blocksums: Block Sums

In accelerometry: Functions for Processing Accelerometer Data

Description

Calculates block sums (i.e. moving sums but for non-overlapping intervals) or maximum block sum. For optimal speed, use integer = TRUE if x is an integer vector and integer = FALSE otherwise. If length(x) is not an exact multiple of window, the last partial segment is dropped.

Usage

blocksums(x, window, integer = FALSE, max = FALSE)

Arguments

x	Integer or numeric vector.
window	Integer value specifying window length.
integer	Logical value for whether x is an integer vector.
max	Logical value for whether to return maximum moving average (as opposed to vector of moving averages).

Value

Numeric value or vector depending on max.

Examples

# Load accelerometer data for first 5 participants in NHANES 2003-2004
data(unidata)

# Get data from ID number 21005, Saturday only
counts.sat <- unidata[unidata[, "seqn"] == 21005 & unidata[, "paxday"] == 7, 
                      "paxinten"]
                      
# Calculate and plot hourly count sums
hourly.sums <- blocksums(x = counts.sat, window = 60, integer = TRUE)
plot(hourly.sums)

accelerometry documentation built on May 2, 2019, 1:07 p.m.