Evaluate if sample data for a categorical variable is consistent with a hypothesized distribution

Evaluate if sample data for a categorical variable is consistent with a hypothesized distribution

goodness(
  dataset,
  var,
  p = NULL,
  tab = NULL,
  data_filter = "",
  envir = parent.frame()
)

Arguments

dataset	Dataset
var	A categorical variable
p	Hypothesized distribution as a number, fraction, or numeric vector. If unspecified, defaults to an even distribution
tab	Table with frequencies as alternative to dataset
data_filter	Expression entered in, e.g., Data > View to filter the dataset in Radiant. The expression should be a string (e.g., "price > 10000")
envir	Environment to extract data from

Value

A list of all variables used in goodness as an object of class goodness

Details

See https://radiant-rstats.github.io/docs/basics/goodness.html for an example in Radiant

See also

summary.goodness to summarize results

plot.goodness to plot results

Examples

goodness(newspaper, "Income") %>% str()
#> List of 8
#>  $ elow       : int 0
#>  $ res        : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
#>   ..$ statistic: Named num 32.8
#>   .. ..- attr(*, "names")= chr "X-squared"
#>   ..$ p.value  : num 1e-08
#>   ..$ parameter: int 1
#>   ..$ method   : chr "Chi-squared test for given probabilities"
#>  $ cst        :List of 10
#>   ..$ statistic: Named num 32.8
#>   .. ..- attr(*, "names")= chr "X-squared"
#>   ..$ parameter: Named num 1
#>   .. ..- attr(*, "names")= chr "df"
#>   ..$ p.value  : num 1e-08
#>   ..$ method   : chr "Chi-squared test for given probabilities"
#>   ..$ data.name: chr "tab"
#>   ..$ observed : 'table' num [1:2(1d)] 359 221
#>   .. ..- attr(*, "dimnames")=List of 1
#>   .. .. ..$ : chr [1:2] "Low Income" "High Income"
#>   ..$ expected : Named num [1:2] 290 290
#>   .. ..- attr(*, "names")= chr [1:2] "Low Income" "High Income"
#>   ..$ residuals: 'table' num [1:2(1d)] 4.05 -4.05
#>   .. ..- attr(*, "dimnames")=List of 1
#>   .. .. ..$ : chr [1:2] "Low Income" "High Income"
#>   ..$ stdres   : 'table' num [1:2(1d)] 5.73 -5.73
#>   .. ..- attr(*, "dimnames")=List of 1
#>   .. .. ..$ : chr [1:2] "Low Income" "High Income"
#>   ..$ chi_sq   : 'table' num [1:2(1d)] 16.4 16.4
#>   .. ..- attr(*, "dimnames")=List of 1
#>   .. .. ..$ : chr [1:2] "Low Income" "High Income"
#>   ..- attr(*, "class")= chr "htest"
#>  $ df_name    : chr "newspaper"
#>  $ var        : chr "Income"
#>  $ p          : num [1:2] 0.5 0.5
#>  $ tab        : 'table' num [1:2(1d)] 359 221
#>   ..- attr(*, "dimnames")=List of 1
#>   .. ..$ : chr [1:2] "Low Income" "High Income"
#>  $ data_filter: chr ""
#>  - attr(*, "class")= chr [1:2] "goodness" "list"
goodness(newspaper, "Income", p = c(3/4, 1/4)) %>% str()
#> List of 8
#>  $ elow       : int 0
#>  $ res        : tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
#>   ..$ statistic: Named num 53.1
#>   .. ..- attr(*, "names")= chr "X-squared"
#>   ..$ p.value  : num 3.15e-13
#>   ..$ parameter: int 1
#>   ..$ method   : chr "Chi-squared test for given probabilities"
#>  $ cst        :List of 10
#>   ..$ statistic: Named num 53.1
#>   .. ..- attr(*, "names")= chr "X-squared"
#>   ..$ parameter: Named num 1
#>   .. ..- attr(*, "names")= chr "df"
#>   ..$ p.value  : num 3.15e-13
#>   ..$ method   : chr "Chi-squared test for given probabilities"
#>   ..$ data.name: chr "tab"
#>   ..$ observed : 'table' num [1:2(1d)] 359 221
#>   .. ..- attr(*, "dimnames")=List of 1
#>   .. .. ..$ : chr [1:2] "Low Income" "High Income"
#>   ..$ expected : Named num [1:2] 435 145
#>   .. ..- attr(*, "names")= chr [1:2] "Low Income" "High Income"
#>   ..$ residuals: 'table' num [1:2(1d)] -3.64 6.31
#>   .. ..- attr(*, "dimnames")=List of 1
#>   .. .. ..$ : chr [1:2] "Low Income" "High Income"
#>   ..$ stdres   : 'table' num [1:2(1d)] -7.29 7.29
#>   .. ..- attr(*, "dimnames")=List of 1
#>   .. .. ..$ : chr [1:2] "Low Income" "High Income"
#>   ..$ chi_sq   : 'table' num [1:2(1d)] 13.3 39.8
#>   .. ..- attr(*, "dimnames")=List of 1
#>   .. .. ..$ : chr [1:2] "Low Income" "High Income"
#>   ..- attr(*, "class")= chr "htest"
#>  $ df_name    : chr "newspaper"
#>  $ var        : chr "Income"
#>  $ p          : num [1:2] 0.75 0.25
#>  $ tab        : 'table' num [1:2(1d)] 359 221
#>   ..- attr(*, "dimnames")=List of 1
#>   .. ..$ : chr [1:2] "Low Income" "High Income"
#>  $ data_filter: chr ""
#>  - attr(*, "class")= chr [1:2] "goodness" "list"
table(select(newspaper, Income)) %>% goodness(tab = .)
#> $elow
#> [1] 0
#> 
#> $res
#> # A tibble: 1 x 4
#>   statistic      p.value parameter method                                  
#>       <dbl>        <dbl>     <int> <chr>                                   
#> 1      32.8 0.0000000100         1 Chi-squared test for given probabilities
#> 
#> $cst
#> 
#> 	Chi-squared test for given probabilities
#> 
#> data:  tab
#> X-squared = 32.834, df = 1, p-value = 1.003e-08
#> 
#> 
#> $df_name
#> [1] "."
#> 
#> $var
#> [1] "variable"
#> 
#> $p
#> [1] 0.5 0.5
#> 
#> $tab
#> 
#>  Low Income High Income 
#>         359         221 
#> 
#> $data_filter
#> [1] ""
#> 
#> attr(,"class")
#> [1] "goodness" "list"