knitr::opts_chunk$set(echo = TRUE) library(SteppedPower)
In general, a study design is referred to as incomplete if not all clusters are observed at every time period [@hemming2015stepped].
Suppose you do not plan to observe all clusters over the whole study period. Rather, clusters that switch early to the intervention are not observed until the end. Analogous, observation starts later in clusters that switch towards the end of the study.
SteppedPower
There are essentially three ways to define cluster periods without observation.
incomplete
argument.
Input can be either a scalar or a matrix of dimension clusters$\cdot$timepoints
or sequences$\cdot$timepoints:1
s for cluster cells that are observed and 0
or NA
s for
cluster cells that are not observed.NA
s into an explicitly defined treatment matrix, easiest done with the argument trtmatrix=
.NA
s into the vector for delayed treatment start trtDelay=
.glsPower()
calls the function construct_DesMat()
to construct
the design matrix with the relevant arguments.
All the above options can be used in the main wrapper function, but
the examples below focus on construct_DesMat()
directly.
SteppedPower
stores information about (un)observed cluster cells separately from the treatment allocation. This is done for more consistency in the code as the indices in the covariance and design matrices is
If for example the a stepped wedge study consists of eight clusters in four sequences (i.e. five timepoints), and we observe two timepoints before and after the switch, then we receive
Dsn1.1 <- construct_DesMat(Cl=rep(2,4), incomplete=2)
A slightly more tedious, but more flexible way is to define a matrix
where each row corresponds to either a cluster or a wave of clusters
and each column corresponds to a timepoint.
If a cluster is not observed at a specific timepoint,
set the value in the corresponding cell to 0
.
For the example above, such a matrix would look like this:
TM <- toeplitz(c(1,1,0,0)) incompleteMat1 <- cbind(TM[,1:2],rep(1,4),TM[,3:4]) incompleteMat2 <- incompleteMat1[rep(1:4,each=2),]
A matrix where each row represents a wave of clusters
suppressWarnings(knitr::kable(incompleteMat1))
or each row represents a cluster
suppressWarnings(knitr::kable(incompleteMat2))
Now all that's left to do is to plug that into the function and we receive the same design matrix
Dsn1.2 <- construct_DesMat(Cl=rep(2,4), incomplete=incompleteMat1) Dsn1.3 <- construct_DesMat(Cl=rep(2,4), incomplete=incompleteMat2) all.equal(Dsn1.1,Dsn1.2) all.equal(Dsn1.1,Dsn1.3)
The argument
incomplete
with matrix input works also for other design types, but makes (supposedly) most sense in the context of stepped wedge designs
Now suppose we want to use a SWD to investigate the intervention effects after at least one month,
i.e. cluster periods directly after the switch to intervention conditions are not observed.
That leads to an incomplete design that is easiest modelled with trtDelay=
Dsn2 <- construct_DesMat(Cl=rep(2,4), trtDelay = c(NA) ) Dsn2
The above arguments can also be combined, e.g.
Dsn3 <- construct_DesMat(Cl=rep(2,4), incomplete=2, trtDelay=c(NA) ) Dsn3
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.