You are on page 1of 6

Econometrics Toolbox

Model and analyze financial and economic systems using statistical methods
Econometrics Toolbox provides functions for modeling economic data. You can select and calibrate
economic models for simulation and forecasting. For time series modeling and analysis, the toolbox
includes univariate ARMAX/GARCH composite models with several GARCH variants,
multivariate VARMAX models, and cointegration analysis. It also provides methods for modeling
economic systems using state-space models and for estimating using the Kalman filter. One can use
a variety of diagnostic functions for model selection, including hypothesis, unit root, and
stationarity tests.

Data Preprocessing
Format, plot, and transform time series data

Classes
LagOp Create lag operator polynomial (LagOp) object

Functions
filter
hpfilter
price2ret
ret2price
recessionplot
isStable
reflect
toCellArray

Apply lag operator polynomial to filter time series


Hodrick-Prescott filter for trend and cyclical components
Convert prices to returns
Convert returns to prices
Overlay recession bands on a time series plot
Determine stability of lag operator polynomial
Reflect lag operator polynomial coefficients around lag zero
Convert lag operator polynomial object to cell array

Time Series Regression Models


Regression models with ARIMA errors and robust standard errors

Classes
regARIMA Create regression model with ARIMA time series errors

Functions
Create Model
regARIMA Create regression model with ARIMA time series errors
arima
Convert regression model with ARIMA errors to ARIMAX model

Fit Model to Data


estimate
hac
fgls
infer
print

Estimate parameters of regression models with ARIMA errors


Heteroscedasticity and autocorrelation consistent covariance estimators
Feasible generalized least squares
Infer innovations of regression models with ARIMA errors
Display estimation results for regression models with ARIMA errors

Generate Simulations and Impulse Responses


simulate Monte Carlo simulation of regression model with ARIMA errors
filter
Filter disturbances through regression model with ARIMA errors
impulse Impulse response of regression model with ARIMA errors

Generate Minimum Mean Square Error Forecasts


forecast Forecast responses of regression model with ARIMA errors

Conditional Mean Models


Autoregressive (AR), moving average (MA), ARMA, ARIMA, ARIMAX, and seasonal models

Classes
arima Create ARIMA or ARIMAX time series model
LagOp Create lag operator polynomial (LagOp) object

Functions
Create Model
arima
Create ARIMA or ARIMAX time series model
LagOp
Create lag operator polynomial (LagOp) object
arma2ar Convert ARMA model to AR model

arma2ma Convert ARMA model to MA model

Fit Model to Data


estimate Estimate ARIMA or ARIMAX model parameters
infer
Infer ARIMA or ARIMAX model residuals or conditional variances
print
Display parameter estimation results for ARIMA or ARIMAX models

Generate Simulations or Impulse Responses


simulate
filter
impulse
armairf

Monte Carlo simulation of ARIMA or ARIMAX models


Filter disturbances using ARIMA or ARIMAX model
Impulse response function
Generate ARMA model impulse responses

Generate Minimum Mean Square Error Forecasts


forecast Forecast ARIMA or ARIMAX process

Multivariate Models
Vector autoregressive (VAR), cointegration, and vector error correction (VEC) models

Functions
Create Model
vgxset Set VARMAX model specification parameters
vgxget Get VARMAX model specification parameters

Convert Between Models


arma2ar
arma2ma
var2vec
vec2var

Convert ARMA model to AR model


Convert ARMA model to MA model
Convert VAR model to VEC model
Convert VEC model to VAR model

Fit Model to Data


vgxvarx
vgxinfer
vgxdisp
vgxplot

Estimate VARX model parameters


Infer VARMAX model innovations
Display VARMAX model parameters and statistics
Plot VARMAX model responses

Test Model
vgxqual Test VARMAX model for stability/invertibility
egcitest Engle-Granger cointegration test

jcitest Johansen cointegration test


jcontest Johansen constraint test

Generate Simulations or Impulse Responses


vgxsim Simulate VARMAX model responses
vgxproc Generate VARMAX model responses from innovations
armairf Generate ARMA model impulse responses

Generate Minimum Mean Square Error Forecasts


vgxpred Forecast VARMAX model responses

State-Space Models
Time-invariant or time-varying, linear, Gaussian state-space models
State-space models specify the structure of unobserved dynamic processes, and the composition of
the processes into observations. Econometrics Toolbox state-space functionality accommodates
time-invariant or time-varying linear state-space models containing mean-zero Gaussian state
disturbances and observation innovations. The initial state distributions can be stationary, constant,
or diffuse.
One can create a standard or diffuse state-space model using ssm or dssm, respectively. After
creating a state-space model, one can estimate any unknown parameters using time-series data,
obtain filtered states, smooth states, or generate forecasts. To filter and smooth states, Econometrics
Toolbox implements the standard or diffuse Kalman filter.
Standard State-Space Model
States that have finite initial state variances
Diffuse State-Space Model
States that can have infinite initial variances

Standard State-Space Model


States that have finite initial state variances

Classes
ssm Create state-space model

Functions

Create Model
ssm Create state-space model
disp Display summary information for state-space model

Fit Model to Data


estimate Maximum likelihood parameter estimation of state-space models
refine
Refine initial parameters to aid state-space model estimation

Estimate State Variables


filter Forward recursion of state-space models
smooth Backward recursion of state-space models

Generate Monte Carlo Simulations


simulate Monte Carlo simulation of state-space models
simsmooth State-space model simulation smoother

Generate Minimum Mean Square Error Forecasts


forecast Forecast states and observations of state-space models

Diffuse State-Space Model


States that can have infinite initial variances

Classes
dssm Create diffuse state-space model

Functions
Create Model
dssm Create diffuse state-space model
disp Display summary information for diffuse state-space model

Fit Model to Data


estimate Maximum likelihood parameter estimation of diffuse state-space models
refine
Refine initial parameters to aid diffuse state-space model estimation

Estimate State Variables


filter Forward recursion of diffuse state-space models
smooth Backward recursion of diffuse state-space models

Generate Minimum Mean Square Error Forecasts


forecast Forecast states and observations of diffuse state-space models

You might also like