I hope Report package can suppport for results of rstatix

[ChenSD]

Describe the solution you'd like The design concept of Report is exciting. But I think rstatix do ANOVA better than aov or lmerTest packages. I tried using Report for rstatix results and found Report did not support it.

How could we do it? I hope Report package can suppport for results of rstatix. Maybe we can add the anova method or the package name as an additional input parameter. For example, report(result, aov ) or report(result, rstatix).

[DominiqueMakowski]

Hi, that makes sense. Essentially in order to support any package by report, its support must first be implemented in insight and parameters, if that's the case (it should be, as @strengejacke will soon be done with R and will start implementing support for packages of the future 😅) ,then it could be quite straightforward. Would you have one reproducible example of a rstatix model as well as the rough output that you think would be good?

[IndrajeetPatil]

I am not sure if it's going to be as straightforward, or even worth it. We have methods to extract effect sizes for htest objects and so it's easy to include all details. This is not going to be the case with rstatix.

library(rstatix)
library(report)

ToothGrowth %>% t.test(len ~ supp, .) %>% report_statistics()
#> difference = -3.70, 95% CI [-0.17, 7.57], t(55.31) = 1.92, p = 0.061; Cohen's d = 0.52, 95% CI [-0.02, 1.05]

ToothGrowth %>% t_test(len ~ supp) %>% report_statistics()
#> Error in names(n_char) <- c("Entry", "n_Entry"): 'names' attribute [2] must be the same length as the vector [1]

^{Created on 2021-03-18 by the reprex package (v1.0.0)}

[genghiskhanofnz]

The report() does describe the result of rstatix::get_summary_stats(). repex pasted at the bottom.

Totally agree with the ANOVA from rstatix is brilliant. Would really appreciate if you could show us the desired output from supporting rstatix::anova_test().

library(rstatix)
#> 
#> Attaching package: 'rstatix'
#> The following object is masked from 'package:stats':
#> 
#>     filter

library(flextable)

library(dplyr)
#> 
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag
#> The following objects are masked from 'package:base':
#> 
#>     intersect, setdiff, setequal, union

iris %>% 
  get_summary_stats() %>% 
  report::report()
#> The data contains 4 observations of the following 13 variables:
#> 
#>   - variable: 4 levels, namely Sepal.Length (n = 1, 25.00%), Sepal.Width (n = 1,
#> 25.00%), Petal.Length (n = 1, 25.00%) and Petal.Width (n = 1, 25.00%)
#>   - n: n = 4, Mean = 150.00, SD = 0.00, Median = 150.00, MAD = 0.00, range: [150,
#> 150], Skewness = , Kurtosis = , 0 missing
#>   - min: n = 4, Mean = 1.85, SD = 1.81, Median = 1.50, MAD = 1.41, range: [0.10,
#> 4.30], Skewness = 0.98, Kurtosis = 0.82, 0 missing
#>   - max: n = 4, Mean = 5.43, SD = 2.44, Median = 5.65, MAD = 2.59, range: [2.50,
#> 7.90], Skewness = -0.35, Kurtosis = -2.60, 0 missing
#>   - median: n = 4, Mean = 3.61, SD = 1.92, Median = 3.67, MAD = 2.08, range:
#> [1.30, 5.80], Skewness = -0.16, Kurtosis = -0.74, 0 missing
#>   - q1: n = 4, Mean = 2.45, SD = 2.04, Median = 2.20, MAD = 1.85, range: [0.30,
#> 5.10], Skewness = 0.64, Kurtosis = 0.20, 0 missing
#>   - q3: n = 4, Mean = 4.15, SD = 2.02, Median = 4.20, MAD = 2.30, range: [1.80,
#> 6.40], Skewness = -0.11, Kurtosis = -1.94, 0 missing
#>   - iqr: n = 4, Mean = 1.70, SD = 1.28, Median = 1.40, MAD = 0.74, range: [0.50,
#> 3.50], Skewness = 1.30, Kurtosis = 2.37, 0 missing
#>   - mad: n = 4, Mean = 1.09, SD = 0.58, Median = 1.04, MAD = 0.44, range: [0.44,
#> 1.85], Skewness = 0.57, Kurtosis = 1.68, 0 missing
#>   - mean: n = 4, Mean = 3.46, SD = 1.92, Median = 3.41, MAD = 1.90, range: [1.20,
#> 5.84], Skewness = 0.17, Kurtosis = 0.87, 0 missing
#>   - sd: n = 4, Mean = 0.95, SD = 0.57, Median = 0.79, MAD = 0.29, range: [0.44,
#> 1.76], Skewness = 1.44, Kurtosis = 2.67, 0 missing
#>   - se: n = 4, Mean = 0.08, SD = 0.05, Median = 0.06, MAD = 0.02, range: [0.04,
#> 0.14], Skewness = 1.45, Kurtosis = 2.66, 0 missing
#>   - ci: n = 4, Mean = 0.15, SD = 0.09, Median = 0.13, MAD = 0.05, range: [0.07,
#> 0.28], Skewness = 1.44, Kurtosis = 2.65, 0 missing

^{Created on 2023-08-13 with reprex v2.0.2}