# Access a model specification, a SA or a pre-adjustment model in X13 and TRAMO-SEATS The following functions enable the access to different parts of the final model specification, as included in the `"SA", "regarima", "SA_spec"` and `"regarima_spec"` S3 class objects. ```r s_estimate(object = NA) s_transform(object = NA) s_usrdef(object = NA) s_preOut(object = NA) s_preVar(object = NA) s_td(object = NA) s_easter(object = NA) s_out(object = NA) s_arima(object = NA) s_arimaCoef(object = NA) s_fcst(object = NA) s_span(object = NA) s_x11(object = NA) s_benchmarking(object = NA) s_seats(object = NA) ``` ## Arguments - `object`: an object of one of the following classes: `c("SA","X13")`, `c("SA","TRAMO_SEATS")`, `c("SA_spec","X13")`, `c("SA_spec","TRAMO_SEATS")`, `c("regarima","X13")`, `c("regarima","TRAMO_SEATS")`, `c("regarima_spec","X13")`, `c("regarima_spec","TRAMO_SEATS")`. ## Returns * `s_estimate` returns a data.frame with the **estimate** variables * `s_transform` returns a data.frame with the **transform** variables * `s_usrdef` returns a data.frame with the **user-defined regressors** (outliers and variables) model specification, indicating if those variables are included in the model and if coefficients are pre-specified * `s_preOut` returns a data.frame with the **pre-specified outliers** * `s_preVar` returns a list with information on the user-defined variables, including: `series` - the time series and `description` - data.frame with the variable type and coefficients * `s_td` returns a data.frame with the **trading.days** variables * `s_easter` returns a data.frame with the **easter** variable * `s_out` returns a data.frame with the **outliers** detection variables * `s_arima` returns a data.frame with the **arima** variables * `s_arimaCoef` returns a data.frame with the user-specified ARMA coefficients * `s_fcst` returns a data.frame with the forecast horizon * `s_span` returns a data.frame with the **span** variables * `s_x11` returns a data.frame with the **x11** variables * `s_seats` returns a data.frame with the **seats** variables ## Examples ```r myseries <- ipi_c_eu[, "FR"] myreg1 <- regarima_x13(myseries, spec = "RG5c") myspec1 <- regarima_spec_x13(myreg1, estimate.from = "2005-10-01", outlier.from = "2010-03-01") s_estimate(myreg1) s_estimate(myspec1) s_transform(myreg1) s_transform(myspec1) s_usrdef(myreg1) s_usrdef(myspec1) myspec2 <- regarima_spec_x13(myreg1, usrdef.outliersEnabled = TRUE, usrdef.outliersType = c("LS", "AO"), usrdef.outliersDate = c("2009-10-01", "2005-02-01")) myreg2 <- regarima(myseries, myspec2) s_preOut(myreg2) s_preOut(myspec2) var1 <- ts(rnorm(length(myseries))*10, start = start(myseries), frequency = 12) var2 <- ts(rnorm(length(myseries))*100, start = start(myseries), frequency = 12) var3 <- ts.union(var1, var2) myspec3 <- regarima_spec_x13(spec = "RG5c", usrdef.varEnabled = TRUE, usrdef.var = var3) myreg3 <- regarima(myseries, myspec3) s_preVar(myspec3) s_preVar(myreg3) s_td(myreg1) s_td(myspec1) s_easter(myreg1) s_easter(myspec1) s_out(myreg1) s_out(myspec1) s_arima(myreg1) s_arima(myspec1) myspec4 <- regarima_spec_x13(myreg1, automdl.enabled = FALSE, arima.coefEnabled = TRUE, arima.p = 1,arima.q = 1, arima.bp = 1, arima.bq = 1, arima.coef = rep(0.2, 4), arima.coefType = rep("Initial", 4)) myreg4 <- regarima(myseries, myspec4) s_arimaCoef(myreg4) s_arimaCoef(myspec4) s_fcst(myreg1) s_fcst(myspec1) s_span(myreg1) s_span(myspec1) myspec5 <- x13_spec(spec = "RSA5c", x11.seasonalComp = FALSE) mysa5 <- x13(myseries, myspec5) s_x11(mysa5) s_x11(myspec5) myspec6 <- tramoseats_spec(spec = "RSAfull", seats.approx = "Noisy") mysa6 <- tramoseats(myseries, myspec6) s_seats(mysa6) s_seats(mysa6) ``` ## References More information and examples related to 'JDemetra+' features in the online documentation: [https://jdemetra-new-documentation.netlify.app/](https://jdemetra-new-documentation.netlify.app/)

specification function