Make nested and crossed balanced hierarchical structures
Arguments
- structure
A formula specifying the structure and sample sizes at each level. See details.
- repeat_obs
Number of repeated observations at the lowest level
- level_names
An optional list, containing names for the levels of different grouping factors
- int_names
An optional vector, containing names for the interactions (see details). These will be applied to the interaction terms in the same order they are specified in the structure argument
- ...
Further arguments passed to or from other methods.
Details
Factors are input as a text string. The name of each factor is followed by the number of levels in that factor in brackets e.g. "individual(100)". Nested factors can be specified using "/", e.g. "population(2)/individual(2)", the lower levels being specified after the higher levels, and the sample sizes of the lower levels. Crossed factors are indicated using "+". Factor levels can be combined to make new combinations, with unique levels for each combination, as an 'interaction' using ':', with factors already in the character existing (e.g. "population(2)/individual(2) + population:individual").
Examples
# simple data structure with 5 'individuals' and 2 observations per individual
make_structure(structure="individual(5)", repeat_obs=2)
#> individual
#> 1 1
#> 2 1
#> 3 2
#> 4 2
#> 5 3
#> 6 3
#> 7 4
#> 8 4
#> 9 5
#> 10 5
# nested data structure with 2 sexes, 5 individuals per sex
# and 2 observations per individual
make_structure(structure="sex(2)/individual(5)", repeat_obs=2)
#> sex individual
#> 1 1 1
#> 2 1 1
#> 3 1 2
#> 4 1 2
#> 5 1 3
#> 6 1 3
#> 7 1 4
#> 8 1 4
#> 9 1 5
#> 10 1 5
#> 11 2 6
#> 12 2 6
#> 13 2 7
#> 14 2 7
#> 15 2 8
#> 16 2 8
#> 17 2 9
#> 18 2 9
#> 19 2 10
#> 20 2 10
# Naming the sexes in the data_structure
make_structure(structure="sex(2)/individual(5)", repeat_obs=2,
level_names=list(sex=c("female","male")))
#> sex individual
#> 1 female 1
#> 2 female 1
#> 3 female 2
#> 4 female 2
#> 5 female 3
#> 6 female 3
#> 7 female 4
#> 8 female 4
#> 9 female 5
#> 10 female 5
#> 11 male 6
#> 12 male 6
#> 13 male 7
#> 14 male 7
#> 15 male 8
#> 16 male 8
#> 17 male 9
#> 18 male 9
#> 19 male 10
#> 20 male 10
# crossed data structure with 5 individuals in 2 treatments
# and 2 observations per individual and treatment combination
make_structure(structure="treatment(2) + individual(5)", repeat_obs=1)
#> treatment individual
#> 1 1 1
#> 2 1 2
#> 3 1 3
#> 4 1 4
#> 5 1 5
#> 6 2 1
#> 7 2 2
#> 8 2 3
#> 9 2 4
#> 10 2 5