5,979 reputation
11137
bio website www54.sap.com/industries/…
location Switzerland
age 38
visits member for 4 years, 1 month
seen 12 hours ago

During the day, I forecast sales at supermarkets, drugstores, furniture, perfume and other retailers and calculate order proposals. Lots of time series, with an emphasis on fast, automatic and robust data cleansing and forecasting - with some logistical optimization thrown in for good measure. I'm active in the International Institute of Forecasters and an Associate Editor for their practitioner-oriented journal Foresight.

At night, I switch hats and do inferential statistics for clinical and biological psychology.

I'm never bored. And I use R.


Oct
6
revised Is there any way to include regressors in tbats function in r?
Corrected answer based on a blog post by the package maintainer
Oct
2
comment Good sources to get papers in machine learning?
I happen to do so, yes. Why?
Oct
2
comment Good sources to get papers in machine learning?
What source did your supervisor recommend when you asked him? (You did ask him, right?)
Oct
1
comment What probability distribution to use for a variable X for which only an estimate is known?
There are a lot of distributions with mass on $(0,1)$ and a given mean: beta, triangular, uniform on subsets of $(0,1)$ symmetric around your mean... If you can assign a probability to each of these distributions (e.g., using a particular lognormal distibution for one parameter of the beta - the other one can then be calculated using the predefined mean), then you could in principle simulate your mixture. Otherwise, "averaging over all distributions" makes little sense.
Oct
1
answered Clustering objects based on event timestamps
Sep
30
awarded  Explainer
Sep
29
answered What is this formula?
Sep
26
comment Statistical learning theory
The 2nd edition of Elements of Statistical Learning can be freely downloaded.
Sep
26
comment Is there any way to include regressors in tbats function in r?
Contact him and ask. Explain that the tbats help page refers to the auto.arima help page, which claims that auto.arima can handle regressors.
Sep
26
comment Is there any way to include regressors in tbats function in r?
It's possible that auto.arima() removes regressors, e.g., by AIC. A quick glance at the paper referenced in the auto.arima help page does not tell how external regressors are handled. You may possibly have found a bug. Best to step through the source code and/or contact the package maintainer, Rob Hyndman.
Sep
26
comment Dichotomizing Continuous Variables in Regression: Good or Bad?
Questions about discretizing continuous data have been asked and answered many times here (Frank Harrell to chime in in 3... 2... 1...). @EdM gives one good example; I pointed to another one in flagging this for closure as a duplicate.
Sep
25
comment Is there any way to include regressors in tbats function in r?
On the one hand, you can try multiple different models, as you propose. On the other hand, sometimes it simply is hard to improve on a given forecast, if the series is inherently not very forecastable. Good luck!
Sep
25
comment forecasting for data excluding holiday dummies
Here you go.
Sep
25
answered Is there any way to include regressors in tbats function in r?
Sep
25
comment forecasting for data excluding holiday dummies
Did you try using dummies for the holidays? Use the xreg parameter to arima() - this also works for tbats(), as it is passed through to auto.arima(), which models the errors.
Sep
25
awarded  time-series
Sep
24
comment How can one say if a model is poor based on RMSE value
When you wrote that "they are almost 80% wrong in predictions", it sounded like you were using published benchmarks on forecasting accuracy for an industry. If I understand your last comment correctly, you already have "standard" forecasts for the data you are using your models on, correct? Then you can disregard my last comment. And you could directly compare your and the standard forecasts and see how often yours is better.
Sep
24
comment How can one say if a model is poor based on RMSE value
@Fateme: that sounds reasonable. However, I'd advise you to be very cautious about trusting industry benchmarks for forecasting accuracy.
Sep
24
revised How can one say if a model is poor based on RMSE value
improved formatting and removed R tag, added time-series and accuracy tags
Sep
24
answered How can one say if a model is poor based on RMSE value