AllTotalEffOutput: Summary of Total Effects
In PathSelectMP: Backwards Variable Selection for Paths using M Plus

Description Usage Arguments Details Value Note Author(s) References See Also Examples

total effects averaged over imputed data sets, if there are imputations, with accompanying p value summaries

1	AllTotalEffOutput(AllDat, GreaterThanNum = 0, Directry = getwd())

`AllDat`	output from `ConvertData2`
`GreaterThanNum`	number of output files containing path over which to average which must be less than the number of imputations and is only used if multiple imputations are performed. Default 0 which is to use all data sets in mean calculations.
`Directry`	this the path where the folder specified by `AllNames` is located and default is working directory

Must initialize and run backwards selection before using this function

list of matrices which are respectively:

`Count`	number of times total effect appears in imputed data sets final path selection
`AverageEffects`	mean values of total effects for paths which are just the total effects if no imputations are performed
`AverageStandardError`	the mean square error of the effect parameters averaged over imputed data sets if they exist
`AveragePVal`	mean p values of these total effects
`MinPval`	minimum p values of these total effects
`MaxPVal`	maximum p value of these total effects
`MedianPVal`	median p value of these total effects

total effects and direct effect averages are done separately so a path may be present in one summary and not the other when using the same GreaterThanNum which is not equal to zero

William Terry

M Plus

AllSummary2

## Not run: 

InitD=Simulate(MissingYN=1)
xxx=Initialize(InitD,NumImpute=3,WhichCat=c(1,1,1,1,0))
ggg=AllBackwardSelect(xxx[[1]])
yyy=AllSummary2(xxx[[1]])
AllDat1=ConvertData2(xxx[[1]],xxx[[2]],yyy[[1]])
TotsAllEff=AllTotalEffOutput(AllDat1)

## End(Not run)