Re: [R] Time Series methods

2009-11-02 Thread Tim Bean
Sure, but it seems like the point of the time series class is so you don't have to create a factor based on the period of sampling. Is there anyway of imposing calculations like median on the time series class, or is Kjetil's suggestion the only approach? Thanks! On Sun, Nov 1, 2009 at 4:09 PM, K

Re: [R] Time Series methods

2009-11-01 Thread Kjetil Halvorsen
introduce a factor variable with the months and then use tapply? Kjetil On Sun, Nov 1, 2009 at 9:07 PM, Tim Bean wrote: > Hello, I have a quick question about time series methodology. If I want to > display a boxplot of time series data, sorted by period, I can type: > > boxplot(data ~ cycle(dat