lpirfs

https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5
Admin
lpirfs is an R package that estimates linear and nonlinear impulse responses using local...
Tokens:23,178
Snippets:134
Trust Score:9.8
Update:6 months ago
Show doc for...
Tokens:
Raw
### Load package for examples

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/plot_nl

Load the lpirfs package to run examples. See examples for lp_nl() and lp_nl_iv() for specific use cases.

```R
# Load package

 # See examples for lp_nl() and lp_nl_iv().
```

--------------------------------

### Load lpirfs Package and Data

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_nl

Loads the lpirfs package and example endogenous data for VAR analysis. Ensure the package is installed before running.

```r
# \donttest{ 
                  ## Example without exogenous variables ##

# Load package
  library(lpirfs)
  library(gridExtra)
  library(ggpubr)


# Load (endogenous) data
  endog_data <- interest_rules_var_data

# Choose data for switching variable (here Federal Funds Rate)
# Important: The switching variable does not have to be used within the VAR!
 switching_data <-  endog_data$Infl

```

--------------------------------

### LPIRFS Package Examples

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_lin_panel

Example code demonstrating how to use the LPIRFS package for impulse response estimation.

```APIDOC
## Examples

Run this code
```
# \donttest{

#--- Info
# This example is based on a STATA code that has been provided on
# Òscar Jordà's website (https://sites.google.com/site/oscarjorda/home/local-projections)
# It estimates impulse reponses of the ratio of (mortgage lending/GDP) to a
# +1% change in the short term interest rate

#--- Get data
# Go to the website of the 'The MacroFinance and MacroHistory Lab'
```
```

--------------------------------

### lpirfs Package Examples

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_nl

Example code demonstrating the usage of the lpirfs package.

```APIDOC
## Examples

Run this code
```R
# \donttest{
                  ## Example without exogenous variables ##

# Load package
  library(lpirfs)
  library(gridExtra)
  library(ggpubr)


# Load (endogenous) data
  endog_data <- interest_rules_var_data

# Choose data for switching variable (here Federal Funds Rate)
# Important: The switching variable does not have to be used within the VAR!
 switching_data <-  endog_data$Infl
```
```

--------------------------------

### Install lpirfs Package

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5

A simple command to install the lpirfs package. This is a repeated instruction for installation.

```R
install.packages('lpirfs')
```

--------------------------------

### Run Impulse Response Estimation Example

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_lin_panel

A basic template for setting up impulse response estimation based on Jordà's local projections.

```R
# \donttest{

#--- Info
# This example is based on a STATA code that has been provided on
# Òscar Jordà's website (https://sites.google.com/site/oscarjorda/home/local-projections)
# It estimates impulse reponses of the ratio of (mortgage lending/GDP) to a
# +1% change in the short term interest rate

#--- Get data
# Go to the website of the 'The MacroFinance and MacroHistory Lab'
```

--------------------------------

### Install lpirfs Development Version from GitHub

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5

Install the latest development version of the lpirfs package from GitHub. This requires the devtools package and may need C++ compilers.

```R
# install.packages("devtools")
devtools::install_github("https://github.com/AdaemmerP/lpirfs")
```

--------------------------------

### Install lpirfs from CRAN

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5

Use this command to install the released version of the lpirfs package from CRAN. Ensure you have a stable internet connection.

```R
install.packages("lpirfs")
```

--------------------------------

### Prepare Variables for Panel Data Analysis

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_nl_panel

Mutates and selects variables from the JST dataset, calculating ratios and logs as required for impulse response analysis. This step is based on the 'data.do' file from the original STATA example.

```r
## Prepare variables. This is based on the 'data.do' file
#   data_set <- jst_data %>%
#                mutate(stir     = stir)                          %>%
#                mutate(mortgdp  = 100*(tmort/gdp))               %>%
#                mutate(hpreal   = hpnom/cpi)                     %>%
#                group_by(country)                                %>%
#                mutate(hpreal   = hpreal/hpreal[year==1990][1]) %>%
#                mutate(lhpreal  = log(hpreal))                   %>%
#
#                mutate(lhpy     = lhpreal - log(rgdppc))         %>%
#                mutate(lhpy     = lhpy - lhpy[year == 1990][1]) %>%
#                mutate(lhpreal  = 100*lhpreal)                   %>%
#                mutate(lhpy     = 100*lhpy)                      %>%
#                ungroup()                                        %>%
#
#                mutate(lrgdp    = 100*log(rgdppc))               %>%
#                mutate(lcpi     = 100*log(cpi)) 	            %>%
#                mutate(lriy     = 100*log(iy*rgdppc))            %>%
#                mutate(cay      = 100*(ca/gdp))                  %>%
#                mutate(tnmort   = tloans - tmort)                %>%
#                mutate(nmortgdp = 100*(tnmort/gdp))              %>%
#                dplyr::select(country, year, mortgdp, stir, ltrate, lhpy,
#                              lrgdp, lcpi, lriy, cay, nmortgdp)
#
```

--------------------------------

### Estimate Panel Model with GMM

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_nl_panel

Estimates a panel model using Generalized Method of Moments (GMM). This example is suited for datasets with fewer time periods (T) than cross-sectional units (N). It includes options for one-step GMM, two-way effects, and lagged endogenous variables. Note that the data set used in this example might not be well-suited for GMM due to a small number of cross-sectional units.

```R
results_panel <-  lp_nl_panel(
                              data_set           = data_set,
                              data_sample       = data_sample,
                              endog_data        = "mortgdp",
                              cumul_mult        = TRUE,

                              shock             = "stir",
                              diff_shock        = TRUE,

                              use_gmm            = TRUE,
                              gmm_model          = "onestep",
                              gmm_effect         = "twoways",
                              gmm_transformation = "ld",

                              switching         = "lrgdp",
                              lag_switching     = TRUE,
                              use_hp            = TRUE,
                              lambda            = 6.25,
                              gamma             = 10,

                              l_exog_data       = "mortgdp",
                              lags_exog_data    = 1,

                              confint           = 1.67,
                              hor               = 5
                              )
```

--------------------------------

### Estimate Panel Model with GMM

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_lin_panel

Use this function to estimate a panel model using Generalized Method of Moments (GMM). It is recommended for datasets where the number of time periods (T) is much larger than the number of cross-sectional units (N). The example includes parameters for endogenous data, cumulative multipliers, shocks, and GMM specific settings.

```R
results_panel <-  lp_lin_panel(data_set          = data_set,
                              data_sample        = data_sample,
                              endog_data         = "mortgdp",
                              cumul_mult         = TRUE,

                              shock              = "stir",
                              diff_shock         = TRUE,

                              use_gmm            = TRUE,
                              gmm_model          = "onestep",
                              gmm_effect         = "twoways",
                              gmm_transformation = "ld",

                              l_exog_data        = "mortgdp",
                              lags_exog_data     = 2,
                              l_fd_exog_data     = colnames(data_set)[c(4, 6)],
                              lags_fd_exog_data  = 1,

                              confint            = 1.67,
                              hor                = 5)
```

--------------------------------

### Decompose Federal Funds Rate using hp_filter

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/hp_filter

This example demonstrates how to use the hp_filter function to decompose the Federal Funds Rate time series. It requires the lpirfs and ggplot2 packages. The results are then prepared for plotting.

```R
library(lpirfs)


# Decompose the Federal Funds Rate
 data_set     <- as.matrix(interest_rules_var_data$FF)
 hp_results   <- hp_filter(data_set, 1600)

# Extract results and save as data.frame
 hp_cyc    <- as.data.frame(hp_results[[1]])
 hp_trend  <- as.data.frame(hp_results[[2]])

# Make data.frames for plots
 cyc_df     <- data.frame(yy = hp_cyc$V1,   xx = seq(as.Date('1955-01-01'),
                            as.Date('2003-01-01') , "quarter"))
 trend_df   <- data.frame(yy = hp_trend$V1, xx = seq(as.Date('1955-01-01'),
                            as.Date('2003-01-01') , "quarter"))

# Make plots
 library(ggplot2)

# Plot cyclical part
 ggplot(data = cyc_df) +
 geom_line(aes(y = yy, x = xx))

# Plot trend component
 ggplot(trend_df) +
 geom_line(aes(y = yy, x = xx))
```

--------------------------------

### Load lpirfs package

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_lin

Initial step to load the lpirfs library before running impulse response estimations.

```R
# \donttest{
          ## Example without exogenous variables

# Load package
  library(lpirfs)
```

--------------------------------

### Prepare panel data with create_panel_data

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/create_panel_data

Use this function to format panel data based on specifications generated by lp_lin_panel or lp_nl_panel.

```R
create_panel_data(specs, data_set)
```

--------------------------------

### Get Robust Covariance Matrix for Panel Data

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/get_robust_cov_panel

Use this function to obtain a robust covariance matrix for panel data estimations. It requires a Plm object from estimation and a list of specifications.

```r
get_robust_cov_panel(panel_results, specs)
```

--------------------------------

### POST /lp_lin

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_lin

Computes linear impulse responses with local projections.

```APIDOC
## POST /lp_lin

### Description
Compute linear impulse responses with local projections by Jordà (2005).

### Method
POST

### Parameters
#### Request Body
- **endog_data** (data.frame) - Required - Endogenous variables for the VAR.
- **lags_endog_lin** (integer/NaN) - Optional - Number of lags for endog_data.
- **lags_criterion** (character/NaN) - Optional - Lag length criterion ('AICc', 'AIC' or 'BIC').
- **max_lags** (integer/NaN) - Optional - Maximum number of lags.
- **trend** (integer) - Optional - 0: No trend, 1: Trend, 2: Trend and quadratic trend.
- **shock_type** (integer) - Optional - 0: Standard deviation shock, 1: Unit shock.
- **confint** (double) - Optional - Width of confidence bands.
- **use_nw** (boolean) - Optional - Use Newey-West standard errors.
- **nw_lag** (integer) - Optional - Max lag for Newey-West estimator.
- **nw_prewhite** (boolean) - Optional - Should estimators be pre-whitened.
- **adjust_se** (boolean) - Optional - Finite sample adjustment for covariance matrix.
- **hor** (integer) - Optional - Number of horizons.
- **exog_data** (data.frame) - Optional - Exogenous variables.
- **lags_exog** (integer) - Optional - Number of lags for exogenous data.
- **contemp_data** (data.frame) - Optional - Exogenous data with contemporaneous impact.
- **num_cores** (integer) - Optional - Number of cores to use.

### Response
#### Success Response (200)
- **irf_lin_mean** (array) - 3D array of impulse responses.
- **irf_lin_low** (array) - 3D array of lower confidence bands.
- **irf_lin_up** (array) - 3D array of upper confidence bands.
- **diagnostic_list** (list) - OLS diagnostics.
- **specs** (list) - Properties of endog_data and estimation specs.
```

--------------------------------

### Data Preparation and Utilities

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5

Utility functions for data manipulation, lag creation, and filtering required for impulse response estimation.

```APIDOC
## create_lin_data

### Description
Compute data for linear model.

## create_nl_data

### Description
Compute data for nonlinear model with instrument variable approach.

## create_panel_data

### Description
Prepare data sets for linear and nonlinear panel model.

## create_lags

### Description
Compute a data frame with lagged exogenous variables.

## hp_filter

### Description
Decompose a times series via the Hodrick-Prescott filter.
```

--------------------------------

### Load Libraries and Data for Panel Model

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_nl_panel

Loads necessary libraries and prepares the Jordà-Schularick-Taylor Macrohistory Database for analysis. Ensure the 'JSTdatasetR5.xlsx' file is in the correct directory.

```r
# Load libraries to download and read excel file from the website
#  library(lpirfs)
#  library(readxl)
#  library(dplyr)
#
# Load JST Macrohistory Database
#  jst_data <- read_excel("JSTdatasetR5.xlsx", sheet = "Data")
#
## Choose years <= 2013. Swap the first two columns so that 'country' is the
## first (cross section) and 'year' the second (time section) column
#  jst_data <- jst_data                    %>%
#              dplyr::filter(year <= 2013) %>%
#              dplyr::select(country, year, everything())
#
```

--------------------------------

### create_panel_data Function

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/create_panel_data

Prepares data sets for linear and nonlinear panel models.

```APIDOC
## create_panel_data: Prepare data sets for linear and nonlinear panel model

### Description
Function to create panel data for linear and nonlinear model.

### Usage
```R
create_panel_data(specs, data_set)
```

### Arguments
* **specs** (list) - A list with specifications created in lp_lin_panel or lp_nl_panel.
* **data_set** (data.frame) - A data.frame consisting of a panel data set.

### Value
A list with prepared endogenous and exogenous data as well as the updated list _specs_.
```

--------------------------------

### LPIRFS Function Arguments

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_nl_panel

Detailed explanation of the arguments available for the main functions within the LPIRFS package.

```APIDOC
## Arguments

### data_set

A data.frame, containing the panel data set. The first column has to be the variable denoting the cross section. The second column has to be the variable denoting the time section.

### data_sample

Character or numeric. To use the full sample set value to "Full" (default). To estimate a subset, you have to provide a sequence of dates. This sequence has to be in the same format as the second column (time-section).

### endog_data

Character. The column name of the endogenous variable. You can only provide one endogenous variable at a time.

### cumul_mult

Boolean. Estimate cumulative multipliers? TRUE (default) or FALSE. If TRUE, cumulative responses are estimated via: y(t+h)−y(t−1), where h = 0,..., H-1.

### shock

Character. The column name of the variable to shock with.

### diff_shock

Boolean. Take first differences of the shock variable? TRUE (default) or FALSE. Note that when using this option both shock and instrument are used in first differences

### panel_model

Character. Type of panel model. The default is "within" (fixed effects). Other options are "random", "ht", "between", "pooling" or "fd". See vignette of the plm package for details.

### panel_effect

Character. The effects introduced in the model. Options are "individual" (default), "time", "twoways", or "nested". See the vignette of the plm-package for details.

### robust_cov

NULL or Character. The character specifies the method how to estimate robust standard errors: Options are "vcovBK", "vcovDC", "vcovG", "vcovHC", "vcovNW", "vcovSCC". For these options see vignette of plm package. Another option is "Vcxt". For details see Miller (2017) If "use_gmm = TRUE", this option has to be NULL.

### robust_method

NULL (default) or Character. The character is an option when robust_cov = "vcovHC". See vignette of the plm package for details.

### robust_type

NULL (default) or Character. The character is an option when robust_cov = "vcovBK", "vcovDC", "vcovHC", "vcovNW" or "vcovSCC". See vignette of the plm package for details.

### robust_cluster

NULL (default) or Character. The character is an option when robust_cov = "vcovBK", "vcovG" or "vcovHC". See vignette of the plm package for details.

### robust_maxlag

NULL (default) or Character. The character is an option when robust_cov = "vcovNW" or "vcovSCC". See vignette of the plm package for details.

### use_gmm

Boolean. Use GMM for estimation? TRUE or FALSE (default). See vignette of plm package for details. If TRUE, the option "robust_cov" has to be set to NULL.

### gmm_model

Character. Either "onestep" (default) or "twosteps". See vignette of the plm package for details.

### gmm_effect

Character. The effects introduced in the model: "twoways" (default) or "individual". See vignette of the plm-package for details.

### gmm_transformation

Character. Either "d" (default) for the "difference GMM" model or "ld" for the "system GMM". See vignette of the plm package for details.

### c_exog_data

NULL or Character. Name(s) of the exogenous variable(s) with contemporaneous impact.

### l_exog_data

NULL or Character. Name(s) of the exogenous variable(s) with lagged impact.

### lags_exog_data

Integer. Lag length for the exogenous variable(s) with lagged impact.

### c_fd_exog_data

NULL or Character. Name(s) of the exogenous variable(s) with contemporaneous impact of first differences.

### l_fd_exog_data

NULL or Character. Name(s) of exogenous variable(s) with lagged impact of first differences.

### lags_fd_exog_data

NaN or Integer. Number of lags for variable(s) with impact of first differences.

### switching

Character. Column name of the switching variable. If "use_logistic = TRUE", this series can either be decomposed by the Hodrick-Prescott filter (see Auerbach and Gorodnichenko, 2013) or directly plugged into the following smooth transition function: Fzt=exp(−γzt)1+exp(−γzt). The data for the two regimes are lagged by default:   
Regime 1 = (1-`F(z	_{t-1}))*y	_{(t-p)}`,   
Regime 2 = `F(z	_{t-1})*y	_{(t-p)}`. This option can be suppressed with "lag_switching = FALSE".

### use_logistic

Boolean. Use logistic function to separate states? TRUE (default) or FALSE. If FALSE, the values of the switching variable have to be binary (0/1).

### use_hp

Boolean. Use HP-filter? TRUE or FALSE (default).

### lag_switching

Boolean. Use the first lag of the values of the transition function? TRUE (default) or FALSE.

### lambda

Double. Value of λ for the Hodrick-Prescott filter (if "use_hp = TRUE").

### gamma

Double. Positive value for γ, used in the transition function.

### confint

Double. Width of confidence bands. 68% = 1; 90% = 1.65; 95% = 1.96.

### hor

Integer. Number of horizons for impulse responses.
```

--------------------------------

### Load and Prepare JST Macrohistory Database in R

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_lin_panel

Loads the JST Macrohistory Database from an Excel file, filters data by year, and prepares key macroeconomic variables for panel model analysis. Requires the 'readxl' and 'dplyr' libraries.

```r
library(lpirfs)
library(readxl)
library(dplyr)

jst_data <- read_excel("JSTdatasetR5.xlsx", sheet = "Data")

jst_data <- jst_data                     %>% 
              dplyr::filter(year <= 2013)  %>% 
              dplyr::select(country, year, everything())

data_set <- jst_data %>% 
               mutate(stir     = stir)                         %>% 
               mutate(mortgdp  = 100*(tmort/gdp))              %>% 
               mutate(hpreal   = hpnom/cpi)                    %>% 
               group_by(country)                               %>% 
               mutate(hpreal   = hpreal/hpreal[year==1990][1]) %>% 
               mutate(lhpreal  = log(hpreal))                  %>% 

               mutate(lhpy     = lhpreal - log(rgdppc))        %>% 
               mutate(lhpy     = lhpy - lhpy[year == 1990][1]) %>% 
               mutate(lhpreal  = 100*lhpreal)                  %>% 
               mutate(lhpy     = 100*lhpy)                     %>% 
               ungroup()                                       %>% 

               mutate(lrgdp    = 100*log(rgdppc))              %>% 
               mutate(lcpi     = 100*log(cpi)) 	            %>% 
               mutate(lriy     = 100*log(iy*rgdppc))           %>% 
               mutate(cay      = 100*(ca/gdp))                 %>% 
               mutate(tnmort   = tloans - tmort)               %>% 
               mutate(nmortgdp = 100*(tnmort/gdp))             %>% 
               dplyr::select(country, year, mortgdp, stir, ltrate, 
                             lhpy, lrgdp, lcpi, lriy, cay, nmortgdp)
```

--------------------------------

### LPIRFS Function Arguments

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_lin_panel

Detailed explanation of the arguments available for the primary functions within the LPIRFS package.

```APIDOC
## Arguments

### data_set
    
A data.frame, containing the panel data set. The first column has to be the variable denoting the cross section. The second column has to be the variable denoting the time section.

### data_sample
    
Character or numeric. To use the full sample set value to "Full" (default). To estimate a subset, you have to provide a sequence of dates. This sequence has to be in the same format as the second column (time-section).

### endog_data
    
Character. The column name of the endogenous variable. You can only provide one endogenous variable at a time.

### cumul_mult
    
Boolean. Estimate cumulative multipliers? TRUE (default) or FALSE. If TRUE, cumulative responses are estimated via: y(t+h)−y(t−1), where h = 0,..., H-1.

### shock
    
Character. The column name of the variable to shock with.

### diff_shock
    
Boolean. Take first differences of the shock variable? TRUE (default) or FALSE. Note that when using this option both shock and instrument are used in first differences

### iv_reg
    
Boolean. Use instrument variable approach? TRUE or FALSE.

### instrum
    
NULL or Character. The name(s) of the instrument variable(s) if iv_reg = TRUE.

### panel_model
    
Character. Type of panel model. The default is "within" (fixed effects). Other options are "random", "ht", "between", "pooling" or "fd". See vignette of the plm package for details.

### panel_effect
    
Character. The effects introduced in the model. Options are "individual" (default), "time", "twoways", or "nested". See the vignette of the plm-package for details.

### robust_cov
    
NULL or Character. The character specifies the method how to estimate robust standard errors: Options are "vcovBK", "vcovDC", "vcovG", "vcovHC", "vcovNW", "vcovSCC". For these options see vignette of plm package. Another option is "Vcxt". For details see Miller (2017) If "use_gmm = TRUE", this option has to be NULL.

### robust_method
    
NULL (default) or Character. The character is an option when robust_cov = "vcovHC". See vignette of the plm package for details.

### robust_type
    
NULL (default) or Character. The character is an option when robust_cov = "vcovBK", "vcovDC", "vcovHC", "vcovNW" or "vcovSCC". See vignette of the plm package for details.

### robust_cluster
    
NULL (default) or Character. The character is an option when robust_cov = "vcovBK", "vcovG" or "vcovHC". See vignette of the plm package for details.

### robust_maxlag
    
NULL (default) or Character. The character is an option when robust_cov = "vcovNW" or "vcovSCC". See vignette of the plm package for details.

### use_gmm
    
Boolean. Use GMM for estimation? TRUE or FALSE (default). See vignette of plm package for details. If TRUE, the option "robust_cov" has to be set to NULL.

### gmm_model
    
Character. Either "onestep" (default) or "twosteps". See vignette of plm package for details.

### gmm_effect
    
Character. The effects introduced in the model: "twoways" (default) or "individual". See vignette of the plm-package for details.

### gmm_transformation
    
Character. Either "d" (default) for the "difference GMM" model or "ld" for the "system GMM". See vignette of the plm package for details.

### c_exog_data
    
NULL or Character. Name(s) of the exogenous variable(s) with contemporaneous impact.

### l_exog_data
    
NULL or Character. Name(s) of the exogenous variable(s) with lagged impact.

### lags_exog_data
    
Integer. Lag length for the exogenous variable(s) with lagged impact.

### c_fd_exog_data
    
NULL or Character. Name(s) of the exogenous variable(s) with contemporaneous impact of first differences.

### l_fd_exog_data
    
NULL or Character. Name(s) of exogenous variable(s) with lagged impact of first differences.

### lags_fd_exog_data
    
NaN or Integer. Number of lags for variable(s) with impact of first differences.

### confint
    
Double. Width of confidence bands. 68% = 1; 90% = 1.65; 95% = 1.96.

### hor
    
Integer. Number of horizons for impulse responses.
```

--------------------------------

### get_vals_switching

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/get_vals_switching

Computes transition values by using a smooth transition function to separate regimes.

```APIDOC
## get_vals_switching

### Description
Computes transition values by using a smooth transition function as used in Auerbach and Gorodnichenko (2012). The time series used in the transition function can be detrended via the Hodrick-Prescott filter.

### Usage
get_vals_switching(data_set, specs)

### Arguments
- **data_set** (numeric vector or panel data set) - Required - The data set used for the model estimation.
- **specs** (list) - Required - A list with inputs as in lp_nl().

### Value
A numeric vector with values from the smooth transition function F(zt-1).
```

--------------------------------

### Summary for Nonlinear lpirfs Object

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/summary.lpirfs_nl_obj

Provides a summary of a nonlinear lpirfs object.

```APIDOC
## summary.lpirfs_nl_obj: Summary for nonlinear lpirfs object

### Description
Summary for nonlinear lpirfs object

### Usage
```R
# S3 method for lpirfs_nl_obj
summary(object, ...)
```

### Arguments
* `object` - An object of type 'lpirfs_nl_obj' ...
* `...` - Additional arguments to be consistent with S3 print() function
```

--------------------------------

### Generate Individual Impulse Response Plots

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_lin

Generates individual plots for impulse responses from a linear model estimation. The plots are accessed via list indexing.

```r
linear_plots <- plot_lin(results_lin)

linear_plots[[1]]
linear_plots[[2]]
```

--------------------------------

### Compute Structural Shock Matrix via Cholesky Decomposition

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/get_mat_chol

Use get_mat_chol to compute the structural shock matrix. Requires input variables created with lp_lin or lp_nl, and a list of specifications.

```R
get_mat_chol(y_lin, x_lin, endog_data, specs)
```

--------------------------------

### Estimate Non-linear Local Projections with Exogenous Variables

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_nl

Demonstrates model estimation incorporating exogenous data and contemporaneous impact variables.

```R
# Load (endogenous) data
 endog_data <- interest_rules_var_data

# Choose data for switching variable (here Federal Funds Rate)
# Important: The switching variable does not have to be used within the VAR!
 switching_data <-  endog_data$FF

# Create exogenous data and data with contemporaneous impact (for illustration purposes only)
 exog_data    <- endog_data$GDP_gap*endog_data$Infl*endog_data$FF + rnorm(dim(endog_data)[1])
 contemp_data <- endog_data$GDP_gap*endog_data$Infl*endog_data$FF + rnorm(dim(endog_data)[1])

# Exogenous data has to be a data.frame
 exog_data    <- data.frame(xx  = exog_data)
 contemp_data <- data.frame(cc  = contemp_data)

# Estimate model and save results
 results_nl <- lp_nl(endog_data,
                          lags_endog_lin  = 4,
                          lags_endog_nl   = 3,
                          trend           = 0,
                          shock_type      = 1,
                          confint         = 1.96,
                          hor             = 24,
                          switching       = switching_data,
                          use_hp          = TRUE,
                          lambda          = 1600, # Ravn and Uhlig (2002):
                                                  # Anuual data    = 6.25
                                                  # Quarterly data = 1600
                                                  # Monthly data   = 129 600
                          gamma           = 3,
                          exog_data       = exog_data,
                          lags_exog       = 3)


# Show all plots
 plot(results_nl)


# Show diagnostics. The first element correponds to the first shock variable.
 summary(results_nl)
```

--------------------------------

### POST /lp_lin_panel

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_lin_panel

Estimates impulse responses with local projections for panel data using the specified configuration parameters.

```APIDOC
## POST /lp_lin_panel

### Description
Computes linear impulse responses with local projections for panel data, either with an identified shock or by an instrument variable approach.

### Method
POST

### Endpoint
/lp_lin_panel

### Parameters
#### Request Body
- **data_set** (object) - Required - The input data set.
- **data_sample** (string) - Optional - Sample selection, default is "Full".
- **endog_data** (object) - Optional - Endogenous data variables.
- **cumul_mult** (boolean) - Optional - Whether to compute cumulative multipliers, default is TRUE.
- **shock** (string) - Optional - The shock variable.
- **diff_shock** (boolean) - Optional - Whether to difference the shock, default is TRUE.
- **iv_reg** (boolean) - Optional - Whether to use instrumental variable regression, default is FALSE.
- **instrum** (string) - Optional - The instrument variable.
- **panel_model** (string) - Optional - Panel model type, default is "within".
- **panel_effect** (string) - Optional - Panel effect type, default is "individual".
- **robust_cov** (string) - Optional - Robust covariance estimator.
- **robust_method** (string) - Optional - Method for robust covariance.
- **robust_type** (string) - Optional - Type of robust covariance.
- **robust_cluster** (string) - Optional - Cluster variable for robust covariance.
- **robust_maxlag** (integer) - Optional - Max lag for robust covariance.
- **use_gmm** (boolean) - Optional - Whether to use GMM, default is FALSE.
- **gmm_model** (string) - Optional - GMM model type, default is "onestep".
- **gmm_effect** (string) - Optional - GMM effect type, default is "twoways".
- **gmm_transformation** (string) - Optional - GMM transformation, default is "d".
- **c_exog_data** (object) - Optional - Contemporaneous exogenous data.
- **l_exog_data** (object) - Optional - Lagged exogenous data.
- **lags_exog_data** (integer) - Optional - Lags for exogenous data.
- **c_fd_exog_data** (object) - Optional - Contemporaneous first-differenced exogenous data.
- **l_fd_exog_data** (object) - Optional - Lagged first-differenced exogenous data.
- **lags_fd_exog_data** (integer) - Optional - Lags for first-differenced exogenous data.
- **confint** (float) - Optional - Confidence interval level.
- **hor** (integer) - Optional - Number of horizons.

### Response
#### Success Response (200)
- **irf_lin_mean** (matrix) - Impulse responses.
- **irf_lin_low** (matrix) - Lower confidence bands.
- **irf_lin_up** (matrix) - Upper confidence bands.
- **reg_outputs** (object) - Full regression output (plm object) for each horizon.
- **reg_summaries** (object) - Summary of regression output for each horizon.
- **xy_data_sets** (object) - Data sets with endogenous and exogenous variables for each horizon.
- **specs** (list) - Data properties for plotting.
```

--------------------------------

### lpirfs Function Arguments

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_nl

Detailed description of the arguments available for functions within the lpirfs package.

```APIDOC
## Arguments

### `endog_data`

A data.frame, containing all endogenous variables for the VAR. The Cholesky decomposition is based on the column order.

### `lags_endog_lin`

NaN or integer. NaN if lag length criterion is used. Integer for number of lags for linear VAR to identify shock.

### `lags_endog_nl`

NaN or integer. Number of lags for nonlinear VAR. NaN if lag length criterion is given.

### `lags_criterion`

NaN or character. NaN (default) means that the number of lags will be given at `lags_endog_nl` and `lags_endog_lin`. The lag length criteria are 'AICc', 'AIC' and 'BIC'.

### `max_lags`

NaN or integer. Maximum number of lags (if `lags_criterion` = 'AICc', 'AIC', 'BIC'). NaN (default) otherwise.

### `trend`

Integer. Include no trend = 0 , include trend = 1, include trend and quadratic trend = 2.

### `shock_type`

Integer. Standard deviation shock = 0, unit shock = 1.

### `confint`

Double. Width of confidence bands. 68% = 1; 90% = 1.65; 95% = 1.96.

### `use_nw`

Boolean. Use Newey-West (1987) standard errors for impulse responses? TRUE (default) or FALSE.

### `nw_lag`

Integer. Specifies the maximum lag with positive weight for the Newey-West estimator. If set to NULL (default), the lag increases with with the number of horizon.

### `nw_prewhite`

Boolean. Should the estimators be pre-whitened? TRUE of FALSE (default).

### `adjust_se`

Boolen. Should a finite sample adjsutment be made to the covariance matrix estimators? TRUE or FALSE (default).

### `hor`

Integer. Number of horizons for impulse responses.

### `switching`

Numeric vector. A column vector with the same length as `endog_data`. If 'use_logistic = TRUE', this series can either be decomposed via the Hodrick-Prescott filter (see Auerbach and Gorodnichenko, 2013) or directly plugged into the following logistic function: Fzt=exp(−γzt)1+exp(−γzt). Important: `F_{z_t}` will be lagged by one and then multiplied with the data. If the variable shall not be lagged, use 'lag_switching = FALSE':   
Regime 1 = (1-`F(z_{t-1}))*y_{(t-p)}`,   
Regime 2 = `F(z_{t-1})*y_{(t-p)}`.

### `lag_switching`

Boolean. Use the first lag of the values of the transition function? TRUE (default) or FALSE.

### `use_logistic`

Boolean. Use logistic function to separate states? TRUE (default) or FALSE. If FALSE, the values of the switching variable have to be binary (0/1).

### `use_hp`

Boolean. Use HP-filter? TRUE or FALSE.

### `lambda`

Double. Value of λ for the Hodrick-Prescott filter (if use_hp = TRUE).

### `gamma`

Double. Positive number which is used in the transition function.

### `exog_data`

A data.frame, containing exogenous variables for the VAR. The row length has to be the same as `endog_data`. Lag lengths for exogenous variables have to be given and will not be determined via a lag length criterion.

### `lags_exog`

NULL or Integer. Integer for the number of lags for the exogenous data. The value cannot be 0. If you want to to include exogenous data with contemporaneous impact use `contemp_data`.

### `contemp_data`

A data.frame, containing exogenous data with contemporaneous impact. This data will not be lagged. The row length has to be the same as `endog_data`.

### `num_cores`

Integer. The number of cores to use for the estimation. If NULL, the function will use the maximum number of cores minus one.
```

--------------------------------

### Compute and display nonlinear impulse responses

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/plot_nl

Use plot_nl() to generate plots of nonlinear impulse responses. Requires results from lp_nl() or lp_nl_iv().

```R
plot_nl(results_nl)
```

--------------------------------

### Plot Impulse Response Functions

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_nl_panel

Generates a plot of the estimated impulse response functions from the panel model results. Requires the 'results_panel' object from the previous estimation step.

```r
## Plot irfs
#  plot(results_panel)
#
```

--------------------------------

### Estimate and Visualize Non-linear Local Projections

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_nl

Estimates a non-linear local projection model and generates diagnostic plots and summaries.

```R
results_nl    <- lp_nl(endog_data,
                                lags_endog_lin  = 4,
                                lags_endog_nl   = 3,
                                trend           = 0,
                                shock_type      = 1,
                                confint         = 1.96,
                                hor             = 24,
                                switching       = switching_data,
                                use_hp          = TRUE,
                                lambda          = 1600,
                                gamma           = 3)

# Show all plots
 plot(results_nl)

# Make and save all plots
 nl_plots <- plot_nl(results_nl)

# Save plots based on states
 s1_plots <- sapply(nl_plots$gg_s1, ggplotGrob)
 s2_plots <- sapply(nl_plots$gg_s2, ggplotGrob)

# Show first irf of each state
  plot(s1_plots[[1]])
  plot(s2_plots[[1]])

# Show diagnostics. The first element correponds to the first shock variable.
 summary(results_nl)
```

--------------------------------

### lp_lin_iv

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_lin_iv

Compute linear impulse responses with identified shock and/or with 2SLS.

```APIDOC
## lp_lin_iv

### Description
Compute linear impulse responses with identified shock and/or with 2SLS.

### Parameters
- **endog_data** (data.frame) - Required - The values of the dependent variable(s).
- **shock** (data.frame) - Optional - One column data.frame including the variable to shock with.
- **cumul_mult** (boolean) - Optional - Estimate cumulative multipliers (default: FALSE).
- **instrum** (data.frame) - Optional - Instrument(s) to use for 2SLS.
- **use_twosls** (boolean) - Optional - Use two stage least squares (default: FALSE).
- **lags_endog_lin** (integer) - Optional - Number of lags for endog_data.
- **exog_data** (data.frame) - Optional - Exogenous variables.
- **lags_exog** (integer) - Optional - Number of lags for exogenous data.
- **contemp_data** (data.frame) - Optional - Exogenous data with contemporaneous impact.
- **lags_criterion** (character) - Optional - Lag length criteria ('AICc', 'AIC', or 'BIC').
- **max_lags** (integer) - Optional - Maximum number of lags.
- **trend** (integer) - Optional - Trend specification (0: none, 1: trend, 2: trend and quadratic).
- **confint** (double) - Optional - Width of confidence bands.
- **use_nw** (boolean) - Optional - Use Newey-West standard errors (default: TRUE).
- **nw_lag** (integer) - Optional - Maximum lag for Newey-West estimator.
- **nw_prewhite** (boolean) - Optional - Pre-whiten estimators (default: FALSE).
- **adjust_se** (boolean) - Optional - Finite sample adjustment for covariance matrix (default: FALSE).
- **hor** (integer) - Optional - Number of horizons.
- **num_cores** (integer) - Optional - Number of cores to use.

### Response
- **irf_lin_mean** (matrix) - The impulse responses.
- **irf_lin_low** (matrix) - Lower confidence bands.
- **irf_lin_up** (matrix) - Upper confidence bands.
- **specs** (list) - Properties of endog_data and estimation details.
```

--------------------------------

### Summarize lpirfs_nl_obj

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/summary.lpirfs_nl_obj

Use this S3 method to generate a summary for nonlinear lpirfs objects. Ensure an object of type 'lpirfs_nl_obj' is provided.

```R
summary(object, ...)
```

--------------------------------

### Usage of create_lin_data

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/create_lin_data

Call this function with a list of specifications and a data frame of dependent variables.

```R
create_lin_data(specs, endog_data)
```

--------------------------------

### Usage of create_nl_data

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/create_nl_data

The function requires a list of specifications and a data frame of endogenous variables to return the necessary matrices for model estimation.

```R
create_nl_data(specs, endog_data)
```

--------------------------------

### lp_nl: Compute nonlinear impulse responses

Source: https://www.rdocumentation.org/packages/lpirfs/versions/0.2.5/topics/lp_nl

Computes nonlinear impulse responses with local projections. Supports state separation via smooth transition functions or dummy variables.

```APIDOC
## lp_nl: Compute nonlinear impulse responses

### Description
Compute nonlinear impulse responses with local projections by Jordà (2005). The data can be separated into two states by a smooth transition function as applied in Auerbach and Gorodnichenko (2012), or by a simple dummy approach.

### Usage
```R
lp_nl(
  endog_data,
  lags_endog_lin = NULL,
  lags_endog_nl = NULL,
  lags_criterion = NaN,
  max_lags = NaN,
  trend = NULL,
  shock_type = NULL,
  confint = NULL,
  use_nw = TRUE,
  nw_lag = NULL,
  nw_prewhite = FALSE,
  adjust_se = FALSE,
  hor = NULL,
  switching = NULL,
  lag_switching = TRUE,
  use_logistic = TRUE,
  use_hp = NULL,
  lambda = NULL,
  gamma = NULL,
  exog_data = NULL,
  lags_exog = NULL,
  contemp_data = NULL,
  num_cores = 1
)
```

### Value
A list containing:
- **irf_s1_mean** (array): A three-dimensional array containing all impulse responses for all endogenous variables of the first state. The last dimension denotes the shock variable. The row in each matrix denotes the responses of the _ith_ variable, ordered as in _endog_data_. The columns are the horizons.
- **irf_s1_low** (array): A three-dimensional array containing all lower confidence bands of the impulse responses, based on robust standard errors by Newey and West (1987). Properties are equal to _irf_s1_mean_.
- **irf_s1_up** (array): A three-dimensional array containing all upper confidence bands of the impulse responses, based on robust standard errors by Newey and West (1987). Properties are equal to _irf_s1_mean_.
- **irf_s2_mean** (array): A three-dimensional array containing all impulse responses for all endogenous variables of the second state. The last dimension denotes the shock variable. The row in each matrix denotes the responses of the _ith_ variable, ordered as in _endog_data_. The columns denote the horizon.
- **irf_s2_low** (array): A three-dimensional array containing all lower confidence bands of the responses, based on robust standard errors by Newey and West (1987). Properties are equal to _irf_s2_mean_.
- **irf_s2_up** (array): A three-dimensional array containing all upper confidence bands of the responses, based on robust standard errors by Newey and West (1987). Properties are equal to _irf_s2_mean_.
- **specs** (list): A list with properties of _endog_data_ for the plot function. It also contains lagged data (_y_nl_ and _x_nl_) used for the IRF estimations, and the selected lag lengths when an information criterion has been used.
- **fz** (vector): A vector containing the values of the transition function `F(z	_{t-1})`.
```
Tokens:
Raw