Package 'ardl.nardl' reference manual

Title:	Linear and Nonlinear Autoregressive Distributed Lag Models: General-to-Specific Approach
Description:	Estimate the linear and nonlinear autoregressive distributed lag (ARDL & NARDL) models and the corresponding error correction models, and test for longrun and short-run asymmetric. The general-to-specific approach is also available in estimating the ARDL and NARDL models. The Pesaran, Shin & Smith (2001) (<doi:10.1002/jae.616>) bounds test for level relationships is also provided. The 'ardl.nardl' package also performs short-run and longrun symmetric restrictions available at Shin et al. (2014) <doi:10.1007/978-1-4899-8008-3_9> and their corresponding tests.
Authors:	Eric I. Otoakhia [aut, cre]
Maintainer:	Eric I. Otoakhia <[email protected]>
License:	GPL (>= 2)
Version:	1.3.0
Built:	2025-03-26 03:18:14 UTC
Source:	https://github.com/cran/ardl.nardl

Linear and Nonlinear Autoregressive Distributed Lag Models: General-to-Specific Approach

Description

Estimate the linear and nonlinear autoregressive distributed lag (ARDL & NARDL) models and the corresponding error correction models, and test for longrun and short-run asymmetric. The Pesaran, Shin & Smith (2001) Bounds test for level relationships is also provided with the aid of Jordan and Philips (2020) pssbounds function. In addition, the 'ardl.nardl' package also performs short-run and longrun symmetric restrictions available at Shin et al. (2014) and their corresponding tests.

References

Jordan S, Philips A (2020). _dynamac: Dynamic Simulation and Testing for Single-Equation ARDL Models_. R package version 0.1.11

Pesaran, M. H., Shin, Y., & Smith, R. J. (2001). Bounds testing approaches to the analysis of level relationships. Journal of applied econometrics, 16(3), 289-326. https://doi.org/10.1002/jae.616

Shin, Y., Yu, B., & Greenwood-Nimmo, M. (2014). Modelling Asymmetric Cointegration and Dynamic Multipliers in a Nonlinear ARDL Framework. In: Sickles, R., Horrace, W. (eds) Festschrift in Honor of Peter Schmidt. Springer, New York, NY. https://doi.org/10.1007/978-1-4899-8008-3_9

Examples

## Not run: 
data(fuel_price)
data(expectation)
 out1 <- gets_ardl_uecm(x = expectation,
                        dep_var = c('nq_inf_exp'), 
                        expl_var = c('food_inf','nethawkish'),
                        p_order = c(4), 
                        q_order = c(5,7),
                        gets_pval = 0.1, 
                        case = 4, 
                        graph_save = FALSE,
                        F_HC = FALSE,
                        order_l = 7)
 out1 

 out2 <- gets_nardl_uecm(x = expectation,
                         decomp = 'food_inf',
                         dep_var = 'nq_inf_exp',
                         control = 'nethawkish',
                         c_q_order = c(3),
                         p_order = c(3),
                         q_order = c(3),
                        gets_pval = 0.1,
                         graph_save = FALSE,
                         case = 5, 
                         F_HC = FALSE)
 out2

OUT3 <- auto_case_ardl(x = expectation,
               dep_var = 'n12m_inf_exp', 
               expl_var = c('food_inf',"hawkish","dovish"),
               p_order = 2,
               q_order = c(4,4,4),
               gets_pval = 0.05,
               graph_save = FALSE, 
               order_l = 7)
OUT3 
               
OUT4 <- nardl_auto_case(x = fuel_price,
                      decomp =  'wti',
                      dep_var = 'fpp',
                      control = 'bdc',
                      c_q_order = c(5), 
                      p_order = c(5),
                      q_order = c(6),
                      gets_pval = 0.1,
                      order_l = 4,
                      graph_save = FALSE)
OUT4

uecm_case3 <- ardl_uecm(x = fuel_price,
                            dep_var = c('fpp'),
                            expl_var = c('bdc', 'wti'),
                            p_order =c(6),
                            q_order =c(5,3),
                            graph_save = FALSE,
                            case = 3)
uecm_case3

output_n1_case5 <- nardl_uecm(x = fuel_price,
                                 decomp  = c('bdc'), 
                                 control =c('wti'),
                                 c_q_order = c(2), 
                                 p_order = c(3), 
                                 q_order = c(5), 
                                 dep_var = c('fpp'), 
                                 graph_save = FALSE, 
                                 case = 5)
output_n1_case5

data(syg_data)
out_srsr <- nardl_uecm_sym(x = syg_data,
             decomp  = 'ca_u', 
             assumption = c('SRSR'),
             control =NULL,
             p_order =5,
             q_order =3,
             dep_var = 'ca_ip',
             graph_save = FALSE, 
             case = 3)
out_srsr

out_lrsr <- nardl_uecm_sym(x = syg_data,
                           decomp  = 'ca_u', 
                           assumption = c('LRSR'),
                           control =NULL,
                           p_order =5,
                           q_order =3,
                           dep_var = 'ca_ip',
                           graph_save = FALSE, 
                           case = 3)
out_lrsr

## End(Not run)
## Not run: 
data(fuel_price)
data(expectation)
 out1 <- gets_ardl_uecm(x = expectation,
                        dep_var = c('nq_inf_exp'), 
                        expl_var = c('food_inf','nethawkish'),
                        p_order = c(4), 
                        q_order = c(5,7),
                        gets_pval = 0.1, 
                        case = 4, 
                        graph_save = FALSE,
                        F_HC = FALSE,
                        order_l = 7)
 out1 

 out2 <- gets_nardl_uecm(x = expectation,
                         decomp = 'food_inf',
                         dep_var = 'nq_inf_exp',
                         control = 'nethawkish',
                         c_q_order = c(3),
                         p_order = c(3),
                         q_order = c(3),
                        gets_pval = 0.1,
                         graph_save = FALSE,
                         case = 5, 
                         F_HC = FALSE)
 out2

OUT3 <- auto_case_ardl(x = expectation,
               dep_var = 'n12m_inf_exp', 
               expl_var = c('food_inf',"hawkish","dovish"),
               p_order = 2,
               q_order = c(4,4,4),
               gets_pval = 0.05,
               graph_save = FALSE, 
               order_l = 7)
OUT3 
               
OUT4 <- nardl_auto_case(x = fuel_price,
                      decomp =  'wti',
                      dep_var = 'fpp',
                      control = 'bdc',
                      c_q_order = c(5), 
                      p_order = c(5),
                      q_order = c(6),
                      gets_pval = 0.1,
                      order_l = 4,
                      graph_save = FALSE)
OUT4

uecm_case3 <- ardl_uecm(x = fuel_price,
                            dep_var = c('fpp'),
                            expl_var = c('bdc', 'wti'),
                            p_order =c(6),
                            q_order =c(5,3),
                            graph_save = FALSE,
                            case = 3)
uecm_case3

output_n1_case5 <- nardl_uecm(x = fuel_price,
                                 decomp  = c('bdc'), 
                                 control =c('wti'),
                                 c_q_order = c(2), 
                                 p_order = c(3), 
                                 q_order = c(5), 
                                 dep_var = c('fpp'), 
                                 graph_save = FALSE, 
                                 case = 5)
output_n1_case5

data(syg_data)
out_srsr <- nardl_uecm_sym(x = syg_data,
             decomp  = 'ca_u', 
             assumption = c('SRSR'),
             control =NULL,
             p_order =5,
             q_order =3,
             dep_var = 'ca_ip',
             graph_save = FALSE, 
             case = 3)
out_srsr

out_lrsr <- nardl_uecm_sym(x = syg_data,
                           decomp  = 'ca_u', 
                           assumption = c('LRSR'),
                           control =NULL,
                           p_order =5,
                           q_order =3,
                           dep_var = 'ca_ip',
                           graph_save = FALSE, 
                           case = 3)
out_lrsr

## End(Not run)

Import from package nardl

Description

The ArchTest object is imported from package nardl. Help is available here: nardl::ArchTest.

Estimate the ARDL and ARDL Error Correction Model.

Description

Estimate ARDL and ARDL error correction model, conduct the bounds test for cointegration

Usage

ardl_uecm(x, p_order = c(2), q_order, dep_var, order_l = 4, 
    graph_save = FALSE, expl_var, case = 3)
ardl_uecm(x, p_order = c(2), q_order, dep_var, order_l = 4, 
    graph_save = FALSE, expl_var, case = 3)

Arguments

`x`	A dataframe object. S3 dataframe object not applicable.
`p_order`	is the lag for the dependent variable (dep_var). Default value is c(2)
`q_order`	A numeric vector containing the lags for each explanatory variable. A vector of two lags (i.e c(3,4)) which corresponds to the expl_var (say c('x1','x2') where x1 has lag of 3 and x2 has lag of 4).
`dep_var`	Character vector containing one dependent variable
`order_l`	Positive integer. lag for the order of serial correlation and ARCH test.
`graph_save`	Logical (default is FALSE). If TRUE, stability plot is displayed as well.
`expl_var`	Character vector containing the explanatory variable(s).
`case`	A numerical vector that can take a value between 1 to 5. The default value is 3.

Value

`ARDL_fit`	This display the ARDL lm fit
`ARDL_ECM_fit`	This display the ARDL ECM lm fit
`UECM`	This display the summary results of the estimated unrestricted error correction models
`UECM`	This display the summary results of the estimated linear unrestricted error correction models
`cointegration`	This presents the Pesaran, Shin, and Smith (2001) cointegration test. The critical F and t statistics obtained if the sample is greater than 80 are asymptotic. If you adopt this segment, please consider citing Pesaran et al (2001) and Jordan and Philips (2020) dynamac package. If the sample is less than or equal to 80, for case 1, the F and t statistics adopted are large sample asymptotic critical value (CV) and no small-sample asymptotic critical value available. When case = 3 or 5, the critical value of F statistic is small sample asymptotic, and the adopted t statistics are large sample asymptotic CV. Consider including Narayan (2005) in your citation list. If the sample is greater than 80, for case 1, 3 and 5, large sample asymptotic CV for F and t statistics are adopted. In case 2 and 4, for sample <= 80, the F statistic are small sample asymptotic and no asymptotic CV for the t statistic. If sample > 80, for case 2 and 4, large sample asymptotic CV for F is adopted and no t-statistic CV.
`Longrun_relation`	The estimated longrun relations
`diagnostics test`	The diagnostic tests indicate the Breusch-Godfrey test for higher-order serial correlation (BG_SC_lm_test). The Engle (1982) test for conditional heteroscedasticity (LM_ARCH_test). The test for non-normality is that of Jarque and Bera (1980). The RESET null hypothesis adopted implies - including the 2nd - degree terms improve the fit (over the model specified). This ARCH LM function is derived from Zaghdoudi (2018)

References

Jordan S, Philips A (2020). _dynamac: Dynamic Simulation and Testing for Single-Equation /n ARDL Models_. R package version 0.1.11

Narayan, P. K. (2005). The saving and investment nexus for China: evidence from cointegration tests. Applied economics, 37(17), 1979-1990.

Pesaran, M. H., Shin, Y., & Smith, R. J. (2001). Bounds testing approaches to the analysis of level relationships. Journal of applied econometrics, 16(3), 289-326.

Zaghdoudi, T. (2018). nardl: Nonlinear Cointegrating Autoregressive Distributed Lag Model_. R package version 0.1.5

Examples

data(fuel_price)
uecm_case3 <- ardl_uecm(x = fuel_price,
                        p_order =c(6),
                        q_order =c(5,3),
                        dep_var = c('fpp'),
                        expl_var = c('bdc', 'wti'),
                        graph_save = FALSE,
                        case = 3)
uecm_case3
uecm_case3$cointegration
uecm_case3$Longrun_relation
uecm_case3$`diagnostics test`

uecm_case2 <- ardl_uecm(x = fuel_price,
                        p_order =c(3),
                        q_order =c(4),
                        dep_var = c('fpp'),
                        expl_var = c('wti'),
                        graph_save = TRUE,
                        case = 2)
uecm_case2
uecm_case2$cointegration
uecm_case2$Longrun_relation
uecm_case2$`diagnostics test`
data(fuel_price)
uecm_case3 <- ardl_uecm(x = fuel_price,
                        p_order =c(6),
                        q_order =c(5,3),
                        dep_var = c('fpp'),
                        expl_var = c('bdc', 'wti'),
                        graph_save = FALSE,
                        case = 3)
uecm_case3
uecm_case3$cointegration
uecm_case3$Longrun_relation
uecm_case3$`diagnostics test`

uecm_case2 <- ardl_uecm(x = fuel_price,
                        p_order =c(3),
                        q_order =c(4),
                        dep_var = c('fpp'),
                        expl_var = c('wti'),
                        graph_save = TRUE,
                        case = 2)
uecm_case2
uecm_case2$cointegration
uecm_case2$Longrun_relation
uecm_case2$`diagnostics test`

Obtain the best ARDL model specification and bounds test.

Description

This function finds the best ARDL model specification and conduct bounds test by relying on the general to specific approach.

Usage

auto_case_ardl(x, dep_var, expl_var, p_order, q_order, 
gets_pval = 0.05, order_l = 3, graph_save = FALSE)
auto_case_ardl(x, dep_var, expl_var, p_order, q_order, 
gets_pval = 0.05, order_l = 3, graph_save = FALSE)

Arguments

`x`	Dataframe.
`dep_var`	A Character vector that contain the response variable.
`expl_var`	Character vector containing the list of explanatory variable(s).
`p_order`	An integer. Lag differenced adopted for the differenced response variable
`q_order`	An integer. Lag differenced adopted for the differenced explanatory variable(s)
`gets_pval`	The p- value which served as the criteria for eliminating non-significant variable in the course of obtaining the best model based on the Schwarz information criteria.
`order_l`	Integer. Needed for the autocorrelation and heteroscedasticity test
`graph_save`	Logical. If TRUE, displays the stability plots

Details

The procedure of the general-to-specific approach in obtaining the parsimonious model involves conducting the multi-path backwards elimination; tests both single and multiple hypothesis tests, diagnostics tests and goodness-of-fit measures. See page 5 of Sucarrat, (2021) for more details.

The value for gets_pval is influential the final model based on the multipath backward elimination. For more details on the general-to-specific approach, see the vignette of the 'gets' package.

Value

`Parsimonious_ARDL_fit`	Return an estimated general-to-specific ARDL model
`Parsimonious_ECM_fit`	Return an estimated general-to-specific error correction model
`Summary_ecm_fit`	Return the summary of 'Parsimonious_ECM_fit'
`Parsimonious_ECM_diagnostics_test`	Return the diagnostic test for 'Parsimonious_ECM_fit'.The diagnostic tests items are the Breusch-Godfrey test for higher-order serial correlation (BG_SC_lm_test). The Engle (1982) test for conditional heteroscedasticity (LM_ARCH_test). The test for non-normality is that of Jarque and Bera (1980). The RESET null hypothesis adopted implies - including the 2nd - degree terms improve the fit (over the model specified). Ljung and Box (1978) tests for autocorrelation in the residuals
`cointegration`	Return the F statistic, the upper and lower critical values for PSS (2001) bounds test
`Longrun_relation`	The estimated longrun relation from the error correction model

Note

Do not differenced the variables to be adopted in this function and all other functions for ARDL and NARDL estimation. The package inherently takes the difference and produced output with a prefix (D.) to the variable name and suffix the variable name with underscore (_) and the lag value.

References

Sucarrat, G. User-Specified General-to-Specific (GETS) and Indicator Saturation (ISAT) Methods. 28th September 2021. https://mirror.epn.edu.ec/CRAN/web/packages/gets/vignettes/user-defined-gets-and-isat.pdf

Examples

data("expectation")
out_aut <- auto_case_ardl(x = expectation, 
                         dep_var = 'n12m_inf_exp', 
                         expl_var = c('food_inf',"hawkish","dovish"), 
                         p_order = 2, 
                         q_order = c(4,4,4), 
                         gets_pval = 0.05, 
                         graph_save = FALSE)

data("fuel_price")
out_aut <- auto_case_ardl(x = fuel_price, 
                         dep_var = 'fpp',
                         expl_var = c('bdc','wti'),
                         p_order = 2,
                         q_order = c(4,4),
                         gets_pval = 0.08,
                         graph_save = TRUE)
data("expectation")
out_aut <- auto_case_ardl(x = expectation, 
                         dep_var = 'n12m_inf_exp', 
                         expl_var = c('food_inf',"hawkish","dovish"), 
                         p_order = 2, 
                         q_order = c(4,4,4), 
                         gets_pval = 0.05, 
                         graph_save = FALSE)

data("fuel_price")
out_aut <- auto_case_ardl(x = fuel_price, 
                         dep_var = 'fpp',
                         expl_var = c('bdc','wti'),
                         p_order = 2,
                         q_order = c(4,4),
                         gets_pval = 0.08,
                         graph_save = TRUE)

Import from package nardl

Description

The cumsq object is imported from package nardl. Help is available here: nardl::cumsq.

Import from package nardl

Description

The cusum object is imported from package nardl. Help is available here: nardl::cusum.

A function in 'dynamac' package to Perform Pesaran, Shin, and Smith (2001) cointegration test

Description

This is an Abridged version of Jordan and Philips (2020). Please, see the dynamac package for the full documentation and due reference be given to the authors of dynamac - Jordan and Philips (2020).

Usage

dynamac_pkg_bounds_test(obs, fstat, tstat = NULL, case, k)
dynamac_pkg_bounds_test(obs, fstat, tstat = NULL, case, k)

Arguments

`obs`	Number of observations
`fstat`	F-statistics
`tstat`	't-statistic of the lagged dependent variable'
`case`	case I to IV
`k`	'number of regressors appearing in levels in the estimated model, not including the lagged dependent variable'

Value

`Fstat`	The bounds F statistic, lower and upper bounds
`tstat`	The bounds t statistic, lower and upper bounds

References

Jordan S, Philips A (2020). _dynamac: Dynamic Simulation and Testing for Single-Equation ARDL Models_. R package version 0.1.11 <https://CRAN.R-project.org/package=dynamac>

Inflation Expectation Dataset

Description

Dataset

Usage

data("expectation")data("expectation")

Format

A data frame with 47 observations on the following variables.

date: date from 2009Q1 to 2020Q4
nq_inf_exp: Natural log of Next quarter inflation expectation (index)
n12m_inf_exp: Natural log of Next 12-month inflation expectation (index)
hawkish: Hawkishness
dovish: Dovishness
nethawkish: nethawkishness
headline_inf: actual headline inflation (percent)
core_inf: actual core inflation (percent)
food_inf: actual food inflation (percent)

Details

The sentiment indices were extracted (text mined) from CBN monetary policy committee ommuniques with the aid of the monetary policy dictionary adopted in Mate et al. (2021).

Source

....

References

Mate A, Sebok M, Barczikay T (2021) The effect of central bank communication on sovereign bond yields: The case of Hungary. PLoS ONE 16(2): e0245515. https://doi.org/10.1371/journal.pone.0245515

Examples

data(expectation)
data(expectation)

Time series data from 2000M01 through 2021M03

Description

Time series data on fuel pump price, oil price and exchange rate

Usage

data("fuel_price")data("fuel_price")

Format

A data frame with 255 observations on the following variables.

fpp: log of Fuel Pump Price Per Litre - Average (PMS)
wti: log of West Texas Intemediate
bdc: log of Bureau De-change exchange rate (N/$)
date: time series from 2000M01 through 2021M03

Source

fpp is obtained from Central Bank of Nigeria 2021Q1 Statistical Bulletin

wti obtained from Wold bank commodity price (pinksheet)

bdc sourced from http://statistics.cbn.gov.ng/cbn-onlinestats/

Examples

data(fuel_price)
data(fuel_price)

General-to-specific approach for the autoregressive distributed lag model

Description

Adopt the general-to-specific approach to estimate the autoregressive distributed lag model

Usage

gets_ardl_uecm(x, dep_var, expl_var, p_order = c(2), q_order = c(3),
              gets_pval = 0.1, case = 3, F_HC = FALSE, order_l = 5, 
              graph_save = FALSE)gets_ardl_uecm(x, dep_var, expl_var, p_order = c(2), q_order = c(3),
              gets_pval = 0.1, case = 3, F_HC = FALSE, order_l = 5, 
              graph_save = FALSE)

Arguments

`x`	data frame
`dep_var`	A character vector. The dependent variable.
`expl_var`	Character vector. List of explanatory variable(s)
`p_order`	Integer. Maximum number of lags for 'dep_var'
`q_order`	Integer. Maximum number of lags for 'expl_var'
`gets_pval`	Integer value between 0 and 1 needed for the general-to-specific approach. The default is 0.1 (10 percent significance level). The chosen p-value is the criteria for determining non-significant repressors to be eliminated in a backward elimination path. The final parsimonious model is the best fit model based on the Schwarz information criteria
`case`	Positive integer 1 to 5. Default is 3
`F_HC`	Logical (default is FALSE). If TRUE, Heteroscedasticity-Consistent Covariance Matrix Estimation is applied to the model before when estimating F statistic
`graph_save`	Logical. If TRUE, display stability plot. Default is FALSE
`order_l`	Integer. order for the serial correlation, and heteroscedasticity test

Value

`Parsimonious_ARDL_fit`	Return an estimated general-to-specific ARDL model
`Parsimonious_ECM_fit`	Return an estimated general-to-specific error correction model
`Summary_ecm_fit`	Return the summary of 'Parsimonious_ECM_fit'
`Parsimonious_ECM_diagnostics_test`	Return the diagnostic test for 'Parsimonious_ECM_fit'.The diagnostic tests items are the Breusch-Godfrey test for higher-order serial correlation (BG_SC_lm_test). The Engle (1982) test for conditional heteroscedasticity (LM_ARCH_test). The test for non-normality is that of Jarque and Bera (1980). The RESET null hypothesis adopted implies - including the 2nd - degree terms improve the fit (over the model specified). Ljung and Box (1978) tests for autocorrelation in the residuals
`cointegration`	Return the F statistic, the upper and lower critical values for PSS (2001) bounds test
`Longrun_relation`	The estimated longrun relation from the error correction model

References

Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflations. Econometrica (50) 987 - 1007

Ljung GM, Box GEP (1978). On a Measure of Lack of Fit in Time Series Models. Biometrika, 65(2), 297 - 303. https://doi.org/10.2307/2335207

Jarque C, Bera A (1980). Efficient Tests for Normality, Homoskedasticity, and Serial Independence. Economics Letters, 6(3), 255 - 259. https://doi.org/10.1016/0165-1765 (80) 90024-5

Pesaran, M. H., Shin, Y., & Smith, R. J. (2001). Bounds testing approaches to the analysis of level relationships Journal of applied econometrics, 16(3), 289-326

Examples

  data(expectation)
  out <- gets_ardl_uecm(x = expectation,
                        dep_var = c('nq_inf_exp'), 
                        expl_var = c('food_inf','nethawkish'),
                        p_order = c(4), 
                        q_order = c(5,7),
                        gets_pval = 0.1, 
                        case = 4, 
                        graph_save = FALSE,
                        F_HC = FALSE,
                        order_l = 7)
  out
data(expectation)
  out <- gets_ardl_uecm(x = expectation,
                        dep_var = c('nq_inf_exp'), 
                        expl_var = c('food_inf','nethawkish'),
                        p_order = c(4), 
                        q_order = c(5,7),
                        gets_pval = 0.1, 
                        case = 4, 
                        graph_save = FALSE,
                        F_HC = FALSE,
                        order_l = 7)
  out

Parsimonious NARDL model

Description

Adopt the general-to-specific approach to estimate the autoregressive distributed lag model

Usage

gets_nardl_uecm(x, decomp, dep_var, control = NULL, d = Inf, c_q_order = c(2), 
                p_order = c(3), q_order = c(4), gets_pval = 0.1, order_l = 4, 
                F_HC = FALSE, graph_save = FALSE, case = 3)gets_nardl_uecm(x, decomp, dep_var, control = NULL, d = Inf, c_q_order = c(2), 
                p_order = c(3), q_order = c(4), gets_pval = 0.1, order_l = 4, 
                F_HC = FALSE, graph_save = FALSE, case = 3)

Arguments

`x`	data frame
`decomp`	A character vector. The variable decomposed into positive (pos) and negative (neg) change.
`dep_var`	A character vector. The dependent variable
`control`	A character vector. Default is NULL. The second dependent variable.
`d`	An integer or character vector. The threshold value (d) is adopted when computing the partial sum. The default value Inf is the implicit threshold for the partial sum whenever the base 'cumsum' function is adopted. The value of d can be 'mean' or 0 and any other integer specified as the threshold value for the partial sum.
`c_q_order`	Integer. Maximum number of lags for 'control'
`p_order`	Integer. Maximum number of lags for 'dep_var'
`q_order`	Integer. Maximum number of lags for level and differenced 'decomp'
`gets_pval`	Integer value between 0 and 1 needed for the general-to-specific approach. The default is 0.1 (10 percent significance level). The chosen p-value is the criteria for determining non-significant repressors to be eliminated in a backward elimination path. The final parsimonious model is the best fit model based on the Schwarz information criteria.
`order_l`	Integer. order for the serial correlation, and heteroscedasticity test
`F_HC`	Logical (default is FALSE). If TRUE, heteroscedasticity-Consistent Covariance Matrix Estimation is applied to the model before when estimating F statistic
`graph_save`	Logical. If TRUE, display stability plot. Default is FALSE.
`case`	Positive integer 1 to 5. Default is 3

Value

`Parsimonious_NARDL_fit`	Return an estimated general-to-specific NARDL model.
`Parsimonious_ECM_fit`	Return an estimated general-to-specific error correction model.
`Summary_uecm_fit`	Return the summary of 'Parsimonious_ECM_fit'
`ecm_diagnostics_test`	Return the diagnostic test for the 'Parsimonious_ECM_fit'. The diagnostic tests indicate the Breusch-Godfrey test for higher-order serial correlation (BG_SC_lm_test). The Engle (1982) test for conditional heteroscedasticity (LM_ARCH_test). The test for non-normality is that of Jarque and Bera (1980). The RESET null hypothesis adopted implies - including the 2nd - degree terms improve the fit (over the model specified).
`longrun_asym`	Return the estimated longrun asymmetric test
`Shortrun_asym`	Return the estimated short-run asymmetric test.If one of the decomposed variable does not appear among the shortrun differenced variables of the parsimonious model, The value returned is a wald test of whether the sum of the coefficients of the remaining decomposed variable included does not have any significant effect on the best model
`cointegration`	Return the F statistic, the upper and lower critical values for PSS (2001) bounds test. Please, disregard the tstat on the cointegration test.
`Longrun_relation`	The longrun relation

Note

The decomposed variable should display both positive and negative change, preferably on a balanced scale. However, when a variable display only positive change and no negative change, vice versa, such variable should not be adopted (i.e decomposed).

References

Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflations. Econometrica 50: 987 - 1007.

Jarque C, Bera A (1980). Efficient Tests for Normality, Homoskedasticity, and Serial Independence. Economics Letters, 6(3), 255 - 259. https://doi.org/10.1016/0165-1765(80) 90024-5.

Pesaran, M. H., Shin, Y., & Smith, R. J. (2001). Bounds testing approaches to the analysis of level relationships. Journal of applied econometrics, 16(3), 289-326.

Examples

## Not run: 
  data(expectation)
  out <- gets_nardl_uecm(x = expectation,
                         decomp = 'food_inf',
                         dep_var = 'nq_inf_exp',
                         control = 'nethawkish',
                         c_q_order = c(3),
                         p_order = c(3),
                         q_order = c(3),
                         gets_pval = 0.1,
                         graph_save = FALSE,
                         case = 5, 
                         F_HC = FALSE)
  out

## End(Not run)
## Not run: 
  data(expectation)
  out <- gets_nardl_uecm(x = expectation,
                         decomp = 'food_inf',
                         dep_var = 'nq_inf_exp',
                         control = 'nethawkish',
                         c_q_order = c(3),
                         p_order = c(3),
                         q_order = c(3),
                         gets_pval = 0.1,
                         graph_save = FALSE,
                         case = 5, 
                         F_HC = FALSE)
  out

## End(Not run)

Lag a matrix

Description

Take the lag of a variable using the specified number of lag(s).

Usage

lagm(x, k)
lagm(x, k)

Arguments

`x`	a matrix object
`k`	number of lags

Value

`x`	dimentional matrix with k

Examples

x <- cbind(x1 = c(23, 45, 56, 78, 98, 21, 17),
            x2 = c(3, 4, 6, 7, 2, 9, 17))
lagm(x, k = 3)
x <- cbind(x1 = c(23, 45, 56, 78, 98, 21, 17),
            x2 = c(3, 4, 6, 7, 2, 9, 17))
lagm(x, k = 3)

Obtain the best NARDL model specification and bounds test.

Description

This function finds the best NARDL model specification and conduct bounds test by relying on the general to specific approach.

Usage

nardl_auto_case(x, decomp, dep_var, control = NULL, d = Inf, c_q_order = c(2), 
                p_order = c(3), q_order, gets_pval = 0.1, 
                order_l = order_l, graph_save = FALSE)
nardl_auto_case(x, decomp, dep_var, control = NULL, d = Inf, c_q_order = c(2), 
                p_order = c(3), q_order, gets_pval = 0.1, 
                order_l = order_l, graph_save = FALSE)

Arguments

`x`	Dataframe
`decomp`	A character vector. The variable to be decomposed to positive (pos) and negative (neg) variable.
`dep_var`	A character vector. The dependent variable
`control`	A character vector. Default is NULL. The second dependent variable.
`d`	An integer or character vector. The threshold value (d) is adopted when computing the partial sum. The default value Inf is the implicit threshold for the partial sum whenever the base 'cumsum' function is adopted. The value of d can be 'mean' or 0 and any other integer specified as the threshold value for the partial sum.
`c_q_order`	Integer. Maximum number of lags for 'control'
`p_order`	An integer. Lag differenced adopted for the differenced response variable
`q_order`	An integer. Lag differenced adopted for the differenced explanatory variable(s)
`gets_pval`	The p- value which served as criteria for eliminating non-significant variable in the course of obtaining the best model based on the Schwarz information criteria.
`order_l`	Integer. Needed for the autocorrelation and heteroscedasticity test
`graph_save`	Logical. If TRUE, displays the stability plots

Details

The value for gets_pval is influential the final model based on the multipath backward elimination. For more details on the general-to-specific approach, see the vignette of the 'gets' package.

Value

`Parsimonious_NARDL_fit`	Return an estimated general-to-specific NARDL model.
`Parsimonious_ECM_fit`	Return an estimated general-to-specific error correction model.
`Summary_uecm_fit`	Return the summary of 'Parsimonious_ECM_fit'
`ecm_diagnostics_test`	Return the diagnostic test for the 'Parsimonious_ECM_fit'. The diagnostic tests indicate the Breusch-Godfrey test for higher-order serial correlation (BG_SC_lm_test). The Engle (1982) test for conditional heteroscedasticity (LM_ARCH_test). The test for non-normality is that of Jarque and Bera (1980). The RESET null hypothesis adopted implies - including the 2nd - degree terms improve the fit (over the model specified).
`longrun_asym`	Return the estimated longrun asymmetric test
`Shortrun_asym`	Return the estimated short-run asymmetric test.If one of the decomposed variable does not appear among the shortrun differenced variables of the parsimonious model, The value returned is a wald test of whether the sum of the coefficients of the remaining decomposed variable included does not have any significant effect on the best model
`cointegration`	Return the F statistic, the upper and lower critical values for PSS (2001) bounds test. Please, disregard the tstat on the cointegration test.
`Longrun_relation`	The longrun relation

Note

Do not differenced the variables to be adopted in this function and all other functions for NARDL and ARDL estimation. The package inherently takes the difference and produced output with a prefix (D.) to the variable name and suffix the variable name with underscore (_) and the lag value.

References

Examples

## Not run: 
 data("fuel_price")
 out1 <- nardl_auto_case(x = fuel_price,
                decomp =  'wti',
                dep_var = 'fpp',
                control = 'bdc',
                c_q_order = c(5), 
                p_order = c(5),
                q_order = c(6),
                gets_pval = 0.1,
                order_l = 4,
                graph_save = FALSE)
 out1

 out2 <- nardl_auto_case(x = fuel_price,
                decomp =  'wti',
                dep_var = 'fpp',
                control = NULL,
                c_q_order = c(4), 
                p_order = c(5),
                q_order = c(6),
                gets_pval = 0.02,
                order_l = 4,
                graph_save = FALSE)
 out2

## End(Not run)
## Not run: 
 data("fuel_price")
 out1 <- nardl_auto_case(x = fuel_price,
                decomp =  'wti',
                dep_var = 'fpp',
                control = 'bdc',
                c_q_order = c(5), 
                p_order = c(5),
                q_order = c(6),
                gets_pval = 0.1,
                order_l = 4,
                graph_save = FALSE)
 out1

 out2 <- nardl_auto_case(x = fuel_price,
                decomp =  'wti',
                dep_var = 'fpp',
                control = NULL,
                c_q_order = c(4), 
                p_order = c(5),
                q_order = c(6),
                gets_pval = 0.02,
                order_l = 4,
                graph_save = FALSE)
 out2

## End(Not run)

A NARDL model with two decomposed variables

Description

Estimate a NARDL model, having mulitple (two) decomposed variables

Usage

nardl_mdv(x, dep_var, decomp1, decomp2, thresh1 = Inf, thresh2 = Inf, 
gets = TRUE, gets_pval = 0.1, case = NULL, conservative = FALSE, p_order = c(3), 
q_order1 = c(5), q_order2 = c(5), order_l = 4, graph_save = FALSE)
nardl_mdv(x, dep_var, decomp1, decomp2, thresh1 = Inf, thresh2 = Inf, 
gets = TRUE, gets_pval = 0.1, case = NULL, conservative = FALSE, p_order = c(3), 
q_order1 = c(5), q_order2 = c(5), order_l = 4, graph_save = FALSE)

Arguments

`x`	A dataframe
`dep_var`	The dependent variable
`decomp1`	Initial variable to be decomposed into postive and negative.
`decomp2`	The second variable decomposed into postive and negative.
`thresh1`	An integer or character vector. The threshold value (thresh1) for the first variable is adopted when computing the partial sum. Inf is the implicit threshold value for the partial sum whenever the base 'cumsum' function is adopted. The value of the threshold can be 'mean' or 0 or any other integer stated for the partial sum.
`thresh2`	An integer or character vector. The threshold value (thresh2) for the second decomposed variable.
`gets`	Logical. General-to-specific (GETS) approach. Default is TRUE which indicate adopting the GETS
`gets_pval`	The p-value adopted when gets is set as TRUE
`case`	An integer which can take either of 1, 2, 3, 4 or 5. The assumption on Bounds test procedure. Default is NULL. When it is set as an integer, gets should be set as FALSE.
`conservative`	Logical. Default is FALSE. When TRUE, the decomposed variables are assumed to be k = 2. When FALSE, k = 4.
`p_order`	An integer. Take the number of lags applicable to the dependent variable
`q_order1`	An integer. Take maximum number of lags applicable to the first variable
`q_order2`	An integer. The maximum number of lags applicable to the second variable
`order_l`	An integer. Used in the diagnostics test
`graph_save`	Logical. Default is FALSE. When TRUE, return the stability plots of the model

Details

Return a list containing

Value

`NARDL_fit`	NARDL model
`ECM_fit`	NARDL-ECM
`Summary_uecm_fit`	Summary of ECM_fit
`ecm_diagnostics_test`	Diagnostic tests
`longrun_asym`	longrun asymmetric test
`Shortrun_asym`	Shortrun asymmetric test
`cointegration`	PSS bounds test
`Longrun_relation`	Longrun relationship

Note

References

Jordan S, Philips A (2020). _dynamac: Dynamic Simulation and Testing for Single-Equation ARDL Models_. R package version 0.1.11

Narayan, P. K. (2005). The saving and investment nexus for China: evidence from cointegration tests. Applied economics, 37(17), 1979-1990.

Pesaran, M. H., Shin, Y., & Smith, R. J. (2001). Bounds testing approaches to the analysis of level relationships. Journal of applied econometrics, 16(3), 289-326.

Zaghdoudi, T. (2018). nardl: Nonlinear Cointegrating Autoregressive Distributed Lag Model_. R package version 0.1.5

Examples

## Not run: 
data(expectation)
nardl_mdv(x = expectation,
          dep_var = 'nq_inf_exp',
          decomp1 = 'food_inf',
          decomp2 = 'nethawkish',
          p_order = c(7),
          q_order1 = c(4),
          q_order2 = c(6),
          gets_pval = 0.1,
          conservative = FALSE,
          gets = FALSE,
          case = 5,
          order_l = 3,
          graph_save = FALSE)

## End(Not run)## Not run: 
data(expectation)
nardl_mdv(x = expectation,
          dep_var = 'nq_inf_exp',
          decomp1 = 'food_inf',
          decomp2 = 'nethawkish',
          p_order = c(7),
          q_order1 = c(4),
          q_order2 = c(6),
          gets_pval = 0.1,
          conservative = FALSE,
          gets = FALSE,
          case = 5,
          order_l = 3,
          graph_save = FALSE)

## End(Not run)

Estimate the nonlinear ARDL (NARDL) Error Correction Model

Description

Function to estimate Shin, Yu, and Greenwood-Nimmo (2014) nonlinear ARDL (NARDL), the NARDL ECM, and conduct the bounds test for cointegration.

Usage

nardl_uecm(x, decomp, d = Inf, control = NULL, c_q_order = c(2), 
p_order = c(3), q_order = c(4), dep_var, order_l = 4, graph_save = FALSE, case = 3)
nardl_uecm(x, decomp, d = Inf, control = NULL, c_q_order = c(2), 
p_order = c(3), q_order = c(4), dep_var, order_l = 4, graph_save = FALSE, case = 3)

Arguments

`x`	A dataframe object. S3 dataframe object not applicable.
`decomp`	A character vector. The variable to be decomposed into positive (pos) and negative (neg) change.
`d`	An integer or character vector. The default value Inf for the threshold value (d) is adopted when computing the partial sum. Inf is the implicit threshold for the partial sum whenever the base 'cumsum' function is adopted. The value of d can be 'mean' or 0 and any other integer specified as the threshold value for the partial sum.
`control`	A character vector with one element serving as the second variable in the right hand side of the equation. The default is NULL.
`c_q_order`	Lag order for 'control'. the default value is c(2) and only applicable when control is specified.
`p_order`	Positive interger. Number of lags for dependent variable (dep_var).
`q_order`	Positive interger. Short-run lags for the decomposed variables. In case the LM test null hypothesis of no serial correlation is rejected, consider increasing the lags, in particular, the p_order or both p_order and q_order lags until the null hypothesis is accepted.
`dep_var`	Character vector. The dependent variable.
`order_l`	Positive integer. lag order for the serial correlation, and heteroscedasticity test
`graph_save`	Logical (default is FALSE). If TRUE, stability plot is displayed.
`case`	A numerical vector that can take a value between 1 to 5. The default value is case 3. See details for more information.

Value

`NARDL_fit`	This display the NARDL lm fit
`NARDL_ECM_fit`	This display the NARDL ECM lm fit
`UECM`	This display the summary results of the estimated unrestricted error correction models
`cointegration`	This presents the Pesaran, Shin, and Smith (2001) cointegration test. The critical F and t statistics obtained if the sample is greater than 80 are asymptotic. If you adopt this segment, please consider citing Pesaran et al (2001) and Jordan and Philips (2020) dynamac package. If the sample is less than or equal to 80, for case 1, the F and t statistics adopted are large sample asymptotic critical value (CV) and no small-sample asymptotic critical value available. When case = 3 or 5, the critical value of F statistic is small sample asymptotic, and the adopted t statistics are large sample asymptotic CV. Consider including Narayan (2005) in your citation list. If the sample is greater than 80, for case 1, 3 and 5, large sample asymptotic CV for F and t statistics are adopted. In case 2 and 4, for sample <= 80, the F statistic are small sample asymptotic and no asymptotic CV for the t statistic. If sample > 80, for case 2 and 4, large sample asymptotic CV for F is adopted and no t-statistic CV.
`Longrun_relation`	The estimated longrun relations
`Longrun_asymmetric_test`	This contains the asymmetric test, with the null hypothesis of longrun coefficients of the positive decomposed variable equals to the coefficient of negative decomposed variable.
`Shortrun_asymmetric_test`	This contains the asymmetric test, with the null hypothesis the sum of the coefficients of all the short run positive decomposed variable equals to the sum of the coefficients of the short-run negative decomposed variable.
`diagnostics test`	The diagnostic tests indicate the Breusch-Godfrey test for higher-order serial correlation (BG_SC_lm_test). The Engle (1982) test for conditional heteroscedasticity (LM_ARCH_test). The test for non-normality is that of Jarque and Bera (1980). The RESET null hypothesis adopted implies - including the 2nd - degree terms improve the fit (over the model specified). This ARCH LM function is derived from Zaghdoudi (2018)

Note

The decomposed variable should display both positive and negative trend, preferably on a balanced scale. However, when a variable display only positive change and no negative change, vice versa, such variable should not be adopted (i.e decomposed).

References

Jordan S, Philips A (2020). _dynamac: Dynamic Simulation and Testing for Single-Equation ARDL Models_. R package version 0.1.11

Narayan, P. K. (2005). The saving and investment nexus for China: evidence from cointegration tests. Applied economics, 37(17), 1979-1990.

Pesaran, M. H., Shin, Y., & Smith, R. J. (2001). Bounds testing approaches to the analysis of level relationships. Journal of applied econometrics, 16(3), 289-326.

Zaghdoudi, T. (2018). nardl: Nonlinear Cointegrating Autoregressive Distributed Lag Model_. R package version 0.1.5

Examples

data(fuel_price)
output_n1_case5 <- nardl_uecm(x = fuel_price,
                                 decomp  = c('bdc'), 
                                 control =c('wti'),
                                 c_q_order = c(2), 
                                 p_order = c(3), 
                                 q_order = c(5), 
                                 dep_var = c('fpp'), 
                                 graph_save = FALSE, 
                                 case = 5)
output_n1_case5
output_n1_case5$UECM

output_n2_case3 <- nardl_uecm(x = fuel_price, 
                                 decomp  = c('bdc'), 
                                 control =NULL,
                                 c_q_order = NULL, 
                                 p_order = c(3), 
                                 q_order = c(5), 
                                 dep_var = c('fpp'), 
                                 graph_save = FALSE, 
                                 case = 3)
output_n2_case3
data(fuel_price)
output_n1_case5 <- nardl_uecm(x = fuel_price,
                                 decomp  = c('bdc'), 
                                 control =c('wti'),
                                 c_q_order = c(2), 
                                 p_order = c(3), 
                                 q_order = c(5), 
                                 dep_var = c('fpp'), 
                                 graph_save = FALSE, 
                                 case = 5)
output_n1_case5
output_n1_case5$UECM

output_n2_case3 <- nardl_uecm(x = fuel_price, 
                                 decomp  = c('bdc'), 
                                 control =NULL,
                                 c_q_order = NULL, 
                                 p_order = c(3), 
                                 q_order = c(5), 
                                 dep_var = c('fpp'), 
                                 graph_save = FALSE, 
                                 case = 3)
output_n2_case3

Short-run symmetry restrictions (SRSR) and the longrun symmetry restrictions (LRSR).

Description

~~ Performs one of Short-run symmetry restrictions or the longrun symmetry restrictions.

Usage

nardl_uecm_sym(x, assumption = c("SRSR"), decomp, d = Inf, control = c(2), 
c_q_order = c(2), p_order = c(3), q_order = c(4), dep_var, graph_save = FALSE, case = 3)
nardl_uecm_sym(x, assumption = c("SRSR"), decomp, d = Inf, control = c(2), 
c_q_order = c(2), p_order = c(3), q_order = c(4), dep_var, graph_save = FALSE, case = 3)

Arguments

`x`	A dataframe object. S3 dataframe object not applicable.
`assumption`	The Short-run symmetry restrictions (SRSR), the default, assume the transitory asymmetric effect is insignificant and testing the longrun asymmetric effect. longrun symmetry restrictions (LRSR) imposes symmetric effect on the longrun coefficients of the positive and negative decomposed variable, and assuming the presence of transitory asymmetric effect.
`decomp`	A variable to be decomposed into positive (pos) and negative (neg)
`d`	An integer or character vector. The default value Inf for the threshold value (d) is adopted when computing the partial sum. Inf is the implicit threshold for the partial sum whenever the base 'cumsum' function is adopted. The value of d can be 'mean' or 0 and any other integer specified as the threshold value for the partial sum.
`control`	A character vector with one element serving as the second variable single control variable. The default is c(2) and applicable when control variable is specified.
`c_q_order`	Lag order for the control. The default value is c(2) and only applicable when control is specified.
`p_order`	Number of lags for dependent variable (dep_var).
`q_order`	Short-run lags for each positive and negative decomposed variable. In case the LM test null hypothesis of no serial correlation is rejected, consider increasing the lags, in particular, the p_order or both p_order and q_order lags until the null hypothesis is accepted.
`dep_var`	Character vector which contain the dependent variable.
`graph_save`	Logical (default is FALSE). If TRUE, stability plot is displayed.
`case`	A numerical vector of either 1, 2 3, 4 or 5. The default value is 3. See details for more information.

Details

The Short-run symmetry restrictions (SRSR), the default may be useful in obtaining more accurate estimate when the sample is small (SYG, 2014). Besides, this may be necessary when the short-run asymmetric effect does not exist. longrun symmetry restrictions (LRSR) imposes symmetric effect on the positive and negative decomposed variable.

Value

`NARDL_ECM_fit`	This display the NARDL ECM lm fit
`UECM`	This display the summary results of the estimated unrestricted error correction models
`cointegration`	This presents the Pesaran, Shin, and Smith (2001) cointegration test. The critical F and t statistics obtained if the sample is greater than 80 are asymptotic. If you adopt this segment, please consider citing Pesaran et al (2001) and Jordan and Philips (2020) dynamac package. If the sample is less than or equal to 80, for case 1, the F and t statistics adopted are large sample asymptotic critical value (CV) and no small-sample asymptotic critical value available. When case = 3 or 5, the critical value of F statistic is small sample asymptotic, and the adopted t statistics are large sample asymptotic CV. Consider including Narayan (2005) in your citation list. If the sample is greater than 80, for case 1, 3 and 5, large sample asymptotic CV for F and t statistics are adopted. In case 2 and 4, for sample <= 80, the F statistic are small sample asymptotic and no asymptotic CV for the t statistic. If sample > 80, for case 2 and 4, large sample asymptotic CV for F is adopted and no t-statistic CV.
`Longrun_relation`	The estimated longrun relations
`asymmetric test`	This contains the asymmetric test
`diagnostics test`	This presents the Breusch-Godfrey test for higher-order serial correlation with null hypothesis of no serial correlation, the Autoregressive Conditional Heteroscedasticity (ARCH) LM-test with the null hypothesis of no ARCH effect and the Jarque-Bera normality test with null hypothesis of normality. This ARCH LM function is derived from Zaghdoudi (2018)

Note

References

Jordan S, Philips A (2020). _dynamac: Dynamic Simulation and Testing for Single-Equation ARDL Models_. R package version 0.1.11

Narayan, P. K. (2005). The saving and investment nexus for China: evidence from cointegration tests. Applied economics, 37(17), 1979-1990.

Pesaran, M. H., Shin, Y., & Smith, R. J. (2001). Bounds testing approaches to the analysis of level relationships. Journal of applied econometrics, 16(3), 289-326.

Zaghdoudi, T. (2018). nardl: Nonlinear Cointegrating Autoregressive Distributed Lag Model_. R package version 0.1.5

Examples

data(syg_data)
out_srsr <- nardl_uecm_sym(x = syg_data,
             decomp  = 'ca_ip', 
             assumption = c('SRSR'),
             control =NULL,
             p_order =5,
             q_order =3,
             dep_var = 'ca_u',
             graph_save = FALSE, 
             case = 3)
out_srsr

out_lrsr <- nardl_uecm_sym(x = syg_data,
                           decomp  = 'ca_ip', 
                           assumption = c('LRSR'),
                           control =NULL,
                           p_order =5,
                           q_order =3,
                           dep_var = 'ca_u',
                           graph_save = FALSE, 
                           case = 3)
out_lrsr
data(syg_data)
out_srsr <- nardl_uecm_sym(x = syg_data,
             decomp  = 'ca_ip', 
             assumption = c('SRSR'),
             control =NULL,
             p_order =5,
             q_order =3,
             dep_var = 'ca_u',
             graph_save = FALSE, 
             case = 3)
out_srsr

out_lrsr <- nardl_uecm_sym(x = syg_data,
                           decomp  = 'ca_ip', 
                           assumption = c('LRSR'),
                           control =NULL,
                           p_order =5,
                           q_order =3,
                           dep_var = 'ca_u',
                           graph_save = FALSE, 
                           case = 3)
out_lrsr

Rename the coefficient of the nardl_uecm summary output

Description

As the case might be, their could be need to rename the rownames in nardl_uecm summary output

Usage

output_ren(x, listn = listn, D.patern, D.repl, l.patern, l.repl)
output_ren(x, listn = listn, D.patern, D.repl, l.patern, l.repl)

Arguments

`x`	A summary model output, preferably, nardl_uecm object
`listn`	A character vector
`D.patern`	The difference and lag difference variables contained the model
`D.repl`	Character vector containing the new names to replace the D.patern
`l.patern`	Character vector of variable appearing at level
`l.repl`	Character vector containing the names to replace l.patern

Value

`x`	nardl_uecm or nardl_uecm_sym object

Examples

data(syg_data)
un <- c('ca_u','jp_u','us_u')
ip <- c('ca_ip','jp_ip','us_ip')
cnames <- c('Canada','Japan','United States')
case <- c(5,5,5)
p_lags <- c(3,4,5)
q_lags <- c(3,4,5)
########################################
out_nardl <- lapply(1:length(un), function(i)
  nardl_uecm(x = syg_data,
             decomp  = un[[i]], 
             control =NULL,
             c_q_order = c(2), 
             p_order =p_lags[[i]],
             q_order =q_lags[[i]],
             dep_var = ip[[i]],
             graph_save = FALSE, 
             case = 3))
names(out_nardl) <- cnames
out_nardl$Canada$UECM

output <- output_ren(x=out_nardl,listn = un,
           D.patern="D.ca_ip|D.jp_ip|D.us_ip",D.repl="D.output",
           l.patern ="ca_ip|jp_ip|us_ip",l.repl="output")

output <- output_ren(x=output,listn = un,
             D.patern="D.ca_u|D.jp_u|D.us_u",D.repl="D.unemployment",
             l.patern ="ca_u|jp_u|us_u",l.repl="unemployment")

output$Canada$UECM
  
data(syg_data)
un <- c('ca_u','jp_u','us_u')
ip <- c('ca_ip','jp_ip','us_ip')
cnames <- c('Canada','Japan','United States')
case <- c(5,5,5)
p_lags <- c(3,4,5)
q_lags <- c(3,4,5)
########################################
out_nardl <- lapply(1:length(un), function(i)
  nardl_uecm(x = syg_data,
             decomp  = un[[i]], 
             control =NULL,
             c_q_order = c(2), 
             p_order =p_lags[[i]],
             q_order =q_lags[[i]],
             dep_var = ip[[i]],
             graph_save = FALSE, 
             case = 3))
names(out_nardl) <- cnames
out_nardl$Canada$UECM

output <- output_ren(x=out_nardl,listn = un,
           D.patern="D.ca_ip|D.jp_ip|D.us_ip",D.repl="D.output",
           l.patern ="ca_ip|jp_ip|us_ip",l.repl="output")

output <- output_ren(x=output,listn = un,
             D.patern="D.ca_u|D.jp_u|D.us_u",D.repl="D.unemployment",
             l.patern ="ca_u|jp_u|us_u",l.repl="unemployment")

output$Canada$UECM

data on health expenditure, per capita income and life expectancy in Sub-Saharan countries

Description

panel data on

Usage

data("ssa")data("ssa")

Format

A panel data frame on the following variables.

id: list of SSA countries
year: year
HEP: health expenditure per capital
PCI: Per capita income
LE: Life expectancy

Note

variables are in natural log

Source

WDI WHO

Time series data on output and unemployment in Canada, Japan and United States from 1981M01 to 2022M07

Description

Data on unemployment and industrial production for Canada, Japan and United States

Usage

data("syg_data")data("syg_data")

Format

A data frame with 0 observations on the following variables.

ca_u: Canada (CA) unemployment rate
jp_u: Japan (JP) unemployment rate
us_u: United States (US) unemployment rate
us_ip: Natural log of US industrial production (s.a)
jp_ip: Natural log of JP industrial production (s.a)
ca_ip: Natural log of CA industrial production (s.a)
time: 1981M01 - 2022M07

Details

_U is Unemployment rate (monthly), Total, All persons _IP is index of industrial production, s.a.

Source

https://stats.oecd.org/index.aspx?lang=en

Examples

data(syg_data)
data(syg_data)

Package 'ardl.nardl'

Help Index

Linear and Nonlinear Autoregressive Distributed Lag Models: General-to-Specific Approach

Description

References

Examples

Import from package nardl

Description

Estimate the ARDL and ARDL Error Correction Model.

Description

Usage

Arguments

Value

References

See Also

Examples

Obtain the best ARDL model specification and bounds test.

Description

Usage

Arguments

Details

Value

Note

References

See Also

Examples

Import from package nardl

Description

Import from package nardl

Description

A function in 'dynamac' package to Perform Pesaran, Shin, and Smith (2001) cointegration test

Description

Usage

Arguments

Value

References

See Also

Inflation Expectation Dataset

Description

Usage

Format

Details

Source

References

Examples

Time series data from 2000M01 through 2021M03

Description

Usage

Format

Source

Examples

General-to-specific approach for the autoregressive distributed lag model

Description

Usage

Arguments

Value

References

See Also

Examples

Parsimonious NARDL model

Description

Usage

Arguments

Value

Note

References

See Also

Examples

Lag a matrix

Description

Usage

Arguments

Value

Examples

Obtain the best NARDL model specification and bounds test.

Description

Usage

Arguments

Details

Value