markshanks
2015-Sep-25 22:33 UTC
[R] Analysis of causal relations between rare (categorical) events
Hi, I have only a relatively basic background in statistics (e.g., anova, regression), and the books on R I have read so far have focused on relatively common statistical analyses (e.g., outlier analysis, trend forecasting) and haven't helped me with the data problem I am facing. In short, imagine if the data is date stamped and we are interested in predicting the occurrence of relatively-rare, categorical events through the occurrence of other, relatively-rare categorical events. Both the outcomes and predictors can be a huge number of different types, although it is possible to group them as well. One way to go would seem to be to take the difference in time between each set of predictors and outcomes and see if there is more consistency for some measures than others?? However, I haven't found a good book or package that is directly aimed at this type of dataset, although I'm guessing there must be some... Thanks, Mark -- View this message in context: http://r.789695.n4.nabble.com/Analysis-of-causal-relations-between-rare-categorical-events-tp4712801.html Sent from the R help mailing list archive at Nabble.com.
Jim Lemon
2015-Sep-26 10:29 UTC
[R] Analysis of causal relations between rare (categorical) events
Hi Mark, You might find the eventInterval package of use. Jim On Sat, Sep 26, 2015 at 8:33 AM, markshanks <markshanks101 at hotmail.com> wrote:> Hi, > > I have only a relatively basic background in statistics (e.g., anova, > regression), and the books on R I have read so far have focused on > relatively common statistical analyses (e.g., outlier analysis, trend > forecasting) and haven't helped me with the data problem I am facing. > > In short, imagine if the data is date stamped and we are interested in > predicting the occurrence of relatively-rare, categorical events through > the > occurrence of other, relatively-rare categorical events. Both the outcomes > and predictors can be a huge number of different types, although it is > possible to group them as well. > > One way to go would seem to be to take the difference in time between each > set of predictors and outcomes and see if there is more consistency for > some > measures than others?? However, I haven't found a good book or package that > is directly aimed at this type of dataset, although I'm guessing there must > be some... > > Thanks, > > Mark > > > > > > -- > View this message in context: > http://r.789695.n4.nabble.com/Analysis-of-causal-relations-between-rare-categorical-events-tp4712801.html > Sent from the R help mailing list archive at Nabble.com. > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. >[[alternative HTML version deleted]]