The underlying assumptions of traditional autoregressive models are well known. The resulting complexity with these models leads to observations such as,
``We have found that choosing the wrong model or parameters can often yield poor results, and it is unlikely that even experienced analysts can choose the correct model and parameters efficiently given this array of choices.’’
NNS
simplifies the forecasting process. Below are some
examples demonstrating NNS.ARMA
and its
assumption free, minimal parameter forecasting
method.
NNS.ARMA
has the ability to fit a
linear regression to the relevant component series, yielding very fast
results. For our running example we will use the
AirPassengers
dataset loaded in base R.
We will forecast 44 periods h = 44
of
AirPassengers
using the first 100 observations
training.set = 100
, returning estimates of the final 44
observations. We will then test this against our validation set of
tail(AirPassengers,44)
.
Since this is monthly data, we will try a
seasonal.factor = 12
.
Below is the linear fit and associated root mean squared error (RMSE)
using method = "lin"
.
nns_lin = NNS.ARMA(AirPassengers,
h = 44,
training.set = 100,
method = "lin",
plot = TRUE,
seasonal.factor = 12,
seasonal.plot = FALSE)
## [1] 35.39965
Now we can try using a nonlinear regression on the relevant component
series using method = "nonlin"
.
We can test a series of seasonal.factors
and select the
best one to fit. The largest period to consider would be
0.5 * length(variable)
, since we need more than 2 points
for a regression! Remember, we are testing the first 100 observations of
AirPassengers
, not the full 144 observations.
seas = t(sapply(1 : 25, function(i) c(i, sqrt( mean( (NNS.ARMA(AirPassengers, h = 44, training.set = 100, method = "lin", seasonal.factor = i, plot=FALSE) - tail(AirPassengers, 44)) ^ 2) ) ) ) )
colnames(seas) = c("Period", "RMSE")
seas
## Period RMSE
## [1,] 1 75.67783
## [2,] 2 75.71250
## [3,] 3 75.87604
## [4,] 4 75.16563
## [5,] 5 76.07418
## [6,] 6 70.43185
## [7,] 7 77.98493
## [8,] 8 75.48997
## [9,] 9 79.16378
## [10,] 10 81.47260
## [11,] 11 106.56886
## [12,] 12 35.39965
## [13,] 13 90.98265
## [14,] 14 95.64979
## [15,] 15 82.05345
## [16,] 16 74.63052
## [17,] 17 87.54036
## [18,] 18 74.90881
## [19,] 19 96.96011
## [20,] 20 88.75015
## [21,] 21 100.21346
## [22,] 22 108.68674
## [23,] 23 85.06430
## [24,] 24 35.49018
## [25,] 25 75.16192
Now we know seasonal.factor = 12
is our best fit, we can
see if there’s any benefit from using a nonlinear regression.
Alternatively, we can define our best fit as the corresponding
seas$Period
entry of the minimum value in our
seas$RMSE
column.
Below you will notice the use of seasonal.factor = a
generates the same output.
nns = NNS.ARMA(AirPassengers,
h = 44,
training.set = 100,
method = "nonlin",
seasonal.factor = a,
plot = TRUE, seasonal.plot = FALSE)
## [1] 20.55102
Note: You may experience instances with monthly data
that report seasonal.factor
close to multiples of 3, 4, 6
or 12. For instance, if the reported
seasonal.factor = {37, 47, 71, 73}
use
(seasonal.factor = c(36, 48, 72))
by setting the
modulo
parameter in
NNS.seas(..., modulo = 12)
. The same
suggestion holds for daily data and multiples of 7, or any other time
series with logically inferred cyclical patterns. The nearest periods to
that modulo
will be in the expanded output.
## $all.periods
## Period Coefficient.of.Variation Variable.Coefficient.of.Variation
## 1: 48 0.4002249 0.4279947
## 2: 12 0.4059923 0.4279947
## 3: 60 0.4279947 0.4279947
## 4: 36 0.4279947 0.4279947
## 5: 24 0.4279947 0.4279947
##
## $best.period
## Period
## 48
##
## $periods
## [1] 48 12 60 36 24
seasonal.factor
NNS also offers a wrapper function
NNS.ARMA.optim()
to test a given vector of
seasonal.factor
and returns the optimized objective
function (in this case RMSE written as
obj.fn = expression( sqrt(mean((predicted - actual)^2)) )
)
and the corresponding periods, as well as the
NNS.ARMA
regression method used.
Alternatively, using external package objective functions work as well
such as
obj.fn = expression(Metrics::rmse(actual, predicted))
.
NNS.ARMA.optim()
will also test whether
to regress the underlying data first, shrink
the estimates
to their subset mean values, include a bias.shift
based on
its internal validation errors, and compare different
weights
of both linear and nonlinear estimates.
Given our monthly dataset, we will try multiple years by setting
seasonal.factor = seq(12, 60, 6)
every 6 months based on
our NNS.seas() insights above.
nns.optimal = NNS.ARMA.optim(AirPassengers,
training.set = 100,
seasonal.factor = seq(12, 60, 6),
obj.fn = expression( sqrt(mean((predicted - actual)^2)) ),
objective = "min",
pred.int = .95, plot = TRUE)
nns.optimal
[1] "CURRNET METHOD: lin"
[1] "COPY LATEST PARAMETERS DIRECTLY FOR NNS.ARMA() IF ERROR:"
[1] "NNS.ARMA(... method = 'lin' , seasonal.factor = c( 12 ) ...)"
[1] "CURRENT lin OBJECTIVE FUNCTION = 35.3996540135277"
[1] "BEST method = 'lin', seasonal.factor = c( 12 )"
[1] "BEST lin OBJECTIVE FUNCTION = 35.3996540135277"
[1] "CURRNET METHOD: nonlin"
[1] "COPY LATEST PARAMETERS DIRECTLY FOR NNS.ARMA() IF ERROR:"
[1] "NNS.ARMA(... method = 'nonlin' , seasonal.factor = c( 12 ) ...)"
[1] "CURRENT nonlin OBJECTIVE FUNCTION = 20.5510211522245"
[1] "BEST method = 'nonlin' PATH MEMBER = c( 12 )"
[1] "BEST nonlin OBJECTIVE FUNCTION = 20.5510211522245"
[1] "CURRNET METHOD: both"
[1] "COPY LATEST PARAMETERS DIRECTLY FOR NNS.ARMA() IF ERROR:"
[1] "NNS.ARMA(... method = 'both' , seasonal.factor = c( 12 ) ...)"
[1] "CURRENT both OBJECTIVE FUNCTION = 19.4534618627141"
[1] "BEST method = 'both' PATH MEMBER = c( 12 )"
[1] "BEST both OBJECTIVE FUNCTION = 19.4534618627141"
$periods
[1] 12
$weights
NULL
$obj.fn
[1] 19.45346
$method
[1] "both"
$shrink
[1] FALSE
$nns.regress
[1] FALSE
$bias.shift
[1] 8.983377
$errors
[1] -14.240300 -20.899691 -17.699956 -31.623457 -22.080467 -15.972663
[7] -12.633377 -4.289462 -2.371119 2.417484 16.657475 24.096405
[13] 8.926263 6.535789 1.826191 -27.314316 14.649727 2.812027
[19] 10.087412 26.318135 8.130503 5.994088 5.810046 8.968724
[25] -15.343831 11.107010 -9.030058 -37.870074 -6.868421 -13.948830
[31] -13.833241 -10.076019 -19.089073 -16.278753 25.441499 -23.904395
[37] -35.211740 -11.322375 -38.211436 -42.494907 -15.487474 -37.670592
[43] -14.477746 -6.587231
$results
[1] 349.7431 410.0837 456.2834 444.3599 390.9029 340.0107 301.3500 340.6939
[9] 346.6123 329.4009 387.6409 381.0798 376.5337 442.1913 493.9687 479.2886
[17] 421.0377 366.8738 324.8321 367.6235 371.9435 351.7882 414.2779 408.6346
[25] 405.9523 477.0303 533.3005 516.6684 452.9214 394.5738 349.1661 394.8069
[33] 397.6765 374.3703 441.9106 436.5026 434.6776 511.4234 571.8929 553.3783
[41] 484.1285 421.4944 373.0609 421.2843
$lower.pred.int
[1] 302.5739 362.9145 409.1142 397.1907 343.7337 292.8415 254.1808 293.5247
[9] 299.4430 282.2317 340.4716 333.9106 329.3645 395.0221 446.7995 432.1194
[17] 373.8685 319.7046 277.6629 320.4543 324.7743 304.6190 367.1087 361.4654
[25] 358.7831 429.8611 486.1313 469.4992 405.7521 347.4046 301.9968 347.6377
[33] 350.5072 327.2011 394.7414 389.3334 387.5084 464.2542 524.7237 506.2091
[41] 436.9593 374.3252 325.8917 374.1151
$upper.pred.int
[1] 384.0671 444.4077 490.6074 478.6839 425.2269 374.3347 335.6740 375.0179
[9] 380.9363 363.7249 421.9648 415.4038 410.8577 476.5153 528.2927 513.6126
[17] 455.3617 401.1978 359.1561 401.9475 406.2675 386.1122 448.6019 442.9586
[25] 440.2763 511.3543 567.6245 550.9924 487.2453 428.8978 383.4900 429.1309
[33] 432.0004 408.6943 476.2346 470.8266 469.0016 545.7474 606.2169 587.7023
[41] 518.4525 455.8184 407.3849 455.6083
We can forecast another 50 periods out-of-sample
(h = 50
), by dropping the training.set
parameter while generating the 95% prediction intervals.
NNS.ARMA.optim(AirPassengers,
seasonal.factor = seq(12, 60, 6),
obj.fn = expression( sqrt(mean((predicted - actual)^2)) ),
objective = "min",
pred.int = .95, h = 50, plot = TRUE)
seasonal.factor = c(1, 2, ...)
We included the ability to use any number of specified seasonal periods simultaneously, weighted by their strength of seasonality. Computationally expensive when used with nonlinear regressions and large numbers of relevant periods.
weights
Instead of weighting by the seasonal.factor
strength of
seasonality, we offer the ability to weight each per any defined
compatible vector summing to 1.
Equal weighting would be weights = "equal"
.
pred.int
Provides the values for the specified prediction intervals within [0,1] for each forecasted point and plots the bootstrapped replicates for the forecasted points.
seasonal.factor = FALSE
We also included the ability to use all detected seasonal periods simultaneously, weighted by their strength of seasonality. Computationally expensive when used with nonlinear regressions and large numbers of relevant periods.
best.periods
This parameter restricts the number of detected seasonal periods to
use, again, weighted by their strength. To be used in conjunction with
seasonal.factor = FALSE
.
modulo
To be used in conjunction with seasonal.factor = FALSE
.
This parameter will ensure logical seasonal patterns (i.e.,
modulo = 7
for daily data) are included along with the
results.
mod.only
To be used in conjunction with
seasonal.factor = FALSE & modulo != NULL
. This
parameter will ensure empirical patterns are kept along with the logical
seasonal patterns.
dynamic = TRUE
This setting generates a new seasonal period(s) using the estimated
values as continuations of the variable, either with or without a
training.set
. Also computationally expensive due to the
recalculation of seasonal periods for each estimated value.
plot
, seasonal.plot
These are the plotting arguments, easily enabled or disabled with
TRUE
or FALSE
.
seasonal.plot = TRUE
will not plot without
plot = TRUE
. If a seasonal analysis is all that is desired,
NNS.seas
is the function specifically suited for that
task.
The extension to a generalized multivariate instance is provided in
the following documentation of the
NNS.VAR()
function:
If the user is so motivated, detailed arguments and proofs are provided within the following: