format.timestamps: Checking for Regularity

In bsts: Bayesian Structural Time Series

Checking for Regularity

Description

Tools for checking if a series of timestamps is 'regular' meaning that it has no duplicates, and no gaps. Checking for regularity can be tricky. For example, if you have monthly observations with Date or POSIXt timestamps then gaps between timestamps can be 28, 29, 30, or 31 days, but the series is still "regular".

Usage

  NoDuplicates(timestamps)
  NoGaps(timestamps)
  IsRegular(timestamps)

  HasDuplicateTimestamps(bsts.object)

Arguments

timestamps	A set of (possibly irregular or non-unique) timestamps. This could be a set of integers (like 1, 2, , 3...), a set of numeric like (1945, 1945.083, 1945.167, ...) indicating years and fractions of years, a Date object, or a POSIXt object.
bsts.object	A bsts model object.

Value

All four functions return scalar logical values. NoDuplicates returns TRUE if all elements of timestamps are unique.

NoGaps examines the smallest nonzero gap between time points. As long as no gaps between time points are more than twice as wide as the smallest gap, it returns TRUE, indicating that there are no missing timestamps. Otherwise it returns FALSE.

IsRegular returns TRUE if NoDuplicates and NoGaps both return TRUE.

HasDuplicateTimestamps returns FALSE if the data used to fit bsts.model either has NULL timestamps, or if the timestamps contain no duplicate values.

Author(s)

Steven L. Scott [e-mail]

Examples

  first <- as.POSIXct("2015-04-19 08:00:04")
  monthly <- seq(from = first, length.out = 24, by = "month")
  IsRegular(monthly) ## TRUE

  skip.one <- monthly[-8]
  IsRegular(skip.one) ## FALSE

  has.duplicates <- monthly
  has.duplicates[1] <- has.duplicates[2]
  IsRegular(has.duplicates) ## FALSE

bsts documentation built on May 29, 2024, 2:14 a.m.