make_complete function

Completion of partial rankings/orderings

Return complete rankings/orderings from partial sequences relying on a random generation of the missing positions/items.

make_complete(data, format_input, nranked = NULL, probitems = rep(1,
  ncol(data)))

Arguments

• data: Numeric N$$x$$K data matrix of partial sequences to be completed.
• format_input: Character string indicating the format of the data input, namely "ordering" or "ranking".
• nranked: Optional numeric vector of length $N$ with the number of items ranked by each sample unit.
• probitems: Numeric vector with the $K$ item-specific probabilities to be employed for the random generation of the missing positions/items (see 'Details'). Default is equal probabilities.

Returns

A list of two named objects:

• completedata: Numeric N$$x$$K data matrix of complete sequences with the same format of the input data.

• nranked: Numeric vector of length $N$ with the number of items ranked by each sample unit of the input data.

Details

The completion of the partial top rankings/orderings is performed according to the Plackett-Luce scheme, that is, with a sampling without replacement of the not-ranked items by using the positive values in the probitems argument as support parameters (normalization is not necessary).

Examples

## Completion based on the top item frequencies
data(d_dublinwest)
head(d_dublinwest)
top_item_freq <- rank_summaries(data=d_dublinwest, format_input="ordering", mean_rank=FALSE, 
                                pc=FALSE)$marginals["Rank_1",]

d_dublinwest_compl <- make_complete(data=d_dublinwest, format_input="ordering", 
                                    probitems=top_item_freq)
head(d_dublinwest_compl$completedata)

Author(s)

Cristina Mollica and Luca Tardella