total_variation_depth function

Total Variation Depth and Modified Shape Similarity Index

This function computes the total variation depth (tvd) and the modified shape similarity index (mss) proposed in Huang and Sun (2019) tools:::Rd_expr_doi("10.1080/00401706.2019.1574241") .

total_variation_depth(dts)

Arguments

• dts: A matrix or dataframe of size $n$ observations/curves by $p$ domain/evaluation points.

Returns

Returns a list containing the following - tvd: the total variation depths of the observations of dts

• mss: the modified shape similarity index of the observations of dts

Details

This function computes the total variation depth (TVD) and modified shape similarity (MSS) index of a univariate functional data. The definition of the estimates of TVD and MSS can be found in Huang and Sun (2019) tools:::Rd_expr_doi("10.1080/00401706.2019.1574241") .

Examples

dt6 <- simulation_model6()
tvd_object <- total_variation_depth(dt6$data)

References

Huang, H., & Sun, Y. (2019). A decomposition of total variation depth for understanding functional outliers. Technometrics, 61(4), 445-458.

See Also

tvd_mss for outlier detection using TVD and MSS.

Author(s)

Oluwasegun Ojo