Package {GarrettRank}

Type: Package
Title: Garrett Ranking Analysis and Visualization
Version: 0.1.5
Description: Performs Garrett ranking analysis of respondent-ranked items such as constraints, problems, factors, or priorities. The package converts respondent rankings into Garrett scores, calculates mean Garrett scores and final ranks and provides methods for summarizing,tabulating and visualizing ranking results. It also provides Kendall's coefficient of concordance for assessing the degree of agreement among respondents. Garrett ranking does not accommodate tied ranks and Kendall's coefficient of concordance is likewise computed for untied ranking data.For more details see Garrett and Woodworth (1969) https://books.google.com/books?id=aoqSmQEACAAJ and Buragohain and Dubey (2021) <doi:10.5958/2454-552X.2021.00055.4>.
License: GPL-3
Encoding: UTF-8
RoxygenNote: 7.3.2
Imports: ggplot2, pheatmap, rlang
Suggests: readxl, testthat (≥ 3.0.0)
Config/testthat/edition: 3
Depends: R (≥ 3.5)
LazyData: true
NeedsCompilation: no
Packaged: 2026-09-26 03:11:27 UTC; bejoy
Author: Blesson B. Varghese [aut, cre], Adarsh V S [aut], Bhavana Sajeev [aut], Azhanuo Rutsa [aut], Joe Shiney M A [aut]
Maintainer: Blesson B. Varghese <blessonvarghese1234@gmail.com>
Repository: CRAN
Date/Publication: 2026-10-06 16:40:08 UTC

Validate Garrett Ranking Data

Description

Validates respondent ranking data before Garrett ranking analysis. The function checks the input data structure, ranking values, and completeness of ranks for each respondent. Supported input formats include data frames, matrices, CSV files, and Excel files.

Usage

.validate_ranking_data(data, respondent = NULL)

Arguments

data

A data.frame, matrix, CSV file path, or Excel file path containing respondent ranking data. Each row represents a respondent and each column represents a factor or item being ranked.

respondent

Optional respondent ID column name or column position to exclude from the ranking data before validation.

Value

A validated data frame containing the ranking data after checking that the data have valid dimensions, numeric integer ranks, and that each respondent assigns every rank exactly once.

#Example Dataset for Garrett Ranking

Description

#Example Dataset for Garrett Ranking

Usage

garrett_example

Format

A data frame with 50 rows and 23 columns:

Respondent

The name or serial number identifying each respondent.

C1

Rank assigned to constraint 1.

C2

Rank assigned to constraint 2.

C3

Rank assigned to constraint 3.

C4

Rank assigned to constraint 4.

C5

Rank assigned to constraint 5.

C6

Rank assigned to constraint 6.

C7

Rank assigned to constraint 7.

C8

Rank assigned to constraint 8.

C9

Rank assigned to constraint 9.

C10

Rank assigned to constraint 10.

C11

Rank assigned to constraint 11.

C12

Rank assigned to constraint 12.

C13

Rank assigned to constraint 13.

C14

Rank assigned to constraint 14.

C15

Rank assigned to constraint 15.

C16

Rank assigned to constraint 16.

C17

Rank assigned to constraint 17.

C18

Rank assigned to constraint 18.

C19

Rank assigned to constraint 19.

C20

Rank assigned to constraint 20.

C21

Rank assigned to constraint 21.

C22

Rank assigned to constraint 22.

Details

The first column contains the respondent's name or serial number. The remaining 22 columns (C1 to C22) contain the ranks assigned by each respondent to the corresponding constraints. There are 50 respondents in the dataset. No tied ranks are present in the dataset.

An example dataset demonstrating the application of the Garrett ranking method.

The dataset contains ranking responses from 50 respondents for 22 constraints.

Examples

data(garrett_example)
#Run Garrett ranking analysis
result <- garrett_rank(garrett_example,respondent = "Respondent")
summary(result)
result$ranking
result$frequency
result$weighted_scores
#Select the plot type
plot(result, type = "bar")
plot(result, type = "lollipop")
plot(result, type = "dot")
plot(result, type = "line")
plot(result, type = "heatmap")
plot(result, type = "cluster")
plot(result,type="contribution")
plot(result, type = "cluster", k = 3)
plot(result,type = "cluster",scale = "row",show_numbers = TRUE)

#Run Kendall's Coefficient of Concordance
kw<-kendall_w(garrett_example,respondent = "Respondent")
summary(kw)

Garrett Ranking Analysis

Description

Performs Garrett ranking analysis on respondent ranking data.

Usage

garrett_rank(data, respondent = NULL)

Arguments

data

A data.frame, matrix, CSV file path or Excel file path containing ranking data.

respondent

Optional respondent ID column name or column position to exclude before analysis.

Details

Each row must represent one respondent and each column one factor, constraint, or item. Each respondent must assign every rank from 1 to the number of factors exactly once.

Value

An object of class "garrett", which is a list containing:

ranking

A data.frame containing the factor names, mean Garrett scores, and final ranks. Mean_Score is the average Garrett score for each factor across all respondents. Higher mean Garrett scores indicate higher overall priority, and Rank = 1 represents the highest-ranked factor.

frequency

A data.frame containing the number of respondents assigning each possible rank to each factor, together with the corresponding percent positions and Garrett scores.

weighted_scores

A numeric matrix containing the rank frequencies multiplied by their corresponding Garrett scores. These values are used to calculate the mean Garrett score for each factor.

reference

A data.frame containing the standard Garrett conversion table used to convert percent positions into Garrett scores.

respondents

An integer giving the number of respondents included in the analysis.

factors

An integer giving the number of factors ranked by the respondents.

factor_names

A character vector containing the names of the ranked factors.

call

The matched function call used to create the object.

Examples


result <- garrett_rank(garrett_example,respondent = "Respondent")
summary(result)
result$ranking
result$frequency
result$weighted_scores

Garrett Conversion Table It is a standard Garrett conversion table used by the package.

Description

Garrett Conversion Table It is a standard Garrett conversion table used by the package.

Usage

garrett_table()

Value

A data.frame with two columns:

Percent_Position

The percent position values used to determine Garrett scores from respondent ranks.

Garrett_Score

The corresponding Garrett scores assigned to the percent positions.

Examples


table<-garrett_table()
print(table)

Kendall's Coefficient of Concordance

Description

Computes Kendall's coefficient of concordance (W) for complete, untied ranking data.

Usage

kendall_w(data, respondent = NULL)

Arguments

data

A data.frame, matrix, CSV file path, or Excel file path containing ranking data.

respondent

Optional respondent ID column name or column position to exclude before analysis.

Details

Each row must represent one respondent and each column one factor. Each respondent must assign every rank from 1 to the number of factors exactly once. Tied ranks are not supported.

Value

An object of class "kendall_w", which is a list containing:

statistic

Kendall's coefficient of concordance (W), ranging from 0 to 1, where larger values indicate stronger agreement among respondents.

chisq

The chi-square statistic used to test the statistical significance of the concordance.

df

Degrees of freedom for the chi-square test.

p.value

The p-value associated with the chi-square test.

respondents

The number of respondents included in the analysis.

factors

The number of ranked factors.

rank_sum

A named numeric vector containing the sum of ranks assigned to each factor across respondents.

call

The matched function call.

Examples


data(garrett_example)
kw <- kendall_w(garrett_example,respondent = "Respondent")
kw
summary(kw)

Plot Garrett Ranking Results

Description

Produces graphical representations of Garrett ranking results.

Usage

## S3 method for class 'garrett'
plot(
  x,
  type = c("bar", "lollipop", "dot", "line", "heatmap", "cluster", "contribution"),
  top = NULL,
  color = "#2C7FB8",
  label = TRUE,
  point_size = 3,
  line_size = 1,
  cluster_rows = TRUE,
  cluster_cols = FALSE,
  distance = "euclidean",
  clustering_method = "complete",
  scale = "none",
  show_numbers = FALSE,
  ...
)

Arguments

x

An object of class "garrett" created by garrett_rank.

type

Type of plot. Options are "bar", "lollipop", "dot", "line", "heatmap", "cluster", and "contribution".

top

Number of top-ranked factors to display. Default is NULL, which displays all factors. Applies to ranking plots.

color

Colour used for ranking plots.

label

Logical. Should Garrett scores be displayed as labels?

point_size

Size of points used in dot, lollipop, and line plots.

line_size

Width of lines used in lollipop and line plots.

cluster_rows

Logical. Should factors be hierarchically clustered in cluster plots?

cluster_cols

Logical. Should ranks be hierarchically clustered?

distance

Distance measure used for hierarchical clustering.

clustering_method

Method used for hierarchical clustering.

scale

Should heatmap data be scaled by rows, columns, or not scaled? Options are "none", "row", or "column".

show_numbers

Logical. Should matrix values be displayed inside heatmap cells?

...

Additional arguments passed to pheatmap::pheatmap.

Value

For "bar", "lollipop", "dot", and "line" plots, a ggplot object. For "heatmap", "cluster", and "contribution" plots, a pheatmap object returned invisibly. The returned object contains the graphical representation of the Garrett ranking results.

Examples


data(garrett_example)
result <- garrett_rank(garrett_example,respondent = "Respondent")
#Select the plot type
plot(result, type = "bar")
plot(result, type = "lollipop")
plot(result, type = "dot")
plot(result, type = "line")
plot(result, type = "heatmap")
plot(result, type = "cluster")
plot(result,type="contribution")
plot(result, type = "cluster", k = 3)
plot(result,type = "cluster",scale = "row",show_numbers = TRUE)