marray | R Documentation |
Creates an m-array for a single- or multistate capture-recapture data with one age class and optionally more than one group.
marray(ch, unobs = 0, freq = 1, groups = NULL)
ch |
an individuals x time matrix with single- or multistate capture histories (0: not captured; 1...X: captured in the 1...X states). See Details. |
unobs |
number of unobserved states (default is 0, needs to be given only in specific cases). |
freq |
a vector with the number of animals with each capture history, or a matrix with a column for each group. If a single value is supplied, it will be used for all rows in the capture history; the default is to assume each row corresponds to a single animal. |
groups |
a factor (or a vector that can be coerced to a factor) which identifies the group that each row of |
The argument ch
can be a matrix of unique capture histories accompanied by a vector or matrix, freq
, specifying the number of animals with each capture history. Trap losses can be indicated either by negative values for freq
, or by filling the row with NA after the last capture. For other formats, see ch2matrix
.
For single-state capture recapture data, an m-array which is a (years-1) x years x groups array, where element [i, j, g] contains the number of individuals in group g released in year i and recaptured in year j+1 (by definition no recaptures can occur in year 1). If no groups are specified, this will be a (years-1) x years matrix. The last column contains the number of individuals released in year i and never recaptured.
For multi-state capture-recapture data with s states (including potential unobservable states), an m-array which is a (years-1)*s x (years-1)*2 + 1 x groups array. An element [i, j, g] contains the number of individuals in group g released in year t and state n (i = (t-1)*s + n) and recaptured in year k+1 in state m (j = (k-1)*s + m). If no groups are specified, this will be a matrix. The last column contains the number of individuals released in year t and state s and never recaptured. The labeling of unobserved states starts with the number of observed states + 1.
Michael Schaub
Schaub, M., Kéry, M. (2022) Integrated Population Models, Academic Press, section 4.5.1.2.
# Convert a single state capture history matrix into an m-array
data(woodchat5)
dim(woodchat5$ch) # 1902 animals x 20 years
ch1 <- cleanCH(woodchat5$ch[, 11:20]) # Use last 10 years only
marray(ch1)
# Convert a multistate capture history into an m-array
data(cormorant)
dim(cormorant$ms.ch) # 12,659 animals x 14 years
ch2 <- cleanCH(cormorant$ms.ch[, 11:14]) # Use last 4 years only
table(ch2) # 6 states
marray(ch2)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.