Tarea ARIMA
pkgs
PIB Alemania
Importar datos
gdp <- tidyquant::tq_get(
x = "CLVMNACSCAB1GQDE",
get = "economic.data",
from = "1997-01-01"
)Registered S3 method overwritten by 'quantmod':
method from
as.zoo.data.frame zoo
gdp <- gdp |>
mutate(date = yearquarter(date)) |>
as_tsibble(
index = date,
key = symbol
)
gdp# A tsibble: 108 x 3 [1Q]
# Key: symbol [1]
symbol date price
<chr> <qtr> <dbl>
1 CLVMNACSCAB1GQDE 1997 Q1 543909.
2 CLVMNACSCAB1GQDE 1997 Q2 550950.
3 CLVMNACSCAB1GQDE 1997 Q3 552622.
4 CLVMNACSCAB1GQDE 1997 Q4 556805.
5 CLVMNACSCAB1GQDE 1998 Q1 561998.
6 CLVMNACSCAB1GQDE 1998 Q2 559628.
7 CLVMNACSCAB1GQDE 1998 Q3 562276.
8 CLVMNACSCAB1GQDE 1998 Q4 559976.
9 CLVMNACSCAB1GQDE 1999 Q1 566459.
10 CLVMNACSCAB1GQDE 1999 Q2 566459.
# ℹ 98 more rows
gdp_train <- gdp |>
filter_index(. ~ "2020 Q4")
gdp_train# A tsibble: 96 x 3 [1Q]
# Key: symbol [1]
symbol date price
<chr> <qtr> <dbl>
1 CLVMNACSCAB1GQDE 1997 Q1 543909.
2 CLVMNACSCAB1GQDE 1997 Q2 550950.
3 CLVMNACSCAB1GQDE 1997 Q3 552622.
4 CLVMNACSCAB1GQDE 1997 Q4 556805.
5 CLVMNACSCAB1GQDE 1998 Q1 561998.
6 CLVMNACSCAB1GQDE 1998 Q2 559628.
7 CLVMNACSCAB1GQDE 1998 Q3 562276.
8 CLVMNACSCAB1GQDE 1998 Q4 559976.
9 CLVMNACSCAB1GQDE 1999 Q1 566459.
10 CLVMNACSCAB1GQDE 1999 Q2 566459.
# ℹ 86 more rows
Gráfica
p <- gdp_train |>
autoplot(price) +
labs(
title = "Time series plot of the Real GDP for Germany",
y = "GDP"
)
ggplotly(p, dynamicTicks = TRUE) |>
rangeslider()Estacionalidad
Descomposición
gdp_train |>
model(stl = STL(price, robust = TRUE)) |>
components() |>
autoplot() |>
ggplotly()Transformación
Suavización exponencial
Modelo
gdp_fit <- gdp_train |>
model(
snaive = SNAIVE(log(price)),
naive = NAIVE(log(price)),
drift = RW(log(price) ~ drift()),
stlf = decomposition_model(
STL(log(price) ~ season(window = "periodic"), robust = TRUE),
RW(season_adjust ~ drift())
),
ets_ANA = ETS(log(price) ~ error("A") + trend("N") + season("A")),
ets_AAdA = ETS(log(price) ~ error("A") + trend("Ad") + season("A")),
ets_MAdM = ETS(log(price) ~ error("M") + trend("Ad") + season("M")),
)
gdp_fit |>
select(snaive) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the Seasonal Naïve Model")Warning: Removed 4 rows containing missing values (`geom_line()`).
Warning: Removed 4 rows containing missing values (`geom_point()`).
Warning: Removed 4 rows containing non-finite values (`stat_bin()`).
gdp_fit |>
select(naive) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the Naïve Model")Warning: Removed 1 row containing missing values (`geom_line()`).
Warning: Removed 1 rows containing missing values (`geom_point()`).
Warning: Removed 1 rows containing non-finite values (`stat_bin()`).
gdp_fit |>
select(drift) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the Drift Model")Warning: Removed 1 row containing missing values (`geom_line()`).
Warning: Removed 1 rows containing missing values (`geom_point()`).
Warning: Removed 1 rows containing non-finite values (`stat_bin()`).
gdp_fit |>
select(stlf) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the stlf Model")Warning: Removed 4 rows containing missing values (`geom_line()`).
Warning: Removed 4 rows containing missing values (`geom_point()`).
Warning: Removed 4 rows containing non-finite values (`stat_bin()`).
gdp_fit |>
select(ets_ANA) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the ets_ANA Model")gdp_fit |>
select(ets_AAdA) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the ets_AAdA Model")gdp_fit |>
select(ets_MAdM) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the ets_MAdM Model")P-value
# A tibble: 7 × 4
symbol .model lb_stat lb_pvalue
<chr> <chr> <dbl> <dbl>
1 CLVMNACSCAB1GQDE drift 8.45 0.999
2 CLVMNACSCAB1GQDE ets_AAdA 7.93 0.999
3 CLVMNACSCAB1GQDE ets_ANA 8.05 0.999
4 CLVMNACSCAB1GQDE ets_MAdM 8.24 0.999
5 CLVMNACSCAB1GQDE naive 8.45 0.999
6 CLVMNACSCAB1GQDE snaive 137. 0
7 CLVMNACSCAB1GQDE stlf 9.00 0.998
gdp_train_accu <- accuracy(gdp_fit) |>
arrange(MAPE)
gdp_train_accu |>
select(symbol:.type, MAPE, RMSE, MAE, MASE)# A tibble: 7 × 7
symbol .model .type MAPE RMSE MAE MASE
<chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 CLVMNACSCAB1GQDE drift Training 0.781 10862. 5113. 0.366
2 CLVMNACSCAB1GQDE stlf Training 0.816 11188. 5366. 0.384
3 CLVMNACSCAB1GQDE ets_MAdM Training 0.861 10487. 5635. 0.403
4 CLVMNACSCAB1GQDE ets_AAdA Training 0.864 10504. 5653. 0.404
5 CLVMNACSCAB1GQDE naive Training 0.868 11023. 5688. 0.407
6 CLVMNACSCAB1GQDE ets_ANA Training 0.946 10936. 6156. 0.440
7 CLVMNACSCAB1GQDE snaive Training 2.16 18331. 13986. 1
Entrenamiento de pronóstico
gdp_fc <- gdp_fit |>
forecast(h = 12)
gdp_fc# A fable: 84 x 5 [1Q]
# Key: symbol, .model [7]
symbol .model date price .mean
<chr> <chr> <qtr> <dist> <dbl>
1 CLVMNACSCAB1GQDE snaive 2021 Q1 t(N(14, 0.00079)) 736685.
2 CLVMNACSCAB1GQDE snaive 2021 Q2 t(N(13, 0.00079)) 668769.
3 CLVMNACSCAB1GQDE snaive 2021 Q3 t(N(13, 0.00079)) 728387.
4 CLVMNACSCAB1GQDE snaive 2021 Q4 t(N(14, 0.00079)) 734105.
5 CLVMNACSCAB1GQDE snaive 2022 Q1 t(N(14, 0.0016)) 736975.
6 CLVMNACSCAB1GQDE snaive 2022 Q2 t(N(13, 0.0016)) 669033.
7 CLVMNACSCAB1GQDE snaive 2022 Q3 t(N(13, 0.0016)) 728674.
8 CLVMNACSCAB1GQDE snaive 2022 Q4 t(N(14, 0.0016)) 734394.
9 CLVMNACSCAB1GQDE snaive 2023 Q1 t(N(14, 0.0024)) 737266.
10 CLVMNACSCAB1GQDE snaive 2023 Q2 t(N(13, 0.0024)) 669297.
# ℹ 74 more rows
gdp_fc |>
autoplot(gdp |> filter_index("2005 Q1" ~ .), size = 1) +
facet_wrap(~ .model, ncol = 3) +
theme(legend.position = "none")Error del pronóstico
# A tibble: 7 × 6
.model .type MAPE RMSE MAE MASE
<chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 stlf Test 0.701 6709. 5234. 0.374
2 drift Test 0.745 6607. 5559. 0.397
3 ets_AAdA Test 2.00 15563. 14984. 1.07
4 naive Test 2.03 15784. 15225. 1.09
5 ets_MAdM Test 2.04 15869. 15299. 1.09
6 ets_ANA Test 2.56 21360. 19184. 1.37
7 snaive Test 4.39 42755. 32859. 2.35
Pronóstico a futuro
gdp_fit_fut <- gdp_train |>
model(
stlf = decomposition_model(
STL(log(price) ~ season(window = "periodic"), robust = TRUE),
RW(season_adjust ~ drift())
)
)
gdp_fc_fut <- gdp_fit_fut |>
forecast(h = "3 years")
gdp_fc_fut |>
autoplot(gdp_train)El modelo que más de ajusta a los datos, y por ende se toma como pronóstico es el modelo stlf, el cuál combina una descomposición de tipo STL, con un modelo drift estacional. Aunque la serie de tiempo no muestra estacionalidad, el hecho de que modelo la incluya, ayuda a su ajuste, ya que la ondulación del pronóstico se asemeja más a el crecimeinto del PIB de cualquier país. Por otro lado el segundo modelo que mejor se ajusta, sorprendentemente, es el modelo drift. No fuimos capaces de encontrar un modelo de suavización exponencial que se ajustara mejor a los datos.
ARIMA
# A tibble: 1 × 2
symbol ndiffs
<chr> <int>
1 CLVMNACSCAB1GQDE 1
gdp_diff <- diff(gdp$price)
gdp_diff [1] 7040.2 1672.9 4182.3 5192.7 -2369.8 2648.6 -2300.1 6482.4
[9] 0.0 6273.1 4739.7 8242.6 4739.7 -278.8 -1742.6 11832.1
[17] -209.1 -1254.6 -557.6 -3066.9 2578.9 2927.5 -836.4 -8904.5
[25] 627.3 4530.7 1672.9 -1045.6 3066.9 -1254.6 -487.9 -52.5
[33] 3206.4 5088.5 2927.6 5907.2 10525.2 4809.5 9549.3 418.1
[41] 5436.9 3276.0 4182.2 4182.2 -1533.4 -4251.9 -10385.8 -30041.9
[49] 975.8 3415.4 4530.7 5001.6 14079.6 5297.3 5227.6 12564.2
[57] 627.3 5855.1 -2091.1 1463.7 1254.7 1951.7 -3136.7 -3014.4
[65] 7248.9 3694.2 1881.9 6639.4 139.4 3276.0 5576.2 -3485.1
[73] 5367.2 2718.3 3136.6 5924.8 3415.5 1394.0 2718.4 8573.5
[81] 6691.5 4600.4 6970.3 -4478.4 5994.3 -6900.4 6342.8 5088.4
[89] -278.8 -139.4 2230.5 -13244.0 -67889.1 59594.6 5715.5 -9339.5
[97] 16170.8 4948.8 69.7 7475.8 -975.9 2718.4 -3066.8 784.1
[105] 209.1 -69.7 -2160.8
gdp |>
gg_tsdisplay(log(price), plot_type = "partial")Modelo
gdp_fit <- gdp_train |>
model(
arima_010 = ARIMA(log(price) ~ pdq(1, 1, 0) + PDQ(0, 0, 0)),
arima_011 = ARIMA(log(price) ~ pdq(1, 1, 0) + PDQ(0, 0, 0)),
arima_012 = ARIMA(log(price) ~ pdq(1, 1, 0) + PDQ(0, 0, 0)),
arima_110 = ARIMA(log(price) ~ pdq(1, 1, 0) + PDQ(0, 0, 0)),
arima_111 = ARIMA(log(price) ~ pdq(1, 1, 1) + PDQ(0, 0, 0)),
arima_210 = ARIMA(log(price) ~ pdq(2, 1, 0) + PDQ(0, 0, 0)),
arima_212 = ARIMA(log(price) ~ pdq(2, 1, 2) + PDQ(0, 0, 0)),
arima_auto = ARIMA(log(price) ~ PDQ(0, 0, 0),
stepwise = FALSE, approximation = FALSE),
)
gdp_fit# A mable: 1 x 9
# Key: symbol [1]
symbol arima_010 arima_011 arima_012
<chr> <model> <model> <model>
1 CLVMN… <ARIMA(1,1,0) w/ drift> <ARIMA(1,1,0) w/ drift> <ARIMA(1,1,0) w/ drift>
# ℹ 5 more variables: arima_110 <model>, arima_111 <model>, arima_210 <model>,
# arima_212 <model>, arima_auto <model>
Series: price
Model: ARIMA(1,1,0) w/ drift
Transformation: log(price)
Coefficients:
ar1 constant
-0.1719 0.0037
s.e. 0.1008 0.0016
sigma^2 estimated as 0.0002518: log likelihood=260.17
AIC=-514.34 AICc=-514.08 BIC=-506.68
Series: price
Model: ARIMA(1,1,0) w/ drift
Transformation: log(price)
Coefficients:
ar1 constant
-0.1719 0.0037
s.e. 0.1008 0.0016
sigma^2 estimated as 0.0002518: log likelihood=260.17
AIC=-514.34 AICc=-514.08 BIC=-506.68
Series: price
Model: ARIMA(1,1,0) w/ drift
Transformation: log(price)
Coefficients:
ar1 constant
-0.1719 0.0037
s.e. 0.1008 0.0016
sigma^2 estimated as 0.0002518: log likelihood=260.17
AIC=-514.34 AICc=-514.08 BIC=-506.68
Series: price
Model: ARIMA(1,1,0) w/ drift
Transformation: log(price)
Coefficients:
ar1 constant
-0.1719 0.0037
s.e. 0.1008 0.0016
sigma^2 estimated as 0.0002518: log likelihood=260.17
AIC=-514.34 AICc=-514.08 BIC=-506.68
Series: price
Model: ARIMA(1,1,1)
Transformation: log(price)
Coefficients:
ar1 ma1
-0.0064 -0.1268
s.e. 0.5372 0.5307
sigma^2 estimated as 0.000265: log likelihood=257.74
AIC=-509.49 AICc=-509.23 BIC=-501.83
Series: price
Model: ARIMA(2,1,0) w/ drift
Transformation: log(price)
Coefficients:
ar1 ar2 constant
-0.1911 -0.0998 0.0039
s.e. 0.1031 0.1209 0.0016
sigma^2 estimated as 0.0002527: log likelihood=260.51
AIC=-513.02 AICc=-512.58 BIC=-502.81
Series: price
Model: ARIMA(2,1,2) w/ drift
Transformation: log(price)
Coefficients:
ar1 ar2 ma1 ma2 constant
-0.4824 -0.8125 0.2825 0.6340 0.0069
s.e. 0.4003 0.2205 0.4185 0.2744 0.0031
sigma^2 estimated as 0.0002526: log likelihood=261.39
AIC=-510.79 AICc=-509.83 BIC=-495.46
Series: price
Model: ARIMA(0,1,1) w/ drift
Transformation: log(price)
Coefficients:
ma1 constant
-0.1933 0.0031
s.e. 0.1053 0.0013
sigma^2 estimated as 0.0002509: log likelihood=260.35
AIC=-514.69 AICc=-514.43 BIC=-507.03
El modelo determinado automáticamente es un modelo ARIMA(0,1,1)
# A tibble: 8 × 9
symbol .model sigma2 log_lik AIC AICc BIC ar_roots ma_roots
<chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <list> <list>
1 CLVMNACSCAB1GQDE arima_au… 2.51e-4 260. -515. -514. -507. <cpl> <cpl>
2 CLVMNACSCAB1GQDE arima_010 2.52e-4 260. -514. -514. -507. <cpl> <cpl>
3 CLVMNACSCAB1GQDE arima_011 2.52e-4 260. -514. -514. -507. <cpl> <cpl>
4 CLVMNACSCAB1GQDE arima_012 2.52e-4 260. -514. -514. -507. <cpl> <cpl>
5 CLVMNACSCAB1GQDE arima_110 2.52e-4 260. -514. -514. -507. <cpl> <cpl>
6 CLVMNACSCAB1GQDE arima_210 2.53e-4 261. -513. -513. -503. <cpl> <cpl>
7 CLVMNACSCAB1GQDE arima_212 2.53e-4 261. -511. -510. -495. <cpl> <cpl>
8 CLVMNACSCAB1GQDE arima_111 2.65e-4 258. -509. -509. -502. <cpl> <cpl>
# A tibble: 8 × 11
symbol .model .type ME RMSE MAE MPE MAPE MASE RMSSE ACF1
<chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 CLVMNACSCA… arima… Trai… 55.0 10660. 5300. 0.00297 0.814 0.379 0.582 -0.0309
2 CLVMNACSCA… arima… Trai… 55.0 10660. 5300. 0.00297 0.814 0.379 0.582 -0.0309
3 CLVMNACSCA… arima… Trai… 55.0 10660. 5300. 0.00297 0.814 0.379 0.582 -0.0309
4 CLVMNACSCA… arima… Trai… 55.0 10660. 5300. 0.00297 0.814 0.379 0.582 -0.0309
5 CLVMNACSCA… arima… Trai… 56.3 10630. 5320. 0.00345 0.817 0.380 0.580 -0.0143
6 CLVMNACSCA… arima… Trai… 55.8 10597. 5348. 0.00404 0.823 0.382 0.578 -0.0198
7 CLVMNACSCA… arima… Trai… 43.8 10467. 5475. 0.00303 0.843 0.391 0.571 -0.0162
8 CLVMNACSCA… arima… Trai… 2345. 10876. 6006. 0.357 0.920 0.429 0.593 -0.0710
gdp_fit |>
select(arima_010) |>
gg_tsresiduals()gdp_fit |>
select(arima_011) |>
gg_tsresiduals()gdp_fit |>
select(arima_012) |>
gg_tsresiduals()gdp_fit |>
select(arima_110) |>
gg_tsresiduals()gdp_fit |>
select(arima_111) |>
gg_tsresiduals()gdp_fit |>
select(arima_210) |>
gg_tsresiduals()gdp_fit |>
select(arima_212) |>
gg_tsresiduals()gdp_fit |>
select(arima_auto) |>
gg_tsresiduals()P-value
gdp_fit |>
augment() |>
features(.innov, ljung_box, lag = 10) |>
mutate(residuos_autocorrelacionados = if_else(lb_pvalue >=0.05, "No autocorrelación", "Autocorrelacionados"))# A tibble: 8 × 5
symbol .model lb_stat lb_pvalue residuos_autocorrelacionados
<chr> <chr> <dbl> <dbl> <chr>
1 CLVMNACSCAB1GQDE arima_010 4.52 0.921 No autocorrelación
2 CLVMNACSCAB1GQDE arima_011 4.52 0.921 No autocorrelación
3 CLVMNACSCAB1GQDE arima_012 4.52 0.921 No autocorrelación
4 CLVMNACSCAB1GQDE arima_110 4.52 0.921 No autocorrelación
5 CLVMNACSCAB1GQDE arima_111 4.49 0.922 No autocorrelación
6 CLVMNACSCAB1GQDE arima_210 5.32 0.869 No autocorrelación
7 CLVMNACSCAB1GQDE arima_212 4.21 0.938 No autocorrelación
8 CLVMNACSCAB1GQDE arima_auto 4.87 0.900 No autocorrelación
Pronóstico a futuro
Produccion de ladrillos en Australia
Importar datos
bricks_production <- aus_production |>
select(Bricks)
bricks_production# A tsibble: 218 x 2 [1Q]
Bricks Quarter
<dbl> <qtr>
1 189 1956 Q1
2 204 1956 Q2
3 208 1956 Q3
4 197 1956 Q4
5 187 1957 Q1
6 214 1957 Q2
7 227 1957 Q3
8 222 1957 Q4
9 199 1958 Q1
10 229 1958 Q2
# ℹ 208 more rows
recent_production <- bricks_production %>% filter(year(Quarter) >= 1981)
bricks_train <- recent_production %>% filter(year(Quarter) <= 2003)
bricks_train# A tsibble: 92 x 2 [1Q]
Bricks Quarter
<dbl> <qtr>
1 519 1981 Q1
2 581 1981 Q2
3 581 1981 Q3
4 578 1981 Q4
5 501 1982 Q1
6 560 1982 Q2
7 512 1982 Q3
8 412 1982 Q4
9 303 1983 Q1
10 409 1983 Q2
# ℹ 82 more rows
Gráfica
p <- bricks_train |>
autoplot(Bricks)
ggplotly(p, dynamicTicks = TRUE) |>
rangeslider()Estacionalidad
##Descomposición
bricks_train |>
model(stl = STL(Bricks, robust = TRUE)) |>
components() |>
autoplot() |>
ggplotly()Modelo
bricks_fit <- bricks_train |>
model(
snaive = SNAIVE(Bricks),
naive = NAIVE(Bricks),
drift = RW(Bricks ~ drift()),
stlf = decomposition_model(
STL(Bricks ~ season(window = "periodic"), robust = TRUE),
RW(season_adjust ~ drift())
),
ets_ANA = ETS(Bricks ~ error("A") + trend("N") + season("A")),
ets_AAdA = ETS(Bricks ~ error("A") + trend("Ad") + season("A")),
ets_MAdM = ETS(Bricks ~ error("M") + trend("Ad") + season("M")),
stl_ets_A = decomposition_model(
STL(Bricks, robust=TRUE),
ETS(season_year ~ error("A") + trend("N") + season("A")),
ETS(season_adjust ~ error("A") + trend("Ad") + season("N"))
),
stl_ets_M = decomposition_model(
STL(Bricks, robust=TRUE),
ETS(season_year ~ error("M") + trend("N") + season("M")),
ETS(season_adjust ~ error("A") + trend("Ad") + season("N"))
)
)
bricks_fit |>
select(snaive) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the Seasonal Naïve Model")Warning: Removed 4 rows containing missing values (`geom_line()`).
Warning: Removed 4 rows containing missing values (`geom_point()`).
Warning: Removed 4 rows containing non-finite values (`stat_bin()`).
bricks_fit |>
select(drift) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the Drift Model")Warning: Removed 1 row containing missing values (`geom_line()`).
Warning: Removed 1 rows containing missing values (`geom_point()`).
Warning: Removed 1 rows containing non-finite values (`stat_bin()`).
bricks_fit |>
select(stlf) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the stlf Model")Warning: Removed 4 rows containing missing values (`geom_line()`).
Warning: Removed 4 rows containing missing values (`geom_point()`).
Warning: Removed 4 rows containing non-finite values (`stat_bin()`).
bricks_fit |>
select(ets_ANA) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the ets_ANA Model")bricks_fit |>
select(ets_AAdA) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the ets_AAdA Model")bricks_fit |>
select(ets_MAdM) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the ets_MAdM Model")bricks_fit |>
select(stl_ets_A) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the stl_ets_A Model")bricks_fit |>
select(stl_ets_M) |>
gg_tsresiduals() +
ggtitle("Residuals Diagnostics for the stl_ets_M Model")P-value
# A tibble: 9 × 3
.model lb_stat lb_pvalue
<chr> <dbl> <dbl>
1 drift 366. 0
2 ets_AAdA 25.5 0.381
3 ets_ANA 33.7 0.0903
4 ets_MAdM 22.5 0.550
5 naive 366. 0
6 snaive 205. 0
7 stl_ets_A 21.0 0.637
8 stl_ets_M 29.7 0.194
9 stlf 31.1 0.151
bricks_train_accu <- accuracy(bricks_fit) |>
arrange(MAPE)
bricks_train_accu |>
select(.model, .type, MAPE, RMSE, MAE, MASE)# A tibble: 9 × 6
.model .type MAPE RMSE MAE MASE
<chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 stl_ets_A Training 3.98 22.8 17.1 0.395
2 ets_ANA Training 4.35 24.4 18.4 0.426
3 ets_AAdA Training 4.36 24.3 18.5 0.428
4 stlf Training 4.48 24.0 18.8 0.433
5 ets_MAdM Training 4.50 25.0 19.3 0.445
6 drift Training 8.74 44.6 37.1 0.856
7 naive Training 8.76 44.6 37.1 0.856
8 stl_ets_M Training 8.92 176. 44.2 1.02
9 snaive Training 10.5 57.7 43.3 1
Entrenamiento de pronóstico
bricks_fc <- bricks_fit |>
forecast(h = 6)
bricks_fc# A fable: 54 x 4 [1Q]
# Key: .model [9]
.model Quarter Bricks .mean
<chr> <qtr> <dist> <dbl>
1 snaive 2004 Q1 N(387, 3334) 387
2 snaive 2004 Q2 N(415, 3334) 415
3 snaive 2004 Q3 N(440, 3334) 440
4 snaive 2004 Q4 N(413, 3334) 413
5 snaive 2005 Q1 N(387, 6667) 387
6 snaive 2005 Q2 N(415, 6667) 415
7 naive 2004 Q1 N(413, 1987) 413
8 naive 2004 Q2 N(413, 3973) 413
9 naive 2004 Q3 N(413, 5960) 413
10 naive 2004 Q4 N(413, 7946) 413
# ℹ 44 more rows
bricks_fc |>
autoplot(bricks_production |> filter_index("1990 Q1" ~ .), size = 1) +
facet_wrap(~ .model, ncol = 3) +
theme(legend.position = "none")Warning: Removed 20 rows containing missing values (`geom_line()`).
Error del pronóstico
bricks_fc |>
accuracy(bricks_production) |>
select(.model:.type, MAPE, RMSE, MAE, MASE) |>
arrange(MAPE)# A tibble: 9 × 6
.model .type MAPE RMSE MAE MASE
<chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 stlf Test 3.10 19.0 12.7 0.352
2 ets_ANA Test 3.71 19.4 14.9 0.415
3 ets_AAdA Test 3.77 19.0 15.1 0.420
4 ets_MAdM Test 3.93 19.3 15.7 0.437
5 stl_ets_M Test 4.30 21.3 17.5 0.488
6 stl_ets_A Test 4.30 21.3 17.6 0.488
7 snaive Test 4.62 19.9 18.3 0.510
8 drift Test 5.36 26.4 21.0 0.585
9 naive Test 5.38 27.2 20.8 0.579
Pronóstico a futuro
bricks_fit_fut <- bricks_train |>
model(
stlf = decomposition_model(
STL(Bricks ~ season(window = "periodic"), robust = TRUE),
RW(season_adjust ~ drift())
)
)
bricks_fc_fut <- bricks_fit_fut |>
forecast(h = "5 years")
bricks_fc_fut |>
autoplot(bricks_train)El modelo que presentó un menor error en el ajuste del pronóstico es el stlf, el cual mezcal una descomposición tipo STL con un modelo drift estacional. Caso contrario con la serie de tiempo pasada, esta si muestra estacionalidad de manera anual, por lo que hace sentido que el modelo se ajuste de mejor manera, ya que respeta la estacionalidad que se presenta en los datos de entramiento, y muestra la tendencia bajista, presentada en los últimos 20 años. El segundo modelo que mejor se ajusta es uno de suavización exponencial con error aditivo, sin tendencia y con una estacionalidad aditiva.