Learn R Programming

⚠️There's a newer version (1.3.1) of this package.Take me there.

MultiATSM (version 1.0.0)

Multicountry Term Structure of Interest Rates Models

Description

Estimation routines for several classes of affine term structure of interest rates models. All the models are based on the single-country unspanned macroeconomic risk framework from Joslin, Priebsch, and Singleton (2014, JF) . Multicountry extensions such as the ones of Jotikasthira, Le, and Lundblad (2015, JFE) , Candelon and Moura (2023, EM) , and Candelon and Moura (Forthcoming, JFEC) are also available.

Copy Link

Version

Install

install.packages('MultiATSM')

Monthly Downloads

324

Version

1.0.0

License

GPL-2 | GPL-3

Maintainer

Rubens Moura

Last Published

October 15th, 2024

Functions in MultiATSM (1.0.0)

Check_comparison__OLS

check whether mean/median of OLS is close to actual OLS estimates

Build the GVAR(1) from the country-specific VARX(1,1,1)

CheckInputsGVAR

Check consistency of the inputs provided in GVARinputs

BuildATSM_RiskFactors

Builds the time series of the risk factors that are used in the estimation of the ATSM

Build the time-series of bond yields for each bootstrap draw

Build country-specific link matrices

Check_label_consistency

Check consistency of labels (economies, domestic and global variables)

CheckInputsForMLE

Check consistence of inputs

CleanOrthoJLL_Boot

Clean unnecessary outputs of JLL models in the bootstrap setup

Data: Risk Factors for the GVAR - Candelon and Moura (2023)

Prepare the factor set for GVAR models (Bootstrap version)

Compute_BnX_AnX

Compute the latent loading AnX and BnX

Check consistency of the inputs provided in JLL-based models

DataForEstimation

Retrieves data from Excel and build the database used in the model estimation

EstimationSigma_GVARrest

Estimate numerically the variance-covariance matrix from the GVAR-based models

Convert2JordanForm

Convert a generic matrix to its Jordan form

EstimationSigma_Ye

Estimate numerically the Cholesky-factorization from the JLL-based models

FEVDs after bootstrap for "joint Q" models

FEVDandGFEVDbs_sepQ

Creates the confidence bounds and the graphs of FEVDs and GFEVDs after bootstrap ("sep Q" models)

Gather data of several countries in a list. Particularly useful for GVAR-based setups (Compute "GVARFactors")

FEVDgraphsJLLOrtho

FEVDs graphs for orthogonalized risk factors of JLL-based models

FEVDjointOrthogoJLL_BS

FEVDs after bootstrap for JLL-based models

mean of the llk function used in the estimation of the selected ATSM

Preliminary checks for inputs provided for the performing out-of-sample forecasting

CholRestrictionsJLL

Impose the zero-restrictions on the Cholesky-factorization from JLL-based models.

FEVDs for "joint Q" models

Mean of the llk function used in the estimation of the selected ATSM

Generates forecasts of bond yields for all model types

Set up the vector-valued objective function (Point estimate)

FolderCreationPoint

Creates the folders and the path in which the graphical outputs are stored (point estimate version)

GFEVDgraphsJLLOrtho

GFEVDs graphs for orthogonalized risk factors of JLL-based models

Performs state rotations

FEVDjointOrthogoJLL

Orthogonalized FEVDs for JLL models

Data: Risk Factors for the GVAR - Candelon and Moura (forthcoming, JFEC)

FEVDs after bootstrap for "sep Q" models

Model fit graphs for ("sep Q" models)

FEVDgraphsJoint

FEVDs graphs for ("joint Q" models)

FolderCreationBoot

Creates the folders and the path in which the graphical outputs are stored (Bootstrap version)

FEVDs for "sep Q" models

GFEVDjointOrthoJLL_BS

GFEVDs after bootstrap for JLL-based models

FEVDandGFEVDbs_jointQ_Ortho

Creates the confidence bounds and the graphs of FEVDs and GFEVDs after bootstrap (JLL-based models)

GFEVDs after bootstrap for "joint Q" models

FEVDandGFEVDbs_jointQ

Creates the confidence bounds and the graphs of FEVDs and GFEVDs after bootstrap ("joint Q" models)

DomesticMacroVar

Data: Risk Factors - Candelon and Moura (forthcoming, JFEC)

GIRFgraphsJLLOrtho

GIRFs graphs for orthogonalized risk factors of JLL-based models

Gen_Artificial_Series

Generate artificial time-series in the bootstrap setup

GaussianDensity

computes the density function of a gaussian process

GIRFjointOrthoJLL

Orthogonalized GIRFs for JLL models

GIRFgraphsJoint

GIRFs graphs for ("joint Q" models)

Factors_NonOrtho

Makes the pre-allocation of the factors set for JLL-based models

Compute the Feedback matrix of each bootstrap draw

Generate the variable labels of the JLL models

GFEVDs after bootstrap for "sep Q" models

GIRFs graphs for ("sep Q" models)

Generate the factor labels for models estimated on a country-by-country bases

GFEVDs for "sep Q" models

GFEVDs graphs for ("sep Q" models)

GFEVDgraphsJoint

GFEVDs graphs for "joint Q" models

GIRFjointOrthoJLL_BS

GIRFs after bootstrap for JLL-based models

BUild the B loadings

GetPdynPara_NoBC

Compute P-dynamics parameters without using the bias correction method from BRW (2012)

GetYields_AllCountries

Gather all country-specific yields in a single matrix of dimension CJ x T

FEVDs graphs for ("sep Q" models)

IRFandGIRFbs_jointQ_Ortho

Creates the confidence bounds and the graphs of IRFs and GIRFs after bootstrap (JLL-based models)

Compute Sigmas/Cholesky factorizations

GFEVDjointOrthoJLL

Orthogonalized GFEVDs for JLL models

GVAR_PrepFactors

Prepare risk factors for the estimation of the GVAR model

Compute the feedback matrix from a GVAR model with global factors

GFEVDs for "joint Q" models

GIRFs for "sep Q" models

Estimates a GVAR(1) and a VARX(1,1,1) models

GeneralMLEInputs

Gathers the general inputs for model estimation

FeedbackMatrixRestrictionsJLL

Set the zero-restrictions on the feedback matrix of JLL's P-dynamics

GIRFs after bootstrap for "sep Q" models

IRFs after bootstrap for "sep Q" models

IRFandGIRFbs_sepQ

Creates the confidence bounds and the graphs of IRFs and GIRFs after bootstrap ("sep Q" models)

Gen_Forecast_Yields

compute the bond yield forecast for any model type

Model fit graphs for ("joint Q" models)

GIRFs for "joint Q" models

GIRFs after bootstrap for "joint Q" models

IRFs graphs for ("joint Q" models)

IRFgraphsJLLOrtho

IRFs graphs for orthogonalized risk factors of JLL-based models

Find the indexes of the spanned factors

MarginalModelPara

Estimate the marginal model for the global factors

IRFs for "joint Q" models

Get the intercept, feedback matrix and the variance-covariance matrix from GVAR without global factors

Compute the maximum likelihood function of all models

Generates the labels factors

IRFs graphs for ("sep Q" models)

Generate the labels of the spanned factors

Generates several inputs that are necessary to build the likelihood function

Compute the parameters used in the P-dynamics of the model

Data: Risk Factors - Candelon and Moura (2023)

Obtain the indexes of both the domestic and global unspanned factors

Extract the indexes related to the spanned factors in the variance-covariance matrix

InputsForOutputs

Collects the inputs that are used to construct the numerical and the graphical outputs

Gather_Forecasts

Gather several forecast dates

Prepare outputs to export after the model optimization

Perform out-of-sample forecast of bond yields

Compute the B matrix of loadings

Obtain the non-orthogonalized model parameters

Estimate the risk-neutral feedbak matrix K1Q using linear regressions

Compute the root mean square error ("sep Q" models)

VAR(1) with orthogonalized factors (JLL models)

Compute the A loadings

OutputConstructionJoint

Numerical outputs (variance explained, model fit, IRFs, GIRFs, FEVDs, GFEVDs and risk premia decomposition) for "joint Q" models

Compute r0 for the various models

IRFjointOrthoJLL_BS

IRFs after bootstrap for JLL-based models

Compute the log-likelihood function

IRFjointOrthoJLL

Orthogonalized IRFs for JLL models

Get_SigmaYields

Compute the variance-covariance matrix of the bond yields

Collect both the domestic and global unspanned factors of all countries in single matrices

Compute P-dynamics parameters using the bias correction method from BRW (2012)

TPDecompGraphSep

Term Premia decomposition graphs for "joint Q" models

Estimates the P-dynamics from JLL-based models

Perform the optimization of the log-likelihood function of the chosen ATSM

Data: Risk Factors - Candelon and Moura (forthcoming, JFEC)

Compute the variance-covariance matrix after the bias correction procedure

Impose stationarity under the Q-measure

TermPremiaDecompJoint

Decomposition of yields into the average of expected future short-term interest rate and risk premia for "joint Q" models

Loads data sets from several papers

Constructs the model numerical outputs (model fit, IRFs, GIRFs, FEVDs, GFEVDs, and risk premia decomposition)

GraphicalOutputs

Generate the graphical outputs for the selected models (Point estimate)

Optimization_PE

Peform the minimization of mean(f)

Data: Yields - Candelon and Moura (forthcoming, JFEC)

Generate the labels of the star variables

Generates the star variables necessary for the GVAR estimation

YieldsFitAllJoint

Fit yields for all maturities of interest

IDXZeroRestrictionsJLLVarCovOrtho

Find the indexes of zero-restrictions from the orthogonalized variance-covariance matrix from the JLL-based models

NumOutputs_Bootstrap

Numerical outputs (IRFs, GIRFs, FEVD, and GFEVD) for bootstrap

Obtain the country-specific a0

Transform a number bounded between a lower bound and upper bound to x by:

Eliminates the @

Build the log-likelihood function of the P-dynamics from the JLL-based models

OutputConstructionSep

Numerical outputs (variance explained, model fit, IRFs, GIRFs, FEVDs, GFEVDs, and risk premia decomposition) for "sep Q" models

Compute the square root of a matrix

Check whether one element is a subset of another element

OutputConstructionJoint_BS

Gathers all the model numerical ouputs after bootstrap for "joint Q" models

Map constrained parameters b to unconstrained auxiliary parameters a.

ParaATSM_opt_ALL

Update the list of parameters

Create the variable labels used in the estimation

OptimizationSetup_ATSM

Optimization routine for the entire selected ATSM

RiskFactorsPrep

Builds the complete set of time series of the risk factors (spanned and unspanned)

RiskFactorsGraphs

Spanned and unspanned factors plot

Reg__OLSconstrained

Restricted OLS regression

Estimates a standard VAR(1)

Update the variance-covariance matrix from the "JLL joint Sigma" model. Necessary for optimization

TPDecompGraphJoint

Term Premia decomposition graphs for "joint Q" models

Computes two measures of model fit for bond yields

TermPremiaDecompSep

Decomposition of yields into the average of expected future short-term interest rate and risk premia for "joint Q" models

Data: Trade Flows - Candelon and Moura (forthcoming, JFEC)

VarianceExplainedSep

Percentage explained by the spanned factors of the variations in the set of observed yields for "sep Q" models

Exclude series that contain NAs

Efficient computation of matrix product for arrays

Compile the bond yield forecast for any model type

residY_original

Compute the residuals from the observational equation

Estimate a VAR(1) - suited to Bauer, Rudebusch and Wu (2012) methodology

Computes numerical first order derivative of f(x)

IRFandGIRFbs_jointQ

Creates the confidence bounds and the graphs of IRFs and GIRFs after bootstrap ("joint Q" models)

computes the logarithm of determinant of a matrix A

Map auxiliary (unconstrained) parameters a to constrained parameters b

IRFs after bootstrap for "joint Q" models

Find mean or median of OLS when DGP is VAR(1)

multiprod_2terms

computes matrix product for arrays a and b: c[,,i] = a[,,i] b[,,i]

Inverts an array of matrices so that: inva[,,i] = inv(a[,,i])

Inverse each 2D slice of an array (M) with arbitrary dimensions support

Extract the parameter values from varargin

Killan's VAR stationarity adjustment

IRFs for "sep Q" models

Computes two measures of model fit for bond yields

Obtain the auxiliary values corresponding to each parameter, its size and its name

YieldsFitAllSep

Fit yields for all maturities of interest

OutputConstructionSep_BS

Gathers all the model numerical ouputs after bootstrap for "sep Q" models

Create a vector of numerical maturities in years

Outputs2exportMLE

Prepares inputs to export

pca_weights_one_country

Weight matrix from principal components

Replications of the JPS (2014) outputs by the MultiATSM package

Get coefficients from the orthogonalized regressions

Transform a positive number y to back to x by:

Compute some key parameters from the P-dynamics (Bootstrap set)

Transition_Matrix

Computes the transition matrix required in the estimation of the GVAR model

SpecificMLEInputs

Concatenate the model-specific inputs in a list

Estimate a VARX(1,1,1)

SpannedFactorsSepQ

Gather all spanned factors ("sep Q" models)

ResampleResiduals_BS

Compute the residuals from the original model

Spanned_Factors

Computes the country-specific spanned factors

SpannedFactorsjointQ

Gather all spanned factors ("joint Q" models)

Data: Risk Factors - Candelon and Moura (forthcoming, JFEC)

Data: Trade Flows - Candelon and Moura (2023)

f_with_vectorized_parameters

Use function f to generate the outputs from a ATSM

Compute the root mean square error ("joint Q" models)

Transform x to a positive number by: y = log(e^x + 1)

Transform x to a number bounded btw lb and ub by:

Generate M data sets from VAR(1) model

VarianceExplainedJoint

Percentage explained by the spanned factors of the variations in the set of observed yields for "joint Q" models

Inverse the (m,m,T) array of matrices for m<=4

Inverse each 2D slice of an array (M) with arbitrary dimensions support

converts the vectorized auxiliary parameter vector x to the parameters that go directly into the likelihood function.

Compute the cross-section loadings of yields of a canonical A0_N model

Bias_Correc_VAR

Estimates an unbiased VAR(1) using stochastic approximation (Bauer, Rudebusch and Wu, 2012)

Generates the bootstrap-related outputs

BUnspannedAdapSep

Transform B_spanned into B_unspanned for sepQ models

BUnspannedAdapSep_BS

Obtain the full form of B unspanned for "sep Q" models within the bootstrap setting

BootstrapBoundsSet

Builds the confidence bounds and graphs (Bootstrap set)

AdjustYieldsDates

Makes sure that the time series of yields and risk factors have coincident sample spans

BuildRiskFactors_BS

Build the time-series of the risk factors in each bootstrap draw

BUnspannedAdapJoint

Transform B_spanned into B_unspanned for jointQ models

Gathers the estimate of the bootstrap draws

Replications of the JPS (2014) outputs by Bauer and Rudebusch (2017)