returns a data.frame with columns c(ids, "statistic") where "statistic" is the value of "variable" where the mode occurs in each group defined by ids.
1 2 | estimate_primary_modes_1d(data, ids, variable, sample_domain = NULL,
min_count = 20, ...)
|
data: A data.frame with columns ids and variable
ids: A vector of strings that are the column names of data that is used to group the data to make multiple comparisons at once. See the Plyr package for details.
variable: A string for a numeric column of data where the primary mode is to be computed.
min_count: The minimum number of rows in group before the primary mode is computed. This helps over-interpreting groups with very few counts
n_pts: The resolution of "variable" in measuring the location of the mode.
sample_domain: The limits of "variable", when computing the primary mode. If it isn't specified then take the whole range of "variable" over all the data.
banddwidth_tolerance: Stop the binary search of kernel density estimation
debug: Print out convergence information in computing the primary mode, and add the column "min_kernel_adjust" to the returned data.frame of the value of the kernel bandwidth for each group.
Extra parameters are passed to the density function.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.