Main Content

Data Sets and Examples

Econometrics Toolbox™ includes historical data sets and featured examples. Data sets include a diverse collection of macroeconomic time series for use with model estimation and testing. Featured examples use the data sets to demonstrate common workflows in econometric analysis and explore connections among related toolbox functions.

Generally, each data set is a MAT file containing the following variables:

  • Data — A matrix of data. Each column is a variable (time series). Each row contains associated observations of the variables.

  • DataTable — A table of data. DataTable contains the same observations and has the same dimensionality as Data.

  • DataTimeTable — A timetable of data. DataTimeTable contains the same observations and has the same dimensionality as Data.

  • Description — Textual data set description, including data set variable definitions and references.

  • series — Vector of descriptive variable names.

To load variables of a data set into the workspace, enter the following command at the command line, where DataSetName is one of the MAT files in the table.

load DataSetName

Data Set NameDescription
Data_AccidentalMonthly number of accidental deaths in the U.S., 1973–1978
Data_AirlineMonthly number of international airline passengers, 1949–1960
Data_CanadaCanadian inflation and interest rates, 1954–1994
Data_ConsumptionUS food consumption, 1927–1962
Data_CreditDefaultsInvestment-grade corporate bond defaults and four predictors, 1984–2004
Data_DanishDanish stock returns, bond yields, 1922–1999
Data_DieboldLiU.S. Treasury unsmoothed Fama-Bliss zero-coupon yields and macroeconomic factors, 1972–2000
Data_ElectricityPricesSimulated daily electricity spot prices, 2010–2013
Data_EquityIdxU.S. equity indices, 1990–2001
Data_FXRatesCurrency exchange rates, 1979–1998
Data_GDPU.S. Gross Domestic Product, 1947–2005
Data_GlobalIdx1Global large-cap equity indices, 1993–2003
Data_GNPU.S. Gross National Product, 1947–2005
Data_Income1Simulated data on income and education
Data_Income2Average annual earnings by educational attainment in eight workforce age categories
Data_JAustralianJohansen's Australian data, 1972–1991
Data_JDanishJohansen's Danish data, 1974–1987
Data_MarkPoundDeutschmark/British Pound foreign-exchange rate, 1984–1991
Data_NelsonPlosserMacroeconomic series of Nelson and Plosser, 1860–1970
Data_OvershortDaily overshorts from an underground gasoline tank in Colorado. 57 consecutive days
Data_PowerConsumptionCanadian electrical power consumption and GDP, 1960–2009
Data_RecessionsU.S. recession start and end dates, 1857–2022
Data_SchwertMacroMacroeconomic series of Schwert, 1947–1985
Data_SchwertStockIndices of U.S. stock prices, 1871–2008
Data_TBillThree-month U.S. treasury bill secondary market rates, 1947–2005
Data_USEconModelU.S. macroeconomic series, 1947–2009
Data_USEconVECModelU.S. macroeconomic series 1957–2016 and projections for the following 10 years from the Congressional Budget Office

To open the script of an Econometrics Toolbox featured example, enter the following command at the command line, where ExampleName is an example name in the table.

openExample('econ/ExampleName')

Example NameTitleDescription
AnalyzeLinearizedDSGEModelsExampleAnalyze Linearized DSGE ModelsAnalyze the dynamic stochastic general equilibrium (DSGE) model in [69] by using Bayesian state-space model tools.
Demo_ClassicalTestsClassical Model Misspecification TestsPerform classical model misspecification tests.
Demo_DieboldLiModelApply State-Space Methodology to Analyze Diebold-Li Yield Curve ModelAnalyze the popular Diebold-Li yields-only and yields-macro models of monthly yield-curve time series derived from U.S. Treasury bills and bonds by using state-space models and the Kalman filter.
Demo_HPFilter Use Hodrick-Prescott Filter to Reproduce Original ResultUse the Hodrick-Prescott filter to reproduce their original result
Demo_RiskFHSUsing Bootstrapping and Filtered Historical Simulation to Evaluate Market RiskUse bootstrapping and filtered historical simulation to evaluate market risk
Demo_RiskEVTUsing Extreme Value Theory and Copulas to Evaluate Market RiskUse extreme value theory and copulas to evaluate market risk
Demo_TSReg1Time Series Regression I: Linear ModelsIntroduce basic assumptions behind multiple linear regression models
Demo_TSReg2Time Series Regression II: Collinearity and Estimator VarianceDetect correlation among predictors and accommodating problems of large estimator variance
Demo_TSReg3Time Series Regression III: Influential ObservationsDetect influential observations in time series data and accommodating their effect on multiple linear regression models
Demo_TSReg4Time Series Regression IV: Spurious RegressionInvestigate trending variables, spurious regression, and methods of accommodation in multiple linear regression models
Demo_TSReg5Time Series Regression V: Predictor SelectionSelect a parsimonious set of predictors with high statistical significance for multiple linear regression models
Demo_TSReg6Time Series Regression VI: Residual DiagnosticsEvaluate model assumptions and investigating respecification opportunities by examining the series of residuals
Demo_TSReg7Time Series Regression VII: ForecastingPresent the basic setup for producing conditional and unconditional forecasts from multiple linear regression models
Demo_TSReg8Time Series Regression VIII: Lagged Variables and Estimator BiasExamine how lagged predictors affect least-squares estimation of multiple linear regression models
Demo_TSReg9Time Series Regression IX: Lag Order SelectionIllustrate predictor history selection for multiple linear regression models
Demo_TSReg10Time Series Regression X: Generalized Least Squares and HAC EstimatorsEstimate multiple linear regression models of time series data in the presence of heteroscedastic or autocorrelated innovations
Demo_USEconModelModel the United States EconomyModel the U.S. economy using a VEC model as a linear alternative to the Smets-Wouters DSGE macroeconomic model
ModelAndSimulateElectricitySpotPricesUsingSkewNormalExampleModel and Simulate Electricity Spot Prices Using the Skew-Normal DistributionSimulate the future behavior of electricity spot prices from a time series model fitted to historical data, and use the skew normal distribution to model the innovations process.

Related Topics