NumXL

NumXL is a Microsoft Excel Add-in for econometrics and financial time series analytics.

NumXL User's Interface

NumXL comes with an elaborate user-interface (i.e. menu and toolbar), and interactive wizards to improve the general usability of the software. The NumXL UI components automate the common process/steps of a time series analysis and modeling.

Using the UI components and the wizards, the user specifies the time series of interest, fine-tune the desired analysis options and specify the location on his/her worksheet for the output. NumXL generates the corresponding analysis blocks (with underlying formulas) in the designated location

Function Categories

NumXL Functions are organized into four categories:

Statistical Tests Functions

• Hypothesis Test for population mean, for standard deviation, for skew and for excess kurtosis.
• Normality test using Jarque–Bera test, Shapiro–Wilk_test, and Chi-square test methods.
• White-noise test - Serial correlation tests (Portmanteau Test, Ljung-Box test and modified Q-test).
• Autoregressive Conditional Heteroskedacity (ARCH) effect test.

Linear Time Series

• Basic Operators - Difference, Lag, Add, Subtract, scale, and time-reverse operators.
• Autocorrelation (ACF) and partial autocorrelation (PACF) - ACF, PACF, ACF/PACF confidence interval limits, and ACF/PACF tests.
• Cross-correlation Functions - XCF and EWXCF
• ARMA/ARIMA model - Log-likelihood function, AICc, standardized residuals, model stability test, forecast values and confidence limits, etc.
• Generalized Linear Model (GLM) - Calibration, parameters' estimate errors, residuals, fitted values

ARCH/GARCH Analysis

• Basic Operators - EWMA/EWV
• General autoregressive conditional heteroskedacity (GARCH) Model - Log likelihood function, AICC, standardized residuals, model stability test, conditional mean/volatility forecast and confidence limits, etc.
• Exponential GARCH (EGARCH) Model - Log likelihood function, AICC, standardized residuals, model stability test, conditional mean/volatility forecast and confidence limits, etc.
• GARCH in the mean (GARCH-M) Model - Log likelihood function, AICC, standardized residuals, model stability test, conditional mean/volatility forecast and confidence limits, etc.

Advanced (Mixed) Models

• Model Definition Function - Mixed modeling.
• Mixed Model - likelihood function, Akaike's Information Criterion(AIC), standardized residuals, model stability test, forecast values and confidence limits, etc.

Utilities

• Interpolation Functions - Flat forward/backward, linear, and cubic spline interpolation.
• Time series Functions - Remove missing values from a time series.
• Statistical Functions - Calculate excess-kurtosis for a GED and Student's t-dist.

History

• Version 1.0 Alpha: released, April 15, 2009
• Version 1.0 Beta: released, June 30th, 2009
• Version 1.0 RC: released, July 24, 2009
• Version 1.0 : released, October 1, 2009

See also

• EViews -- A statistical package for Windows
• gretl -- an open source alternative to EViews
• Rcmdr -- an open source R-based alternative to SPSS
• OxMetrics -- an alternative econometrics package
• RATS
• Comparison of statistical packages
• AREMOS

External links

• NumXL Home page
• NumXL Release notes

id:NumXL