Section: 10 πŸ”– Multiple Hypothesis Testing

  • Lecture slides:
Table 10.1: Snippet of Hindex Dataset
IDN COUNTRY HAPPINESS
1446 76566 Georgia 7.49
330 25368 Madagascar 3.72
1858 30300 Rwand2a4 3.39
4503 47019 Luxembourg 5.71
3371 22889 Mexico 6.22
3519 50266 New Zealand 5.29
76 84902 Somaliland region 8.59
1355 26937 United States 3.28
1788 32982 Chile 4.35
4085 33987 Tajikistan 4.70

10.1 Snippet 1 - Benjamini-Hochberg Algorithm

eyJsYW5ndWFnZSI6InIiLCJzYW1wbGUiOiJwPC1zb3J0KHJvdW5kKHJ1bmlmKDEwMCwgbWluPTAsIG1heD0wLjA1KSwgNCkpXG5wXG5wPC1wKzAuMDAwM1xucFxuI2ltcGxlbWVudCBCZW5qYW1pbmktSG9jaGJlcmcgZm9ybXVsYVxucTwtcmVwKDAuMDUsMTAwKVxucVxucj1jKDE6MTAwKVxucTwtcm91bmQocSpyLzEwMCw0KVxudGVtcDwtcDxxXG4jU2VsZWN0IHAtdmFsdWVzIHdoaWNoIGNvcnJlc3BvbmQgdG8gZGlzY292ZXJpZXMgKHJlamVjdCBOVUxMKVxubWF4aW5kZXg8LW1heCh3aGljaCh0ZW1wPT0nVFJVRScpKVxucFsxOm1heGluZGV4XSJ9

10.2 Snippet 2

Happiness Index synthetic data set which is used in my slides for multiple hypotheses testing

  • How to order by aggregate?

  • First make data frame out of tapply? Use aggregate and list functions.

eyJsYW5ndWFnZSI6InIiLCJzYW1wbGUiOiJIaW5kZXggPC1yZWFkLmNzdihcImh0dHBzOi8vcmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbS9kZXY3Nzk2L2RhdGExMDFfdHV0b3JpYWwvbWFpbi9maWxlcy9kYXRhc2V0L0hpbmRleC5jc3ZcIikgI3dlYiBsb2FkXG5cbkhpbmRleDwtYWdncmVnYXRlKEhpbmRleCRIQVBQSU5FU1MsIGxpc3QoSGluZGV4JENPVU5UUlkpLCBtZWFuKVxuY29sbmFtZXMoSGluZGV4KTwtIGMoXCJDb3VudHJ5XCIsXCJBdmVyYWdlSFwiKVxuI3JlbmFtZXMgY29sdW1ucyBvZiB0aGUgSGluZGV4IGRhdGEgZnJhbWVcbmNvbG5hbWVzKEhpbmRleClcblxuSGluZGV4W29yZGVyKEhpbmRleCRBdmVyYWdlSCksXSJ9