If all the values are N times larger, the RMSE is N times larger, yes. You could calculate that as a percentage of the range of values or something to normalize, yes.
On Tue, Jan 15, 2013 at 6:53 PM, Zia mel <[email protected]> wrote: > the RMSE will vary depending on the range of data. For example if the > range of ratings is 0-1 it will be different when it is 1-10 . So my > question is that is there a way to say that the predicting rate is X% > instead of saying that the RMSE is 1 or 2 ? So I suggested diving the > RMSE/range to get a % . Do that make sense ? > > > On Tue, Jan 15, 2013 at 12:23 PM, Sean Owen <[email protected]> wrote: >> You have the definition there already, what are you asking? >> On Jan 15, 2013 5:58 PM, "Zia mel" <[email protected]> wrote: >> >>> Hi again , >>> >>> When evaluting preferences in recommenders and using >>> RMSRecommenderEvaluator, is it RMSE/RMSD >>> http://en.wikipedia.org/wiki/Root_mean_square_deviation >>> >>> If we get a value of 1 or 10 for RMSE what does that really mean ? Can >>> we represent RMSE by a % by dividing it on the range of preferences to >>> get a % of the error. For example if the RMSE is 1 and range is from >>> 0-5 can we say that the error of predicting is 1/5= 20% ? >>> >>> Thanks >>>
