Load example data and packages
data("example_sml")Example: Diagnostic 3 for a time-varying exposure without censoring
PRELIMINARY STEP: MAKE EXPOSURE HISTORY
Remove history for illustration. Note that the input data is already in wide format.
drops <- c("h_0", "h_1", "h_2")
mydata <- example_sml[ , !(names(example_sml) %in% drops)]
mydata.history <- makehistory.one(input=mydata,
id="id",
exposure="a",
name.history="h",
times=c(0,1,2))STEP 1: RESTRUCTURE THE DATA
mydata.tidy <- lengthen(
input=example_sml, #mydata.history,
id="id",
diagnostic=3,
censoring="no",
times.exposure=c(0,1,2),
times.covariate=c(0,1,2),
exposure="a",
temporal.covariate=c("l","m","o"),
static.covariate=c("n","p"),
history="h",
weight.exposure="wax"
)Example of how to remove relative covariate history
mydata.tidy.omit <- omit.history(
input=mydata.tidy,
omission="relative",
covariate.name=c("l","m","o"),
distance=1
)STEP 2: CREATE BALANCE TABLE
mytable <- balance (
input=mydata.tidy.omit,
diagnostic=3,
approach="weight",
censoring="no",
scope="all",
times.exposure=c(0,1,2),
times.covariate=c(0,1,2),
exposure="a",
history="h",
weight.exposure="wax",
ignore.missing.metric="no",
sort.order= c("l","m","o","n","p")
)STEP 3: PLOT BALANCE METRIC
myplot <- makeplot (
input=mytable,
diagnostic =3,
approach="weight",
scope="all",
metric="SMD"
)Display the plot
myplot
STEP 4: SAVE BALANCE TABLE AND PLOT
write.csv(mytable,paste(path,"mytable.csv",sep=""))
ggsave(filename=paste(path,"myplot.pdf",sep=""))Example of Regression Approach for Diagnostic 1
Now, we illustrate how Diagnostic 1 can be implemented using a regression approach.
Create tidy dataset
mydata.tidy <- lengthen(
input=mydata.history,
diagnostic=1,
censoring="no",
id="id",
times.exposure=c(0,1,2),
times.covariate=c(0,1,2),
exposure="a",
temporal.covariate=c("l","m","n","o","p"),
history="h"
)
head(mydata.tidy)
#> id name.cov time.exposure time.covariate h a value.cov
#> 1 1 l 0 0 H 1 1
#> 2 1 l 1 0 H1 0 1
#> 3 1 l 1 1 H1 0 1
#> 4 1 l 2 0 H10 0 1
#> 5 1 l 2 1 H10 0 1
#> 6 1 l 2 2 H10 0 1Notice that lengthen has already subset the data appropriately for diagnostic 1, where at any time \(t\) covariates are measured at or before exposure. We could use omit.history() to further restrict to the same measurement times for exposures and covariates.
Make a balance table using lengthen() and regression models
library(dplyr)
#>
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#>
#> filter, lag
#> The following objects are masked from 'package:base':
#>
#> intersect, setdiff, setequal, union
library(broom)
mydata.tidy.reg <- mutate(mydata.tidy,
time=time.exposure,
distance=time.exposure-time.covariate,
history=h)
output <- mydata.tidy.reg %>%
group_by(name.cov) %>% #note, you can include other stratifying variables here or in the model
filter(time.exposure>=time.covariate) %>% #lengthen actually arealdy took care of this, provided here for clarity
do(tidy(lm(formula=value.cov~a+time+distance+history,.))) %>% #same model form used for every covariate
filter(term=="a") %>% ungroup()
table.reg <- output %>%
select(name.cov,estimate) %>%
rename(D=estimate)
print(table.reg)
#> # A tibble: 5 x 2
#> name.cov D
#> <chr> <dbl>
#> 1 l 0.102
#> 2 m -0.149
#> 3 n 0.0462
#> 4 o 0.0832
#> 5 p 0.0368Compare that to a balance table via direct calculation & standardization
table.std <- balance(input=mydata.tidy,
diagnostic=1,
approach="none",
censoring="no",
scope="average",
average.over="distance",
ignore.missing.metric="no",
times.exposure=c(0,1,2),
times.covariate=c(0,1,2),
exposure="a",
history="h"
)
print(table.std)
#> period.id period.start period.end name.cov D SMD N
#> 1 1 0 2 l 0.10203234 0.21905115 60000
#> 2 1 0 2 m -0.15051552 -0.33489936 60000
#> 3 1 0 2 n 0.04648841 0.09452689 60000
#> 4 1 0 2 o 0.08324444 0.18305066 60000
#> 5 1 0 2 p 0.03766586 0.08452254 60000