wrMisc (version 1.15.3.1)

combineAsN: Combine Vectors From List And Return Basic Count Statistics

Description

The aim of this function is to choose a fixed number (nCombin) of list-elments from lst and count the number of common values/words. Furthermore, one can define levels to fine-tune the types of combinations to examine. In case multiple combinations for a given level are possible, some basic summary statistics are provided, too.

Usage

combineAsN(
  lst,
  lev = NULL,
  nCombin = 3,
  remDouble = TRUE,
  silent = FALSE,
  debug = FALSE,
  callFrom = NULL
)

Value

This function returns an array with 3 dimensions : i) ii) the combinations of nCombin list-elements, iii) the number of counts (n), sem (standard error of the mean), CI (confidence interval) and sd

Arguments

lst

(list of character or integer vectors) main input

lev

(character) define groups of lst

nCombin

(integer) number of list-elements to combine from lst

remDouble

(logical) remove intra-duplicates (defaults to TRUE)

silent

(logical) suppress messages

debug

(logical) additional messages for debugging

callFrom

(character) allow easier tracking of messages produced

Details

Note of caution : With very long lists and/or high numbers of repeats of given levels, however, the computational effort incerases very much (like it does when using table). Thus, when exploring all different combinations of large data-sets may easily result in queries consuming many ressources (RAM and processing time) ! It is recommended to start testing with test smaller sub-groups.

The main idea of this function is to count frequency of terms when combining different drawings. For example, you ask students from different cities which are their preferred hobbies, they may have different preference depending on the city ( defined by lev). Now, if you want to make groups of 3 students, possibly with one from each city (A ,B and C), you want to count (/estimate) the frequency of different combinations possible. Thus, using this function all combinations of the students from city A with the students from city B and C will be made when counting the number of common hobbies (by nCombin students). Then, all counting results will be summarized to the average count for the various categories (which hobbies were seen once, twice or 3 times...), sem (standard error of the mean) and CI (95

Of course, the number of potential combinations may quickly get very large. Using the argument remDouble=TRUE you can limit the search to either finding all students giving the same answer plus all student giving different answers. In this case, when a given level appears multiple times, all possible combinations using one of the respective entries will be be made with the other levels.

See Also

table, replicateStructure

Examples

## all list-elements are considered equal
tm1 <- list(a1=LETTERS[1:17], a2=LETTERS[3:19], a3=LETTERS[6:20], a4=LETTERS[8:22])
combineAsN(tm1, lev=gl(1,4))[,1,]

## different levels/groups in list-elements
tm4 <- list(a1=LETTERS[1:15], a2=LETTERS[3:16], a3=LETTERS[6:17], a4=LETTERS[8:19],
  b1=LETTERS[5:19], b2=LETTERS[7:20], b3=LETTERS[11:24], b4=LETTERS[13:25], c1=LETTERS[17:26],
  d1=LETTERS[4:12], d2=LETTERS[5:11], d3=LETTERS[6:12], e1=LETTERS[7:10])
te4 <- combineAsN(tm4, nCombin=4, lev=substr(names(tm4),1,1))
str(te4)
te4[,,1]