Rolling mean (moving average) by group/id with dplyr

slider is a 'new-er' alternative that plays nicely with the tidyverse.

Something like this would do the trick

test2 <- test %>%
  group_by(ID) %>%
  arrange(ID, YEAR_VISIT) %>%
  mutate(BLOOD_PRESSURE_UPDATED = slider::slide_dbl(BLOOD_PRESSURE, mean, .before = 1, .after = 0)) %>%
ungroup()

If you are not committed to to dplyr this should work:

get.mav <- function(bp,n=2){
  require(zoo)
  if(is.na(bp[1])) bp[1] <- mean(bp,na.rm=TRUE)
  bp <- na.locf(bp,na.rm=FALSE)
  if(length(bp)<n) return(bp)
  c(bp[1:(n-1)],rollapply(bp,width=n,mean,align="right"))  
}
test <- with(test,test[order(ID,YEAR_VISIT),])

test$BLOOD_PRESSURE_UPDATED <- 
  unlist(aggregate(BLOOD_PRESSURE~ID,test,get.mav,na.action=NULL,n=2)$BLOOD_PRESSURE)
test
#    ID AGE YEAR_VISIT BLOOD_PRESSURE TREATMENT BLOOD_PRESSURE_UPDATED
# 1   1  20       2000             NA         3               134.6667
# 2   1  21       2001            129         2               131.8333
# 3   1  22       2002            145         3               137.0000
# 4   1  22       2002            130         2               137.5000
# 5   2  23       2003             NA        NA               130.0000
# 6   2  30       2010            150         2               140.0000
# 7   2  31       2011            110         3               130.0000
# ...

This works for moving averages > 2 as well.

And here's a data.table solution, which is likely to be much faster if your dataset is large.

library(data.table)
setDT(test)     # converts test to a data.table in place
setkey(test,ID,YEAR_VISIT)
test[,BLOOD_PRESSURE_UPDATED:=as.numeric(get.mav(BLOOD_PRESSURE,2)),by=ID]
test
#    ID AGE YEAR_VISIT BLOOD_PRESSURE TREATMENT BLOOD_PRESSURE_UPDATED
#  1:  1  20       2000             NA         3               134.6667
#  2:  1  21       2001            129         2               131.8333
#  3:  1  22       2002            145         3               137.0000
#  4:  1  22       2002            130         2               137.5000
#  5:  2  23       2003             NA        NA               130.0000
#  6:  2  30       2010            150         2               140.0000
#  7:  2  31       2011            110         3               130.0000
# ...

How about this?

    library(dplyr)   
    test2<-arrange(test,ID,YEAR_VISIT) %>% 
           mutate(lag1=lag(BLOOD_PRESSURE),
                  lag2=lag(BLOOD_PRESSURE,2),
                  movave=(lag1+lag2)/2)

Another solution using 'rollapply' function in zoo package (I like more)

library(dplyr)
library(zoo)
test2<-arrange(test,ID,YEAR_VISIT) %>%
       mutate(ma2=rollapply(BLOOD_PRESSURE,2,mean,align='right',fill=NA))

Tags:

R

Dplyr