LongData-class {longitudinalData} | R Documentation |
~ Class: LongData ~
Description
LongData
is an objet containing the longitudinal
data (the individual trajectories) and some associate value (like time, individual
identifiant,...). It can be used either for a single
variable-trajectory or for joint variable-trajectories.
Objects from the Class
Object LongData
for single variable-trajectory can be created using
the fonction longData
on a data.frame
or on a matrix
.
LongData
for joint trajectories can be created by calling
the fonction longData3d
on a data.frame
or on an array
.
Slots
idAll
[vector(character)]
: Single identifier for each of the longData (each individual). Usefull to export clusters.idFewNA
[vector(character)]
: Restriction ofidAll
to the trajectories that does not have 'too many' missing value. SeemaxNA
for 'too many' definition.time
[numeric]
: Time at which measures are made.varNames
[character]
: Name of the variable measured.traj
[matrix(numeric)]
: Contains the longitudianl data. Each lines is the trajectories of an individual. Each column is the time at which measures are made.dimTraj
[vector3(numeric)]
: size of the matrixtraj
(iedimTraj=c(length(idFewNA),length(time))
).maxNA
[numeric]
or[vector(numeric)]
: Individual whose trajectories contain 'too many' missing value are exclude fromtraj
and will no be use in the analysis. Their identifier is preserved inidAll
but not inidFewNA
. 'too many' is define bymaxNA
: a trajectory with more missing thanmaxNA
is exclude.reverse
[matrix(numeric)]
: if the trajectories are scale using the functionscale
, the 'scaling parameters' (probably mean and standard deviation) are saved inreverse
. This is usefull to restore the original data after a scaling operation.
Construction
Object LongData
for single variable-trajectory can be created by calling
the fonction longData
on a data.frame
or on a matrix
.
LongData
for joint trajectories can be created by calling
the fonction longData3d
on a data.frame
or on an array
.
Get [
- Object["idAll"]
[vecteur(character)]: Gets the full list of individual identifiant (the value of the slot
idAll
)- Object["idFewNA"]
[vecteur(character)]: Gets the list of individual identifiant with not too many missing values (the value of the slot
idFewNA
)- Object["varNames"]
[character]: Gets the name(s) of the variable (the value of the slot
varNames
)- Object["time"]
[vecteur(numeric)]: Gets the times (the value of the slot
time
)- Object["traj"]
[array(numeric)]: Gets all the longData' values (the value of the slot
traj
)- Object["dimTraj"]
[vector3(numeric)]: Gets the dimension of
traj
.- Object["nbIdFewNA"]
[numeric]: Gets the first dimension of
traj
(ie the number of individual include in the analysis).- Object["nbTime"]
[numeric]: Gets the second dimension of
traj
(ie the number of time measurement).- Object["nbVar"]
[numeric]: Gets the third dimension of
traj
(ie the number of variables).- Object["maxNA"]
[vecteur(numeric)]: Gets maxNA.
- Object["reverse"]
[matrix(numeric)]: Gets the matrix of the scaling parameters.
Methods
scale
scale the trajectories. Usefull to normalize variable trajectories measured with different units.
restoreRealData
restore original data that have been modified after a scaling operation.
longDataFrom3d
Extract a variable trajectory form a dataset of joint trajectories.
plotTrajMeans
plot all the variables of the
LongData
, optionnaly according to aPartition
.plotTrajMeans3d
plot two variables of the
LongData
in 3 dimensions, optionnaly according to aPartition
.plot3dPdf
create 'Triangle objects' representing in 3D the cluster's center according to a
Partition
. 'Triangle object' can latter be include in a LaTeX file to get a dynamique (rotationg) pdf figure.imputation
Impute the missing values of the trajectories.
qualityCriterion
Compute some quality criterion that can be use to compare the quality of differents
Partition
.
Author
Christophe Genolini
1. UMR U1027, INSERM, Université Paul Sabatier / Toulouse III / France
2. CeRSME, EA 2931, UFR STAPS, Université de Paris Ouest-Nanterre-La Défense / Nanterre / France
References
[1] C. Genolini and B. Falissard
"KmL: k-means for longitudinal data"
Computational Statistics, vol 25(2), pp 317-328, 2010
[2] C. Genolini and B. Falissard
"KmL: A package to cluster longitudinal data"
Computer Methods and Programs in Biomedicine, 104, pp e112-121, 2011
See Also
Overview: longitudinalData-package
Methods: longData
, longData3d
, imputation
, qualityCriterion
Plot: plotTrajMeans
,
plotTrajMeans3d
, plot3dPdf
Examples
#################
### building trajectory (longData)
mat <- matrix(c(NA,2,3,4,1,6,2,5,1,3,8,10),4)
ld <- longData(mat,idAll=c("I1","I2","I3","I4"),time=c(2,4,8),varNames="Age")
### '[' and '[<-'
ld["idAll"]
ld["idFewNA"]
ld["varNames"]
ld["traj"]
(ld)
### Plot
plotTrajMeans(ld,parMean=parMEAN(type="n"))