39
## 95
0 39
## 98
0 39
## 108
0 34
## 110
0 39
## 114
0 38
## 116
1 33
## 117
1 38
## 119
0 35
## 120
1 34
## 127
0 34
## 131
0 38
## 138
0 39
## 146
0 39
## 151
0 39
## 157
1 38
## 171
0 29
## 179
0 37
## 204
0 31
## 207
0 35
## 208
1 35
## 209
0 28
## 216
0 30
## 217
1 39
## 220
0 29
## 224
0 33
## 228
1 38
## 230
0 37
## 231
0 37
## 233
0 38
## 236 0 39
## 258
0 36
## 268
0 34
## 272
0 32
## 290
0 36
## 295
1 32
## 314
1 34
## 323
1 38
## 333
0 38
## 350
1 36
## 359
1 38
## 384 1
38
## 394
1 38
## 396
1 38
## 406
1 35
## 513
0 35
## 569
1 38
## 588
0 37
## 648
0 37
## 693
0 39
## 697
1 35
## 754
0 34
## 776
1 38
## 790
0 34
## 809
1 35
## 825
0 37
## 830
0 29
## 840
0 35
## 847
1 39
## 857
0 39
## 893
0 39
## 899
0 35
## 918 0 38
#As
you can see, the data shown from sample data is just a refined list of two
vectors, of 574 cleaned data entries that list their number of entry at random,
age and presence of heart disease (0/1)
#I will
comment them out because everytime the code is run the numbers change and I aim
to preserve consistency
#there will
be a sample self titled for what data entries they hold either over or under
the age of forty with proper constraints
overforty <- sample(uppersampledata$HeartDisease, 40, replace
= FALSE, prob = NULL)
underforty <- sample(lowersampledata$HeartDisease, 40, replace
= FALSE, prob = NULL)
##Load
libraries
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked
from 'package:stats':
##
## filter, lag
## The following objects are masked
from 'package:base':
##
## intersect,
setdiff, setequal, union
library(stats)
library(EnvStats)
##
## Attaching package: 'EnvStats'
## The following objects are masked
from 'package:stats':
##
## predict,
predict.lm
## The following object is masked
from 'package:base':
##
## print.default
library(ISwR)
#Two way
T-Test using overforty and underforty, both derived from the 918 observation
"heartdata".
t.test(overforty,underforty)
##
## Welch Two Sample
t-test
##
## data: overforty
and underforty
## t = 2.0564, df = 77.718, p-value = 0.0431
## alternative hypothesis: true difference in means is not
equal to 0
## 95 percent confidence interval:
## 0.00716346
0.44283654
## sample estimates:
## mean of x mean of y
## 0.550 0.325
#Welch
Two Sample t-test
#data: overforty and underforty
#t =
1.5744, df = 77.942, p-value = 0.1195
#alternative
hypothesis: true difference in means is not equal to 0
#95 percent
confidence interval:
# -0.04629819
0.39629819
#sample
estimates:
# mean of x mean of y
#0.550 0.375
#These
results boast a very small p value which would suggest that we reject the null
hypothesis as there are factors outside of chance
#that
caused this trend
#this
experiment left little room for underforty as the majority of the people of the
near 1000 in the dataset were over 40. These results would suggest that if age
was the only factor, it would not be enough to be a primary cause of the rise
in heart disease presence
#thee
results would also go against what most will say over the age of forty, so lets
try something else.
#the
results may differ if we put heart disease presence and a max resting heart
rate
#Lets
repeat the above steps and entitle here forth a subsection using heart disease
presence, people over the age of forty who have
#heart
rates over 140 is like running an inline motor at half load, its a reasonable
amount of stress the heart is under. The point of this is to use this metric to
make predictions about the hearts ability
#and
capacity to handle strenuous aerobic activity as age progresses, regardless of
biological sex.
##Null
Hypothesis: Patients over the age of forty have higher heart disease presence
when their max heart rate is over 140
range(heartdata$MaxHR)
## [1] 60 202
#lets
set the threshold for members of these new samples to be a max heart rate above 140
sub2 <- subset(heartdata, HeartDisease = 1, select
= c(HeartDisease,
MaxHR))
upperHRsplit <- subset(sub2, MaxHR > 140, select
= c(HeartDisease,
MaxHR))
lowerHRsplit <- subset(sub2, MaxHR < 140, select
= c(HeartDisease,
MaxHR))
#Two Way T
Test for Heart Rate and Heart Disease
sampleUHR <- sample(upperHRsplit$HeartDisease, 40, replace
= FALSE, prob = NULL)
sampleLHR <- sample(lowerHRsplit$HeartDisease, 40, replace
= FALSE, prob = NULL)
t.test(sampleUHR, sampleLHR)
##
## Welch Two Sample
t-test
##
## data: sampleUHR
and sampleLHR
## t = -4.1867, df = 76.66, p-value = 7.481e-05
## alternative hypothesis: true difference in means is not
equal to 0
## 95 percent confidence interval:
## -0.6271486
-0.2228514
## sample estimates:
## mean of x mean of y
## 0.350 0.775
plot(heartdata$Age,heartdata$MaxHR, xlab = "Age", ylab
= "Max Resting Heartrate")
abline(lm(heartdata$MaxHR~heartdata$Age))
title("Heart
Rate vs Age ")
#This
visual shows a plot with a trendline that shows a linearly decreasing heart
rate capacity as people age. Intuitively there are many conclusions that we can
draw from the results
#Heart
disease is a multivariate issue and cannot be referenced and tested off two
variables alone
#The
concentrations of people at certain ages having certain heart rates begins to
cluster heavily between 40 and 60, presumably because most people that age are
well within a career that typically is sedentary.
#Even if
they are in blue collar industries, many of the more experienced workers work
in management or are a foreman or lead.
#with the p
value of this specific test of these samples being run, will be very close to 0
which would suggest that heart disease presnece and a high resting heart rate
is not enough of a contraint
#to be able
to identify if certain metrics have a dominating effect on human health over
the age of 40.
#This
analysis and hypothesis was constructed to explore the following concepts
# How that not all
statistical tests and metrics give full context to another issue
# That these tests
conversely from the prior, may help statisticians and other data professionals
gain a better grasp
##at the depths
and complexities of the problems they face in the working world
#My
hypothesis and alternate here as follows
#H0-Presence
of heart disease and other metric extremes ALONE do not dictate the presence of
heart disease or bad health over the age of 40
#HA- Other
factors are present that determine heart disease presence over a certain age
(ex. Patient D has high heart rate and heart disease but is also a smoker, but
not all smokers have heart disease)
#I found
this hypothesis to pick at the bones of the skeleton that is the delicate
intricacies of analytic mathematics, performing and conducting experiments
alone is not enough to solve a problem.
#defining
proper constraint and analogous ones with different, but related data will
reveal trends that will advocate towards the probability of extenuating
circumstances being present of not.
#A two
sided t test was needed because i intended on taking multiple samples and the
variances of any sample that I have taken and/or
##
will take is going to have a similar but different variance at least out to 4
decimal places which is enough of a difference to throw off results
##The
p value for every time the code was run on both sections was close to zero
which means that essentially there is a high probability of rejecting the null
rather than failing to reject.
##additionally,
these findings go more towards a more accurate anecdote in public and over
dinner "Everything in Moderation".
##Heart
disease can be caused by numerous things and a combination of such, the some
important things to remember that humans follow similar trends simply because
the only thing we have in common among billions of characteristics, is that we
are humans on earth.
##There
is so much variation and so many differences that makes the world what it is
and using these tools and these mindsets to solve problems helps us as
academics to keep the best interest of our work a top priority.
Comments
Post a Comment