SDQ: Generating scores in R
The scoring algorithm is based on the 25 variables plus impact items for
each questionnaire. The algorithm expects to find these variables with
specific names: the first letter of each variable name is 'p' for the parent
SDQ, 's' for the self-report SDQ and 't' for the teacher SDQ. After this
first letter, the variable names are as follows:
| consid | = | Item 1 : considerate |
| restles | = | Item 2 : restless |
| somatic | = | Item 3 : somatic symptoms |
| shares | = | Item 4 : shares readily |
| tantrum | = | Item 5 : tempers |
| loner | = | Item 6 : solitary |
| obeys | = | Item 7 : obedient |
| worries | = | Item 8 : worries |
| caring | = | Item 9 : helpful if someone hurt |
| fidgety | = | Item 10 : fidgety |
| friend | = | Item 11 : has good friend |
| fights | = | Item 12 : fights or bullies |
| unhappy | = | Item 13 : unhappy |
| popular | = | Item 14 : generally liked |
| distrac | = | Item 15 : easily distracted |
| clingy | = | Item 16 : nervous in new situations |
| kind | = | Item 17 : kind to younger children |
| lies | = | Item 18 : lies or cheats [for the SDQ for 2-4 year olds, replace 'lies' with 'argues'] |
| bullied | = | Item 19 : picked on or bullied |
| helpout | = | Item 20 : often volunteers |
| reflect | = | Item 21 : thinks before acting |
| steals | = | Item 22 : steals [for the SDQ for 2-4 year olds, replace 'steals' with 'spite'] |
| oldbest | = | Item 23 : better with adults than with children |
| afraid | = | Item 24 : many fears |
| attends | = | Item 25 : good attention |
| ebddiff | = | Impact question: oveall difficulties in at least one area |
| distres | = | Impact question: upset or distressed |
| imphome | = | Impact question: interferes with home life |
| impfrie | = | Impact question: interferes with friendships |
| impclas | = | Impact question: interferes with learning |
| impleis | = | Impact question: interferes with leisure |
For each of these items, if the first response category (not true, no, not
at all) has been selected, this is coded as zero, the next response category
(somewhat true, yes-minor, just a little) is coded as one and so on.
For each informant, the algorithm generates six scores. The first letter
of each derived variable is 'p' for parent-based scores, 's' for self-report-based
scores and 't' for teacher-based scores. After this first letter, the names
of the scores are as follows:
| emotion | = | emotional symptoms |
| conduct | = | conduct problems |
| hyper | = | hyperactivity/inattention |
| peer | = | peer problems |
| prosoc | = | prosocial |
| ebdtot | = | total difficulties |
| impact | = | impact |
# Syntax assumes data is already read into R
require(car) # Required for the "recode" function
# Recoding variables and then scoring the parent SDQ scores
qobeys <- recode (pobeys, "0=2; 1=1; 2=0; else=NA")
qreflect <- recode (preflect, "0=2; 1=1; 2=0; else=NA")
qattends <- recode (pattends, "0=2; 1=1; 2=0; else=NA")
qfriend <- recode (pfriend, "0=2; 1=1; 2=0; else=NA")
qpopular <- recode (ppopular, "0=2; 1=1; 2=0; else=NA")
qqdistres <- recode (pdistres, "0:1=0; 2=1; 3=2; NA=0")
qqimphome <- recode (pimphome, "0:1=0; 2=1; 3=2; NA=0")
qqimpfrie <- recode (pimpfrie, "0:1=0; 2=1; 3=2; NA=0")
qqimpclas <- recode (pimpclas, "0:1=0; 2=1; 3=2; NA=0")
qqimpleis <- recode (pimpleis, "0:1=0; 2=1; 3=2; NA=0")
df.pemotion <- data.frame(psomatic, pworries, punhappy, pclingy, pafraid)
pnemotion <- apply(df.pemotion, 1, function(x) sum(is.na(x)))
pemotion <- ifelse(pnemotion<3, rowMeans(df.pemotion, na.rm=TRUE), NA)
pemotion <- as.numeric(pemotion) * 5
pemotion <- floor(0.5 + pemotion)
df.pconduct <- data.frame(ptantrum, qobeys, pfights, plies, psteals)
pnconduct <- apply(df.pconduct, 1, function(x) sum(is.na(x)))
pconduct <- ifelse(pnconduct<3, rowMeans(df.pconduct, na.rm=TRUE), NA)
pconduct <- as.numeric(pconduct) * 5
pconduct <- floor(0.5 + pconduct)
df.phyper <- data.frame(prestles, pfidgety, pdistrac, qreflect, qattends)
pnhyper <- apply(df.phyper, 1, function(x) sum(is.na(x)))
phyper <- ifelse(pnhyper<3, rowMeans(df.phyper, na.rm=TRUE), NA)
phyper <- as.numeric(phyper) * 5
phyper <- floor(0.5 + phyper)
df.ppeer <- data.frame(ploner, qfriend, qpopular, pbullied, poldbest)
pnpeer <- apply(df.ppeer, 1, function(x) sum(is.na(x)))
ppeer <- ifelse(pnpeer<3, rowMeans(df.ppeer, na.rm=TRUE), NA)
ppeer <- as.numeric(ppeer) * 5
ppeer <- floor(0.5 + ppeer)
df.pprosoc <- data.frame(pconsid, pshares, pcaring, pkind, phelpout)
pnprosoc <- apply(df.pprosoc, 1, function(x) sum(is.na(x)))
pprosoc <- ifelse(pnprosoc<3, rowMeans(df.pprosoc, na.rm=TRUE), NA)
pprosoc <- as.numeric(pprosoc) * 5
pprosoc <- floor(0.5 + pprosoc)
df.pimpact <- data.frame(pdistres, pimphome, pimpfrie, pimpclas, pimpleis)
pnimpact <- apply(df.pimpact, 1, function(x) sum(is.na(x)))
pimpact <- ifelse(!pnimpact==5, qqdistres+qqimphome+qqimpfrie+qqimpclas+qqimpleis, NA)
pimpact <- ifelse(pebddiff==0, 0, pimpact)
pimpact <- as.numeric(pimpact)
pebdtot <- pemotion+pconduct+phyper+ppeer
rm(qobeys, qreflect, qattends, qfriend, qpopular, qqdistres, qqimphome, qqimpfrie,
qqimpclas, qqimpleis, pnemotion, pnconduct, pnhyper, pnpeer, pnprosoc, pnimpact,
df.pemotion, df.pconduct, df.phyper, df.ppeer, df.pprosoc, df.pimpact)
# Recoding variables and then scoring the youth self-report SDQ scores
robeys <- recode (sobeys, "0=2; 1=1; 2=0; else=NA")
rreflect <- recode (sreflect, "0=2; 1=1; 2=0; else=NA")
rattends <- recode (sattends, "0=2; 1=1; 2=0; else=NA")
rfriend <- recode (sfriend, "0=2; 1=1; 2=0; else=NA")
rpopular <- recode (spopular, "0=2; 1=1; 2=0; else=NA")
rrdistres <- recode (sdistres, "0:1=0; 2=1; 3=2; NA=0")
rrimphome <- recode (simphome, "0:1=0; 2=1; 3=2; NA=0")
rrimpfrie <- recode (simpfrie, "0:1=0; 2=1; 3=2; NA=0")
rrimpclas <- recode (simpclas, "0:1=0; 2=1; 3=2; NA=0")
rrimpleis <- recode (simpleis, "0:1=0; 2=1; 3=2; NA=0")
df.semotion <- data.frame(ssomatic, sworries, sunhappy, sclingy, safraid)
snemotion <- apply(df.semotion, 1, function(x) sum(is.na(x)))
semotion <- ifelse(snemotion<3, rowMeans(df.semotion, na.rm=TRUE), NA)
semotion <- as.numeric(semotion) * 5
semotion <- floor(0.5 + semotion)
df.sconduct <- data.frame(stantrum, robeys, sfights, slies, ssteals)
snconduct <- apply(df.sconduct, 1, function(x) sum(is.na(x)))
sconduct <- ifelse(snconduct<3, rowMeans(df.sconduct, na.rm=TRUE), NA)
sconduct <- as.numeric(sconduct) * 5
sconduct <- floor(0.5 + sconduct)
df.shyper <- data.frame(srestles, sfidgety, sdistrac, rreflect, rattends)
snhyper <- apply(df.shyper, 1, function(x) sum(is.na(x)))
shyper <- ifelse(snhyper<3, rowMeans(df.shyper, na.rm=TRUE), NA)
shyper <- as.numeric(shyper) * 5
shyper <- floor(0.5 + shyper)
df.speer <- data.frame(sloner, rfriend, rpopular, sbullied, soldbest)
snpeer <- apply(df.speer, 1, function(x) sum(is.na(x)))
speer <- ifelse(snpeer<3, rowMeans(df.speer, na.rm=TRUE), NA)
speer <- as.numeric(speer) * 5
speer <- floor(0.5 + speer)
df.sprosoc <- data.frame(sconsid, sshares, scaring, skind, shelpout)
snprosoc <- apply(df.sprosoc, 1, function(x) sum(is.na(x)))
sprosoc <- ifelse(snprosoc<3, rowMeans(df.sprosoc, na.rm=TRUE), NA)
sprosoc <- as.numeric(sprosoc) * 5
sprosoc <- floor(0.5 + sprosoc)
df.simpact <- data.frame(sdistres, simphome, simpfrie, simpclas, simpleis)
snimpact <- apply(df.simpact, 1, function(x) sum(is.na(x)))
simpact <- ifelse(!snimpact==5, rrdistres+rrimphome+rrimpfrie+rrimpclas+rrimpleis, NA)
simpact <- ifelse(sebddiff==0, 0, simpact)
simpact <- as.numeric(simpact)
sebdtot <- semotion+sconduct+shyper+speer
rm (robeys, rreflect, rattends, rfriend, rpopular, rrdistres, rrimphome, rrimpfrie,
rrimpclas, rrimpleis, snemotion, snconduct, snhyper, snpeer, snprosoc, snimpact,
df.semotion, df.sconduct, df.shyper, df.speer, df.sprosoc, df.simpact)
# Recoding variables and then scoring the teacher SDQ scores
uobeys <- recode (tobeys, "0=2; 1=1; 2=0; else=NA")
ureflect <- recode (treflect, "0=2; 1=1; 2=0; else=NA")
uattends <- recode (tattends, "0=2; 1=1; 2=0; else=NA")
ufriend <- recode (tfriend, "0=2; 1=1; 2=0; else=NA")
upopular <- recode (tpopular, "0=2; 1=1; 2=0; else=NA")
uudistres <- recode (tdistres, "0:1=0; 2=1; 3=2; NA=0")
uuimpfrie <- recode (timpfrie, "0:1=0; 2=1; 3=2; NA=0")
uuimpclas <- recode (timpclas, "0:1=0; 2=1; 3=2; NA=0")
df.temotion <- data.frame(tsomatic, tworries, tunhappy, tclingy, tafraid)
tnemotion <- apply(df.temotion, 1, function(x) sum(is.na(x)))
temotion <- ifelse(tnemotion<3, rowMeans(df.temotion, na.rm=TRUE), NA)
temotion <- as.numeric(temotion) * 5
temotion <- floor(0.5 + temotion)
df.tconduct <- data.frame(ttantrum, uobeys, tfights, tlies, tsteals)
tnconduct <- apply(df.tconduct, 1, function(x) sum(is.na(x)))
tconduct <- ifelse(tnconduct<3, rowMeans(df.tconduct, na.rm=TRUE), NA)
tconduct <- as.numeric(tconduct) * 5
tconduct <- floor(0.5 + tconduct)
df.thyper <- data.frame(trestles, tfidgety, tdistrac, ureflect, uattends)
tnhyper <- apply(df.thyper, 1, function(x) sum(is.na(x)))
thyper <- ifelse(tnhyper<3, rowMeans(df.thyper, na.rm=TRUE), NA)
thyper <- as.numeric(thyper) * 5
thyper <- floor(0.5 + thyper)
df.tpeer <- data.frame(tloner, ufriend, upopular, tbullied, toldbest)
tnpeer <- apply(df.tpeer, 1, function(x) sum(is.na(x)))
tpeer <- ifelse(tnpeer<3, rowMeans(df.tpeer, na.rm=TRUE), NA)
tpeer <- as.numeric(tpeer) * 5
tpeer <- floor(0.5 + tpeer)
df.tprosoc <- data.frame(tconsid, tshares, tcaring, tkind, thelpout)
tnprosoc <- apply(df.tprosoc, 1, function(x) sum(is.na(x)))
tprosoc <- ifelse(tnprosoc<3, rowMeans(df.tprosoc, na.rm=TRUE), NA)
tprosoc <- as.numeric(tprosoc) * 5
tprosoc <- floor(0.5 + tprosoc)
df.timpact <- data.frame(tdistres, timpfrie, timpclas)
tnimpact <- apply(df.timpact, 1, function(x) sum(is.na(x)))
timpact <- ifelse(!tnimpact==3, uudistres+uuimpfrie+uuimpclas, NA)
timpact <- ifelse(tebddiff==0, 0, timpact)
timpact <- as.numeric(timpact)
tebdtot <- temotion+tconduct+thyper+tpeer
rm (uobeys, ureflect, uattends, ufriend, upopular, uudistres, uuimpfrie, uuimpclas,
tnemotion, tnconduct, tnhyper, tnpeer, tnprosoc, tnimpact, df.temotion, df.tconduct,
df.thyper, df.tpeer, df.tprosoc, df.timpact)
The predictive algorithm was converted into R syntax by Tormod Bøe
|