Visualization of probabilistic forecasts

This week my research group dis­cussed Adrian Raftery’s recent paper on “Use and Com­mu­ni­ca­tion of Prob­a­bilis­tic Fore­casts” which pro­vides a fas­ci­nat­ing but brief sur­vey of some of his work on mod­el­ling and com­mu­ni­cat­ing uncer­tain futures. Coin­ci­den­tally, today I was also sent a copy of David Spiegelhalter’s paper on “Visu­al­iz­ing Uncer­tainty About the Future”. Both are well-​​worth reading.

It made me think about my own efforts to com­mu­ni­cate future uncer­tainty through graph­ics. Of course, for time series fore­casts I nor­mally show pre­dic­tion inter­vals. I pre­fer to use more than one inter­val at a time because it helps con­vey a lit­tle more infor­ma­tion. The default in the fore­cast pack­age for R is to show both an 80% and a 95% inter­val like this: Con­tinue reading →

Seasonal periods

I get ques­tions about this almost every week. Here is an exam­ple from a recent com­ment on this blog:

I have two large time series data. One is sep­a­rated by sec­onds inter­vals and the other by min­utes. The length of each time series is 180 days. I’m using R (3.1.1) for fore­cast­ing the data. I’d like to know the value of the “fre­quency” argu­ment in the ts() func­tion in R, for each data set. Since most of the exam­ples and cases I’ve seen so far are for months or days at the most, it is quite con­fus­ing for me when deal­ing with equally sep­a­rated sec­onds or min­utes. Accord­ing to my under­stand­ing, the “fre­quency” argu­ment is the num­ber of obser­va­tions per sea­son. So what is the “sea­son” in the case of seconds/​minutes? My guess is that since there are 86,400 sec­onds and 1440 min­utes a day, these should be the val­ues for the “freq” argu­ment. Is that correct?

Con­tinue reading →

ABS seasonal adjustment update

Since my last post on the sea­sonal adjust­ment prob­lems at the Aus­tralian Bureau of Sta­tis­tics, I’ve been work­ing closely with peo­ple within the ABS to help them resolve the prob­lems in time for tomorrow’s release of the Octo­ber unem­ploy­ment figures.

Now that the ABS has put out a state­ment about the prob­lem, I thought it would be use­ful to explain the under­ly­ing method­ol­ogy for those who are inter­ested. Con­tinue reading →

Prediction intervals too narrow

Almost all pre­dic­tion inter­vals from time series mod­els are too nar­row. This is a well-​​known phe­nom­e­non and arises because they do not account for all sources of uncer­tainty. In my 2002 IJF paper, we mea­sured the size of the prob­lem by com­put­ing the actual cov­er­age per­cent­age of the pre­dic­tion inter­vals on hold-​​out sam­ples. We found that for ETS mod­els, nom­i­nal 95% inter­vals may only pro­vide cov­er­age between 71% and 87%. The dif­fer­ence is due to miss­ing sources of uncertainty.

There are at least four sources of uncer­tainty in fore­cast­ing using time series models:

  1. The ran­dom error term;
  2. The para­me­ter estimates;
  3. The choice of model for the his­tor­i­cal data;
  4. The con­tin­u­a­tion of the his­tor­i­cal data gen­er­at­ing process into the future.

Con­tinue reading →

hts with regressors

The hts pack­age for R allows for fore­cast­ing hier­ar­chi­cal and grouped time series data. The idea is to gen­er­ate fore­casts for all series at all lev­els of aggre­ga­tion with­out impos­ing the aggre­ga­tion con­straints, and then to rec­on­cile the fore­casts so they sat­isfy the aggre­ga­tion con­straints. (An intro­duc­tion to rec­on­cil­ing hier­ar­chi­cal and grouped time series is avail­able in this Fore­sight paper.)

The base fore­casts can be gen­er­ated using any method, with ETS mod­els and ARIMA mod­els pro­vided as options in the forecast.gts() func­tion. As ETS mod­els do not allow for regres­sors, you will need to choose ARIMA mod­els if you want to include regres­sors. Con­tinue reading →

Explaining the ABS unemployment fluctuations

Although the Guardian claimed yes­ter­day that I had explained “what went wrong” in the July and August unem­ploy­ment fig­ures, I made no attempt to do so as I had no infor­ma­tion about the prob­lems. Instead, I just explained a lit­tle about the pur­pose of sea­sonal adjustment.

How­ever, today I learned a lit­tle more about the ABS unem­ploy­ment data prob­lems, includ­ing what may be the expla­na­tion for the fluc­tu­a­tions. This expla­na­tion was offered by Westpac’s chief econ­o­mist, Bill Evans (see here for a video of him explain­ing the issue). Con­tinue reading →

Connect with local employers

I keep telling stu­dents that there are lots of jobs in data sci­ence (includ­ing sta­tis­tics), and they often tell me they can’t find them adver­tised. As usual, you do have to do some net­work­ing, and one of the best ways of doing it is via a Data Sci­ence Meetup. Many cities now have them includ­ing Mel­bourne, Syd­ney, Lon­don, etc. It is the per­fect oppor­tu­nity to meet with local employ­ers, many of which are hir­ing due to the huge expan­sion in the use of data analy­sis in busi­ness (aka busi­ness analytics).

At the end of each Mel­bourne meetup, some employ­ers have been adver­tis­ing their cur­rent ana­lytic job open­ings to the audience.

Now the local orga­niz­ers are going to extend the oppor­tu­nity to allow job-​​searchers to give a 90 sec­ond pitch to employ­ers. Details are pro­vided on the mes­sage board.

TBATS with regressors

I’ve received a few emails about includ­ing regres­sion vari­ables (i.e., covari­ates) in TBATS mod­els. As TBATS mod­els are related to ETS mod­els, tbats() is unlikely to ever include covari­ates as explained here. It won’t actu­ally com­plain if you include an xreg argu­ment, but it will ignore it.

When I want to include covari­ates in a time series model, I tend to use auto.arima() with covari­ates included via the xreg argu­ment. If the time series has mul­ti­ple sea­sonal peri­ods, I use Fourier terms as addi­tional covari­ates. See my post on fore­cast­ing daily data for some dis­cus­sion of this model. Note that fourier() and fourierf() now han­dle msts objects, so it is very sim­ple to do this.

For exam­ple, if holiday con­tains some dummy vari­ables asso­ci­ated with pub­lic hol­i­days and holidayf con­tains the cor­re­spond­ing vari­ables for the first 100 fore­cast peri­ods, then the fol­low­ing code can be used:

y <- msts(x, seasonal.periods=c(7,365.25))
z <- fourier(y, K=c(5,5))
zf <- fourierf(y, K=c(5,5), h=100)
fit <- auto.arima(y, xreg=cbind(z,holiday), seasonal=FALSE)
fc <- forecast(fit, xreg=cbind(zf,holidayf), h=100)

The main dis­ad­van­tage of the ARIMA approach is that the sea­son­al­ity is forced to be peri­odic, whereas a TBATS model allows for dynamic seasonality.