library(tidyverse)
library(fpp3)
library(patchwork)Ejercicio SARIMA
Ejercicio SARIMA
h02 <- PBS |>
filter(ATC2 == "H02") |>
summarise(Cost = sum(Cost)/1e6)
h02# A tsibble: 204 x 2 [1M]
Month Cost
<mth> <dbl>
1 1991 jul. 0.430
2 1991 ago. 0.401
3 1991 sep. 0.432
4 1991 oct. 0.493
5 1991 nov. 0.502
6 1991 dic. 0.603
7 1992 ene. 0.660
8 1992 feb. 0.336
9 1992 mar. 0.351
10 1992 abr. 0.380
# ℹ 194 more rows
h02 |>
mutate(log(Cost)) |>
gather() |>
ggplot(aes(x = Month, y = value)) +
geom_line() +
facet_grid(key ~ ., scales = "free_y") +
xlab("Year") + ylab("") +
ggtitle("Cortecosteroid drug scripts (H02)")Training
h02_train <- h02 |>
filter_index(.~'2006 December')h02_train %>% gg_tsdisplay(log(Cost) %>% difference(12) %>% difference, plot_type='partial', lag_max = 48)Warning: Removed 13 rows containing missing values (`geom_line()`).
Warning: Removed 13 rows containing missing values (`geom_point()`).
h02_fit <- h02_train |>
model(
arima_211_111 = ARIMA(log(Cost) ~ pdq(2,1,1) + PDQ(1,1,1)),
arima_311_210 = ARIMA(log(Cost) ~ pdq(3,1,1) + PDQ(2,1,0)),
arima_210_311 = ARIMA(log(Cost) ~ pdq(2,1,2) + PDQ(3,1,1)+1),
arima_110_312 = ARIMA(log(Cost) ~ pdq(1,1,0) + PDQ(3,1,2)),
arima_112_112 = ARIMA(log(Cost) ~ pdq(1,1,2) + PDQ(1,1,2)),
arima_213_110 = ARIMA(log(Cost) ~ pdq(2,1,1) + PDQ(1,1,0)),
arima_212_212 = ARIMA(log(Cost) ~ pdq(2,1,1) + PDQ(2,1,2)+1)
)Warning: Model specification induces a quadratic or higher order polynomial trend.
This is generally discouraged, consider removing the constant or reducing the number of differences.
Model specification induces a quadratic or higher order polynomial trend.
This is generally discouraged, consider removing the constant or reducing the number of differences.
h02_fit# A mable: 1 x 7
arima_211_111 arima_311_210
<model> <model>
1 <ARIMA(2,1,1)(1,1,1)[12]> <ARIMA(3,1,1)(2,1,0)[12]>
# ℹ 5 more variables: arima_210_311 <model>, arima_110_312 <model>,
# arima_112_112 <model>, arima_213_110 <model>, arima_212_212 <model>
h02_fit |>
glance() |>
arrange(AICc)# A tibble: 7 × 8
.model sigma2 log_lik AIC AICc BIC ar_roots ma_roots
<chr> <dbl> <dbl> <dbl> <dbl> <dbl> <list> <list>
1 arima_212_212 0.00339 245. -473. -472. -444. <cpl [26]> <cpl [25]>
2 arima_211_111 0.00361 240. -469. -468. -450. <cpl [14]> <cpl [13]>
3 arima_210_311 0.00350 244. -468. -467. -437. <cpl [38]> <cpl [14]>
4 arima_112_112 0.00369 239. -464. -463. -442. <cpl [13]> <cpl [26]>
5 arima_311_210 0.00375 238. -463. -462. -441. <cpl [27]> <cpl [1]>
6 arima_110_312 0.00357 237. -461. -460. -439. <cpl [37]> <cpl [24]>
7 arima_213_110 0.00418 229. -449. -449. -433. <cpl [14]> <cpl [1]>
h02_accu_train <- accuracy(h02_fit) |>
arrange(MAPE)
h02_accu_train# A tibble: 7 × 10
.model .type ME RMSE MAE MPE MAPE MASE RMSSE ACF1
<chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 arima_212_212 Traini… -5.14e-4 0.0447 0.0330 -0.137 4.20 0.551 0.620 -0.0388
2 arima_210_311 Traini… -1.03e-3 0.0454 0.0335 -0.167 4.28 0.560 0.630 -0.0284
3 arima_110_312 Traini… -2.77e-3 0.0473 0.0341 -0.395 4.32 0.570 0.656 -0.185
4 arima_211_111 Traini… -4.02e-3 0.0465 0.0341 -0.528 4.36 0.569 0.645 -0.0448
5 arima_311_210 Traini… -4.94e-3 0.0471 0.0340 -0.757 4.37 0.568 0.654 -0.00568
6 arima_112_112 Traini… -4.32e-3 0.0476 0.0348 -0.575 4.44 0.582 0.661 -0.0494
7 arima_213_110 Traini… -2.28e-3 0.0499 0.0361 -0.413 4.63 0.602 0.693 -0.0758
h02_fit |>
select( arima_212_212) |>
gg_tsresiduals()h02_fit |>
select(arima_211_111) |>
gg_tsresiduals()h02_fit|>
select(arima_210_311) |>
gg_tsresiduals()h02_fit |>
augment() |>
features(.innov, ljung_box, lag = 10) |>
mutate(residuos_autocorrelacionados = if_else(lb_pvalue >=0.05, "No autocorrelación", "Autocorrelacionados"))# A tibble: 7 × 4
.model lb_stat lb_pvalue residuos_autocorrelacionados
<chr> <dbl> <dbl> <chr>
1 arima_110_312 24.2 0.00716 Autocorrelacionados
2 arima_112_112 20.4 0.0260 Autocorrelacionados
3 arima_210_311 9.80 0.459 No autocorrelación
4 arima_211_111 11.8 0.296 No autocorrelación
5 arima_212_212 8.19 0.611 No autocorrelación
6 arima_213_110 13.3 0.207 No autocorrelación
7 arima_311_210 12.2 0.270 No autocorrelación
Test
h02_fc <- h02_fit |>
forecast(h='24 months')
h02_fc# A fable: 168 x 4 [1M]
# Key: .model [7]
.model Month Cost .mean
<chr> <mth> <dist> <dbl>
1 arima_211_111 2007 ene. t(N(0.2, 0.0036)) 1.22
2 arima_211_111 2007 feb. t(N(-0.54, 0.0038)) 0.585
3 arima_211_111 2007 mar. t(N(-0.37, 0.0048)) 0.696
4 arima_211_111 2007 abr. t(N(-0.4, 0.0062)) 0.669
5 arima_211_111 2007 may. t(N(-0.27, 0.0067)) 0.768
6 arima_211_111 2007 jun. t(N(-0.22, 0.0079)) 0.808
7 arima_211_111 2007 jul. t(N(-0.11, 0.0088)) 0.901
8 arima_211_111 2007 ago. t(N(0.001, 0.0096)) 1.01
9 arima_211_111 2007 sep. t(N(0.021, 0.011)) 1.03
10 arima_211_111 2007 oct. t(N(0.11, 0.012)) 1.13
# ℹ 158 more rows
h02_fc |>
autoplot(h02 |> filter_index('2000 January' ~.), level= NULL, size=1)h02_fc |>
autoplot(h02 |> filter_index('2000 January' ~.), size=1)+
facet_wrap(~ .model, ncol= 3)+
theme(legend.position = 'none')h02_fc |>
accuracy(h02) |>
arrange(MAPE)Warning: The future dataset is incomplete, incomplete out-of-sample data will be treated as missing.
6 observations are missing between 2008 jul. and 2008 dic.
# A tibble: 7 × 10
.model .type ME RMSE MAE MPE MAPE MASE RMSSE ACF1
<chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 arima_311_210 Test 0.00781 0.0678 0.0492 0.374 6.24 0.822 0.940 -0.111
2 arima_211_111 Test 0.0241 0.0691 0.0529 2.10 6.51 0.883 0.959 -0.141
3 arima_112_112 Test 0.0169 0.0675 0.0537 1.16 6.57 0.896 0.936 -0.0957
4 arima_212_212 Test 0.0145 0.0684 0.0537 1.04 6.57 0.896 0.949 -0.0582
5 arima_210_311 Test 0.0234 0.0709 0.0564 1.92 6.80 0.942 0.983 -0.0367
6 arima_110_312 Test 0.0224 0.0686 0.0572 1.87 6.83 0.955 0.951 -0.0588
7 arima_213_110 Test 0.0491 0.0857 0.0632 5.20 7.48 1.06 1.19 -0.196
Pronóstico a futuro
h02_fut<- h02 |>
model(
arima_311_210 = ARIMA(log(Cost) ~ pdq(2,0,1) + PDQ(1,1,0))
) |>
forecast(h= '24 months')
h02_fut# A fable: 24 x 4 [1M]
# Key: .model [1]
.model Month Cost .mean
<chr> <mth> <dist> <dbl>
1 arima_311_210 2008 jul. t(N(0.026, 0.0051)) 1.03
2 arima_311_210 2008 ago. t(N(0.11, 0.0051)) 1.12
3 arima_311_210 2008 sep. t(N(0.13, 0.0057)) 1.14
4 arima_311_210 2008 oct. t(N(0.18, 0.006)) 1.20
5 arima_311_210 2008 nov. t(N(0.19, 0.0064)) 1.22
6 arima_311_210 2008 dic. t(N(0.21, 0.0067)) 1.23
7 arima_311_210 2009 ene. t(N(0.26, 0.0069)) 1.30
8 arima_311_210 2009 feb. t(N(-0.29, 0.0072)) 0.749
9 arima_311_210 2009 mar. t(N(-0.34, 0.0074)) 0.712
10 arima_311_210 2009 abr. t(N(-0.26, 0.0076)) 0.776
# ℹ 14 more rows
h02_fut |>
autoplot(h02)