This data set has been analyzed and provided by the listed reference. Examined were two groups with different types of HIV (Type B and Type C), each consisting of 73 participants. Within both groups the number of amino-acid mutations at each position was determined.
data("hiv")data("hiv_four_columns")
hiv is a data.frame with 118 rows and the following two
columns:
Number of test subjects with HIV type C and mutated i-th amino acid.
Number of test subjects with HIV type B and mutated i-th amino acid.
Thus, each row describes a 2x2 table:
| Subject 1 | Mutation | No mutation |
| Type C | \(X_{i, 1}\) | 73 - \(X_{i, 1}\) |
| Type B | \(X_{i, 2}\) | 73 - \(X_{i, 2}\) |
hiv_four_columns is a data.frame with 118 rows and the
following four columns:
Number of test subjects with HIV type C and mutated i-th amino acid.
Number of test subjects with HIV type B and mutated i-th amino acid.
Number of test subjects with HIV type C and non-mutated i-th amino acid.
Number of test subjects with HIV type B and non-mutated i-th amino acid.
Thus, each row describes a 2x2 table:
| Subject 1 | mutation | no mutation |
| Type C | \(X_{i, 1}\) | \(X_{i, 3}\) |
| Type B | \(X_{i, 2}\) | \(X_{i, 4}\) |
Gilbert, P. B. (2005). A modified false discovery rate multiple-comparisons procedure for discrete data, applied to human immunodeficiency virus genetics. Journal of the Royal Statistical Society, 54(1), pp. 143-158. tools:::Rd_expr_doi("10.1111/j.1467-9876.2005.00475.x")