The Mode function computes the mode of the specified random variable or computes the kernel or sample mode for a data set.

The first parameter can be a data set (represented as an Array or a Matrix data set), a distribution (see Statistics[Distribution]), a random variable, or an algebraic expression involving random variables (see Statistics[RandomVariable]).

By default, all computations involving random variables are performed symbolically (see option numeric below).

All computations involving data are performed in floating-point; therefore, all data provided must have type/realcons and all returned solutions are floating-point, even if the problem is specified with exact values.

For more information about computation in the Statistics package, see the Statistics[Computation] help page.

The ds_options argument can contain one or more of the options shown below. More information for some options is available in the Statistics[DescriptiveStatistics] help page.

ignore=truefalse -- This option controls how missing data is handled by the Mode command. Missing items are represented by undefined or Float(undefined). So, if ignore=false and A contains missing data, the Mode command will return undefined. If ignore=true all missing items in A will be ignored. The default value is false.

weights=rtable -- Vector of weights (one-dimensional rtable). If weights are given, the Mode function will scale each data point to have given weight. Note that the weights provided must have type/realcons and the results are floating-point, even if the problem is specified with exact values. Both the data array and the weights array must have the same number of elements.

type=sample or kernel -- The type options indicates what mode type should be calculated on the data set (by default this is set to 'sample').  If 'sample' is set, the sample mode (defined as the most frequent data item in the set) will be calculated.  If 'kernel' is set, the kernel mode (defined as the mode of a kernel density estimate based upon the data set) will be calculated.

kernel=gaussian, biweight, epanechnikov, triangular or rectangular -- If type='kernel' then this option specifies the type of kernel used in the kernel density estimate (by default this is 'gaussian'.  This parameter is ignored otherwise.

bandwidth=realcons -- If type='kernel' then this options specifies the bandwidth of the kernel density estimate (by default this is 1/4).  This parameter is ignored otherwise.

bins=posint -- If type='kernel' and result='discrete' then this option represents the number of bins used in the operation of calculating a discrete kernel density estimate (by default this is 512).  This parameter is ignored otherwise.

left=realcons -- If type='kernel' then this option represents the lower (left) bound on elements of the data sample used in calculating the kernel density estimate.  This parameter is ignored otherwise.

right=realcons -- If type='kernel' then this option represents the upper (right) bound on elements of the data sample used in calculating the kernel density estimate.  This parameter is ignored otherwise.

method=discrete or exact -- If type='kernel' then this parameter specifies the output method for the kernel density estimate (by default this is 'discrete').  This parameter is ignored otherwise.

The rv_options argument can contain one or more of the options shown below. More information for some options is available in the Statistics[RandomVariables] help page.

numeric=truefalse -- By default, the mode is computed using exact arithmetic. To compute the mode numerically, specify the numeric or numeric = true option.

This function is only guaranteed to return one potential mode - in cases where multiple modes exist, the first detected mode will be returned.

Note that discrete kernel density estimation removes results that do not fall within the generated range, including missing data.  Hence, if you do not specify result='exact' option, missing data will be automatically ignored.

The A parameter was updated in Maple 16.

Stuart, Alan, and Ord, Keith. Kendall's Advanced Theory of Statistics. 6th ed. London: Edward Arnold, 1998. Vol. 1: Distribution Theory.