Skip to main content

Table 1 Top 10 covariates returned by four RF runs with 500 trees

From: Detecting gene-by-smoking interactions in a genome-wide association study of early-onset coronary heart disease using random forests

 

Run 1

Run 2

Run 3

Run 4a

Rank

Covariate

Importance

Covariate

Importance

Covariate

Importance

Covariate

Importance

1

Birth decade 1900

16.3077

Birth decade 1900

20.2087

Birth decade 1900

17.6408

Birth decade 1900

19.6011

2

Birth decade 1930

8.8219

Birth decade 1930

8.2609

Birth decade 1930

11.7332

Birth decade 1930

10.2538

3

Smoking

1.7807

Smoking

2.5351

Birth decade 1920

1.7106

Smoking

2.8397

4

Birth decade 1920

1.1131

Birth decade 1920

0.6642

Smoking

1.6917

Birth decade 1920

1.6002

5

Sex

0.9290

rs2011345_C

0.4265

Sex

0.8159

Sex

0.4328

6

rs2011345_C

0.4912

rs32732_G

0.3341

rs3866685_A

0.2945

rs2566762_T

0.2865

7

rs9349061_T

0.4427

rs17456025_A

0.3095

rs2011345_C

0.2915

rs549582_T

0.2757

 

rs732998_T

0.2739

rs2396500_G

0.2993

rs4849404_C

0.2714

rs963274_T

0.2424

9

rs949753_G

0.2719

Sex

0.2935

Birth decade 1910

0.2694

rs4490198_G

0.2059

10

rs1686567_A

0.2664

rs6565249_T

0.2538

rs12052316_A

0.2594

rs17456025_A

0.2047

  1. ars2011345 was ranked 30th, with an importance score of 0.1268