Have a Question?
Phone: +1 (888) 427-9486
+1 (312) 324-0367
Fax: +1 (312) 238-9092
Or use our Contact Form
NumXL
NumXL
 |
NumXL is an econometric and time series analysis Excel Add-in. With NumXL, you can conduct your own time series analysis, diagnose a model’s residuals and make forecasts all in Microsoft Excel and using only the NumXL Add in. |   |
Description
NumXL is a powerful Excel Add-in that provides users with an intuitive solution for time series analysis, econometrics, and forecasting.
NumXL wraps common mundane calculations such as auto-correlation, log-likelihood, model fitting/calibration, residuals diagnosis, forecasting and much more, into a simple extension of Excel. You can use this time series' analysis functions via Excel menus, entering them directly into your workbook cells' formulas, or by using the Excel function wizard. Once a spreadsheet is created with NumXL functions for a data set, running the same analysis with different data (or the same but with new observations) is as simple as copying and pasting.
As a result, NumXL does the data analysis work for you, so you can focus your efforts on devising the proper model, back-testing, examining different scenarios, etc. NumXL's functionality also allows you to present your conclusions/recommendations in a tractable report, which you can share with just the push of a button.
All NumXL functions have been intensively tested against industry standard software models to guarantee users full, reliable results.
Descriptive Statistics
- Population Mean, Variance, Skew, and Excess Kurtosis tests.
- Normality test - Jarque–Bera test, Shapiro–Wilk_test, and Chi-square test methods.
- White-Noise test - Portmanteau test, Ljung-Box test and modified Q-test.
- ARCH Effect test
Time Series Operators
- LAG and Difference operators
- Weighted-Moving Average (WMA)
- Exponential Weighted-Moving Average (EWMA)
- Correlation and Exponential-Weighted Correlation functions
- Autocorrelation and Partial-Autocorrelation functions
Model's Fitting Functions
- Log-Likelihood Function (LLF)
- Akaike Information Criterion (AIC)
- Stability Check
- Residuals diagnosis
Forecast and Back-testing Functions
- In-sample and out-sample forecast
- Mean and confidence interval forecast
- Conditional and term-structure volatility forecast
- Long-run forecast
Models supported
- Autoregressive Moving Average (ARMA, ARIMA and ARMAX)
- AirLine Model
- Generalized Linear Model (GLM)
- Generalized Autoregressive Conditional Heteroskedacity Models (ARCH/GARCH)
- Exponential GARCH
- GARCH in the Mean (GARCH-M)
Lite vs Pro
Still using the Lite version of NumXL? Here's what you are missing!
- A complete, unlocked financial function set
- No nagging screen
- Free updates for one year, plus priority customer service support
- Unlimited mail support
- And more...
Just check the tabs below to see all of the pro functions available when you purchase.
Statistical Testing
| Function | Description | Lite | Pro |
| ARCHTest | Calculates the p-value of the ARCH effect test, that is, white-noise test for the squared time series. | x | |
| NormalityTest | Returns the p-value of the normality test, that is, whether a data set is well-modeled by a normal distribution | x | |
| TEST_MEAN | Calculates the p-value of the statistical test for the population mean | x | x |
| TEST_SKEW | Calculates the p-value of the statistical test for the population skew (i.e. 3rd moment). | x | x |
| TEST_STDEV | Calculates the p-value of the statistical test for the population standard deviation | x | x |
| TEST_XKURT | Calculates the p-value of the statistical test for the population excess kurtosis (4th moment). | x | x |
| WNTest | Computes the p-value of the statistical portmanteau test (whether any of a group of autocorrelations of a time series are different from zero). | x |
Linear Time Series
| Function | Description | Lite | Pro |
| ACF | Calculates the sample autocorrelation function (ACF) of a stationary time series | X | |
| ACFCI | Calculates the confidence interval limits (upper/lower) for the autocorrelation function | X | |
| ACFTest | Calculates the p-value of the statistical test for population autocorrelation function | X | |
| ARMA | Return an array of cells for the packed form of the given ARMA model | X | |
| ARMA_AIC | Calculates the Akaike's information criterion (AIC) of the given estimated ARMA model (with correction to small sample sizes). | X | |
| ARMA_CALIBRATE | Computes the maximum likelihood estimated (MLE) model's parameters | X | X |
| ARMA_CHECK | Examines the model's parameters for stability constraints (e.g. stationary, etc.). | X | X |
| ARMA_ERRORS | Returns an array of cells for the estimated error/standard deviation of the model's parameters | X | |
| ARMA_FORE | Calculates the out-of-sample conditional mean forecast | X | |
| ARMA_FORECI | Returns the confidence interval limits of the conditional mean forecast | X | |
| ARMA_FORESD | Calculates the estimated error/standard deviation of the conditional mean forecast | X | |
| ARMA_GUESS | Returns an array of cells for the initial/quick guess of the model's parameters | X | X |
| ARMA_LLF | Computes the log-likelohood function (LLF) of the estimated ARMA model | X | |
| ARMA_MEAN | Returns an array of cells for the fitted values of the conditional mean. | X | X |
| ARMA_RESID | Returns an array of cells for the standardized residuals of the given ARMA model | X | X |
| ARMA_VOL | Returns an array of cells for the fitted (in-sample) conditional volatility/standard deviation | X | X |
| ARMAX | Return an array of cells for the packed form of the given ARMAX model. | X | |
| DIFF | Returns an array of cells for the differenced time series. | X | X |
| EWXCF | Computes the correlation factor using the exponential-weighted correlation function (i.e. using exponential weighted covariance (EWCOV) and volatility (EWMA/EWV) method). | X | |
| GLM | Return an array of cells for the packed form of the given GLM model. | X | |
| GLM_CALIBRATE | Calculates the fitted model's coefficients | X | |
| GLM_ERRORS | Returns an array of cells for the estimated error/standard deviation of the model's parameters | X | |
| GLM_MEAN | Calculates the mean value of Y using generalized linear model (GLM). | X | |
| GLM_RESID | Calculates the residuals/errors of the given Generalized linear model (e.g. regression). | X | |
| LAG | Returns an array of cells for the backshifted/lagged time series | X | X |
| PACF | Caluculates the sample partial autocorrelation function (PACF). | X | |
| PACFCI | Returns the confidence interval limits (upper/lower) for the partial auto-correlation function (PACF) | X | |
| TSADD | Returns an array of cells for the sum of a two time series | X | X |
| TSREVERSE | Returns an array of cells for the time-order reversed time series, that is, first onservation becomes the last observation, etc | X | X |
| TSSCALE | Returns an array of cells for the scaled time series | X | X |
| TSSUB | Returns an array of the difference between two time series | X | X |
| WMA | Returns an array of cells for the weighted-moving average time series | X | X |
| XCF | Calculates the cross-correlation function between two time series | X | X |
| AIRLINE_LLF | Calculates the log-likelohood function (LLFi) of the given airline model | X | |
| AIRLINE_AIC | Calculates the Akaike's information criterion (AICi) of the given airline model (with correction to small sample sizes) | X | |
| AIRLINE_CHECK | Examines the model's parameters for stability constraints (e.g. stationary, etc.) | X | |
| AIRLINE_GUESS | Returns an array of cells for the initial/quick guess of the model's parameters | X | |
| AIRLINE_MEAN | Returns an array of cells for the fitted values of the conditional mean | X | |
| AIRLINE_RESID | Returns an array of cells for the standardized residuals of a given airline model. | X | |
| AIRLINE_FORE | Calculates the out-of-sample conditional mean forecast. | X | |
| AIRLINE_FORECI | Returns the confidence interval limits of the conditional mean forecast. | X | |
| AIRLINE_FORESD | Calculates the estimated error/standard deviation of the conditional mean forecast. | X |
GARCH Analysis
| Function | Description | Lite | Pro |
| EWMA | Calculates the estimated value of the exponential weighted volatility (EWV). | X | X |
| GARCH | Return an array of cells for the packed form of the given GARCH model. | X | |
| GARCH_AIC | Calculates the Akaike's information criterion (AIC) of the given estimated GARCH model (with correction to small sample sizes). | X | |
| GARCH_CALIBRATE | Computes the maximum likelihood estimated (MLE) model's parameters. | X | |
| GARCH_CHECK | Examines the model's parameters for stability constraints (e.g. stationary, positive variance, etc.). | X | X |
| GARCH_ERRORS | Returns an array of cells for the estimated error/standard deviation of the model's parameters. | X | |
| GARCH_FORE | Calculates the out-of-sample conditional mean forecast | X | |
| GARCH_FORECI | Returns the confidence interval limits of the conditional mean forecast. | X | |
| GARCH_FORESD | Calculates the estimated error/standard deviation of the conditional mean forecast. | X | |
| GARCH_GUESS | Returns the initial guess of the model parameters. | X | X |
| GARCH_LLF | Computes the log-likelihood function for the fitted model. | X | |
| GARCH_RESID | Returns an array of the standardized residuals for the fitted GARCH model. | X | X |
| GARCH_VL | Calculates the long-run average volatility for the given GARCH model. | X | |
| GARCH_VOL | Returns an array of the fitted (in-sample) conditional volatility/standard deviations (sigmas). | X | X |
E-GARCH Analysis
| Function | Description | Lite | Pro |
| EGARCH | Return an array of cells for the packed form of the given E-GARCH model. | X | |
| EGARCH_AIC | Calculates the Akaike's information criterion (AIC) of the given estimated EGARCH model (with correction to small sample sizes). | X | |
| EGARCH_CALIBRATE | Computes the maximum likelihood estimated (MLE) model's parameters. | X | |
| EGARCH_CHECK | Examines the model's parameters for stability constraints (e.g. stationary, positive variance, etc.). | X | X |
| EGARCH_ERRORS | Returns an array of cells for the estimated error/standard deviation of the model's parameters. | X | |
| EGARCH_FORE | Calculates the out-of-sample conditional mean forecast. | X | |
| EGARCH_FORECI | Returns the confidence interval limits of the conditional mean forecast. | X | |
| EGARCH_FORESD | Calculates the estimated error/standard deviation of the conditional mean forecast. | X | |
| EGARCH_GUESS | Returns the initial/quick guess of the model parameters. | X | X |
| EGARCH_LLF | Computes the log-likelihood function for the fitted model. | X | |
| EGARCH_RESID | Returns an array of the standardized residuals for the fitted E-GARCH model. | X | X |
| EGARCH_VL | Calculates the long-run average volatility for the given E-GARCH model | X | |
| EGARCH_VOL | Returns an array of the fitted (in-sample) conditional volatilities/standard deviations. | X | X |
GARCH-M Model
| Function | Description | Lite | Pro |
| GARCHM | Return an array of cells for the packed form of the given GARCH-M model. | X | |
| GARCHM_AIC | Calculates the Akaike's information criterion (AIC) of the given estimated GARCH-M model (with correction to small sample sizes). | X | |
| GARCHM_CALIBRATE | Computes the maximum likelihood estimated (MLE) model's parameters. | X | |
| GARCHM_CHECK | Examines the model's parameters for stability constraints(e.g. stationary, positive variance, etc.). | X | X |
| GARCHM_ERRORS | Returns an array of cells for the estimated error/standard deviation of the model's parameters. | X | |
| GARCHM_FORE | Calculates the out-of-sample conditional mean forecast. | X | |
| GARCHM_FORECI | Returns the confidence interval limits of the conditional mean forecast. | X | |
| GARCHM_FORESD | Calculates the estimated error/standard deviation of the conditional mean forecast. | X | |
| GARCHM_GUESS | Returns the initial guess of the model's parameters. | X | X |
| GARCHM_LLF | Calculates the log-likelihood function for the fitted GARCH-M model. | X | |
| GARCHM_MEAN | Returns an array of the fitted (in-sample) conditional mean values. | X | X |
| GARCHM_RESID | Returns an array for the fitted GARCH-M model standardized residuals. | X | X |
| GARCHM_VL | Calculates the model's long-run average volatility. | X | |
| GARCHM_VOL | Returns an array for the model fitted conditional volatilities/standard deviations. | X | X |
Advanced Models
| Function | Description | Lite | Pro |
| MIXED_MODEL | Return an array of cells for the packed form of the mixed model (i.e. conditional mean and conditional volatility model components). | X | |
| TSM_AIC | Calculates the Akaike's information criterion (AIC) of the given estimated mixed model (with correction to small sample sizes). | X | |
| TSM_CALIBRATE | Computes the maximum likelihood estimated (MLE) model's parameters. | X | |
| TSM_CHECK | Examines the model's parameters for stability constraints (e.g. stationary, positive variance, etc.). | X | |
| TSM_ERRORS | Returns an array of cells for the estimated error/standard deviation of the model's parameters. | X | |
| TSM_FORE | Calculates the out-of-sample conditional mean forecast. | X | |
| TSM_FORECI | Returns the confidence interval limits of the conditional mean forecast. | X | |
| TSM_FORESD | Calculates the estimated error/standard deviation of the conditional mean forecast | X | |
| TSM_LLF | Computes the log-likelihood function for the fitted model. | X | |
| TSM_MEAN | Returns an array of the fitted (in-sample) conditional mean values. | X | |
| TSM_RESID | Returns an array of the standardized residuals for the fitted mixed-model. | X | |
| TSM_VOL | Returns an array of the fitted (in-sample) conditional volatility/standard deviations. | X |
Utilities
| Function | Description | Lite | Pro |
| GED_XKURT | Calculates the excess kurtosis of the generalized error distribution (GED). | X | |
| INTERPOLATE | Returns an array of cells for the interpolated function value(s). | X | |
| RMNA | Returns an array of cells for the time series after removing all missing values. | X | X |
| TDIST_XKURT | Calculates the excess kurtosis of the student's t-distribution. | X | |
| NUMXL_INFO | Returns version and license information for the local NumXL installation. | X | X |
Pricing
General
| Quantity | Full Price | Discount | Final Price | |
|---|---|---|---|---|
| Student | Contact Us | |||
| 1 | $500 | $200 | Buy it now | |
| 2 - 4 | 5% | $190/license | Buy it now | |
| 5 - 9 | 10% | $180/license | Buy it now | |
| 10 - 24 | 20% | $160/license | Buy it now | |
| 25 - 49 | 30% | $140/license | Buy it now | |
| 50 & more |
YOU WILL BE ABLE TO DOWNLOAD THE PRODUCT IMMEDIATELY AFTER ORDERING After you have successfully completed the purchase, payment and verification process, we will send you an e-mail with the full instructions for downloading your fully licensed version of NumXL. 12 MONTHS FULL MAINTENANCE AND SUPPORT - FREE Your original purchase of any Spider product includes all updates, upgrades and support FREE of charge for 12 months from the date of purchase. After that, as a valued customer, you can keep everything current and take advantage of all the latest features that we’re continuing to add to our products by upgrading to the latest version. For more information on our store policies, check our help section. |
Education / Government
A license for student, educational, non-profit, or government users is equivalent to the full-featured commercial license at a special price. The licensee must be a school, university, academic institution, not-for-profit or government organization, or must be a student or employee thereof. Proof of eligibility is required. Please contact us to verify your account and to receive a coupon from us directly that will allow you to purchase NumXL at a discount rate.
| Quantity | Full Price | Discount | Final Price | |
|---|---|---|---|---|
| Student | Contact Us | |||
| 1 | $300 | 25% | $150 | Buy it now |
| 2 - 4 | 30% | $140/license | Buy it now | |
| 5 - 9 | 35% | $130/license | Buy it now | |
| 10 - 24 | 45% | $110/license | Buy it now | |
| 25 - 49 | 55% | $90/license | Buy it now | |
| 50 & more |
YOU WILL BE ABLE TO DOWNLOAD THE PRODUCT IMMEDIATELY AFTER ORDERING After you have successfully completed the purchase, payment and verification process, we will send you an e-mail with the full instructions for downloading your fully licensed version of NumXL. 12 MONTHS FULL MAINTENANCE AND SUPPORT - FREE Your original purchase of any Spider product includes all updates, upgrades and support FREE of charge for 12 months from the date of purchase. After that, as a valued customer, you can keep everything current and take advantage of all the latest features that we’re continuing to add to our products by upgrading to the latest version. For more information on our store policies, check our help section. |
Demos
NumXL Installation & Licensing
Installation & Licensing: A group of videos explaining the program installation and license activation process.
Tips & Tricks
Tips & Tricks Learn tips and tricks to get the most out of NumXL.Resources
Changelog
(January 26th, 2012) - NumXL 1.52.40934.5 - New version
- Revamped support for generalized linear models (GLM):
- Added a new menu, toolbar and Wizard to assist user with GLM construction
- Added support for two new link functions: probit and complementary log-log, for the Binomial GLM
- Added support for calibration using Excel solver.
- Added residual diagnosis and Goodness-of-fit functions (e.g. GLM_LLF, GLM_AIC, GLM_RSQ).
- Fixed an issue in license manager related to network time-out during the activation process.
(January 20th, 2012) - NumXL 1.51.40927.3 - Maintenance release (IV)
- Resolved issues related to regional/international settings on non-English Windows and Microsoft office (e.g. decimal point interpretation, solver add-in listing, etc.
(blog: Issues reported with Spanish version of Excel ) - Resolved an issue related to MS Excel Solver 2010 which yield to sub-optimal calibration. This was due to a new default (introduced for Excel 2010) for Non-negative values constraints.
(FAQ: The calibration with Excel 2010 Solver does not give optimal coefficients.) - Fixed an issue related to missing first constraint (stable model check) in the Excel Solver Dialog Box. This issue related to a limitation on Excel Solver, but we added a workaround for it.
(FAQ: Why does the calibration function in NumXL shows the constraint's rhs of 0.9999?)
(December 30th, 2011) - NumXL 1.51.40907.5 (ORB)- Maintenance release (III)
- Fix for Ticket #901734 - AIRLINE_FORESD over-estimates the forecast errors and the forecast confidence interval.
(November 16th, 2011) - NumXL 1.51.40863.1 (ORB)- Maintenance release (II)
- Minor enhancement and fixes for license activation.
(November 11th, 2011) - NumXL 1.51.40857.1 (ORB)- Maintenance release (I)
- Several Enhancements to the license Manager.
- Minor fixes for license activation for trial and permanent-key users.
(September 23th, 2011) - NumXL 1.51 (ORB) - Maintenance Release
- improvement product diagnosis and troubleshooting
- major enhancement on the license management
- retrieve license key
- generate new license key automatically
- forms made simpler
- integrated with new manual activation form online, for activation code
- various minor fixes
(June 14th, 2011) - NumXL 1.5 (FINAL) - Official Release
Installation- [NEW] (Start Menu) Custom icons, shortcuts
- [NEW] (Start Menu) NumXL is now stored in own folder, rather than under Spider Financial
- [NEW] (Start Menu) License Manager and uninstallation now available
- [NEW] Can detect previous installation (SP3 and lower)
- [NEW] Can detect whether Excel is running before installing or uninstalling
- [REVISED] Installation time and pages have been cut down, enhancing user experience by removing unnecessary steps
- [REVISED] Enhanced installation readability, use, and stability
- [REVISED] Enhanced support for single-user installation
- [UPDATED] New graphics, logo
- [UPDATED] (License Manager) automatically launches at the end of installation, is not dependent on the installation any more (can be launched at a later time)
- [UPDATED] (License Manager) Direct Connection automatically shows license key, if available/activated previously
- [UPDATED] (License Manager) Manual Activation includes license key, if available, and machine ID
- [FIXES] Miscellaneous code fixes and enhancements
- [REMOVED] Documentation and case-studies from installation, moved to website
User Interface (UI)
- [NEW] Airline, Forecast Models
- [NEW] Nag Window
- [NEW] Excel 2003 has now custom icons relevant to NumXL
- [UPDATED] Excel 2007 and 2010 icons
- [FIXES] Enchances usability, miscellaneous fixes
Documentation
- [UPDATED] New models, examples
- [MOVED] Moved the documentation from the installer to the website
- [REVISED] Help file
(September 2nd, 2010) - NumXL 1.0 (SP3) - Maintenance Release
- Fixed Issue: Using the toolbar/menu in Excel XP (2002) triggers a compiler error.
- Fixed Issue: The installer program does not support MS Excel/Office 2010.
- No code/feature change.
(January 30th, 2010) - NumXL 1.0 (SP2) - Maintenance Release
- Fixed Issue: The spreadsheet examples (tutorial & case studies) were not updated to reflect the latest changes.
- No code/feature change.
(January 26th, 2010) - NumXL 1.0 (SP2) - Maintenance Release
- Fixed Issue: GARCH/EGARCH out-of-sample volatility forecast does not mean-revert to long-run value.
- Fixed Issue: How can I construct an EGARCH model and to forecast the long-run average volatility.
- Fixed Issue: Cannot use keyboard shortcuts to select ranges.
- Fixed Issue: A missing leading zero in significance level field locks up excel.
- Fixed Issue: NumXL VBA compile errors.
- Minor Enhancements:
- Revised the arguments list for EWMA and EWXCF.
- Revised the arguments list for GARCH/EGARCH/GARCHM_FORESD.
- Support for term structure volatility forecast.
- NumXL dialog pops up on Excel main window upon startup (and is never hidden).
- A splash window pops up for 3 seconds upon Excel startup.
(January 5th, 2010) - NumXL 1.0 (SP1) - License support
- Activated the license management subsystem. The downloaded add-in operates in professional mode during the trial period. Afterward, the add-in reverts to lite (function-restricted) mode.
- No code/feature change.
(October 6th, 2009) - NumXL 1.0 - Security release
- Complying with software industry security policy and practices, the NumXL 1.0 package is signed using a CA-issued digital certificate to ensure authenticity and integrity.
- No code/feature change.
(October 1st, 2009) - NumXL 1.0
- Added Function, EWXCF, to compute the correlation time series using exponential weighted volatility and covariance.
- Added Functions to calibrate the user's model(s). The need for such functions arises in the model's parameter stability and back-testing using rolling windows.
- Added Support for building hybrid models (e.g. ARMA for the mean and GARCH for the vol, GLM+ARMA for the mean and EGARCH for the vol, etc.)
- Added Generalized Linear Model (GLM) to the list of supported models. The GLM is introduced to present linear models for exogenous factors (e.g. calendar events, economical data, etc.)
- MINOR: NumXL clears any messages posted to Excel's status bar upon loading.
- Added Calibration (i.e. model fitting) functionality to NumXL UI's menu and toolbar. Upon selection, NumXL initializes the Solver's Add-in fields with the selected model's values and launches it on screen.
(July 24th, 2009) - NumXL 1.0 RC
- Added Toolbars and Menu - A new add-in (NumXL UI), written in VBA, is designed to assist our users to automate the process of data analysis. The new add-in includes a dialog box and wizard to capture user's input and insert the corresponding analysis blocks (with equations) into an Excel worksheet.
- Added Tutorial Document to introduce basic principles of data analysis using NumXL. An online version is available as well.
- Redesigned Function Categories to ease finding specific NumXL functions.
- Fixed Minor Issues in the help file related to the tree view.
- Fixed Minor Problems in the installer with regard to registering the add-in with Excel.
- Removed Functions - TSAVG, TSSD, TSSKEW and TSXKURT: With the introduction of RMNA, our users can use Excel's built-in functions to acheive the same goal. For instance, TSAVG(Data) is now equivalent to AVERAGE(RMNA(Data)).
- Added Function - RMNA: RMNA removes missing values (#NA) from a given data set while preserving the original order of the series.
- Performance Revision - Revised the INTERPOLATE function to accept an array of target values and return an array of values.
(June 30th, 2009) - NumXL 1.0 Beta
- Added API to perform basis statistical test for the mean (TEST_MEAN), standard deviation (TEST_STDEV), skewness (TEST_SKEW) and excess-kurtosis (TEST_XKURT).
- Added support for leptokurtic (fat-tail distributed) innovations (Student's t-distribution, GED) into GARCH/EGARCH/GARCH-M models.
- Added Case Study for S&P 500 monthly, daily and weekly returns analysis.
- Added Case Study for Russell 2000 monthly, daily and weekly return analysis.
(April 15th, 2009) - NumXL 1.0 Alpha
- Initial Release.
- Revised Calculation of ACF to the following formula: $r_{h} = \frac{\sum_{k=h}^N{(y_{k}-\bar y)(y_{k-h}-\bar y)}}{\sum_{k=h}^N(y_{k}-\bar y)^2}$
- Added Support for Lagging (LAG) and Difference (DIFF) Operations in NumXL. As a result, the returned series contains missing values, for which "#N/A" is inserted.
- NumXL Functions recognize "#N/A" values as missing values and adjusts appropriately.
- Added Normal Distribution Test for a sample using the Jacque-Bera test. The test is primarily based on skewness and kurtosis of the sample data.
$ JB = {S^*}^2+{K^*}^2 \sim \chi^2(2) $
$ S^* = \frac{\textrm{Skewness}}{\sqrt{6/T}} $
$ K^* = \frac{\textrm{Kurtosis}}{\sqrt{24/T}} $ - Added Two-Tailed Test for ACF and PACF.
- Added Test, WNTest, for white noise (Portmanteau statistics). The test primarily checks for serial correlations in the sample. We implemented the Ljung-Box (1978) modified Q*(m)\sim \chi^2(m) statistics. The default and recommended value for m is ln(T), but the user can supply his own. The function returns the P-Value of the test.
- Added Support for 3 statistical normality tests (jarque-Bera, Wilk-Shapiro, and Durnik Chi-square).
- Added ARMA Model Support APIs: ARMA_AIC (measure goodness of fit), ARMA_LLF (log-likelihood), ARMA_RESID (standardized residuals), ARMA_FORE (forecast), ARMA_FORECI (confidence interval limits).
- Added GARCH Model Support APIs: GARCH_AIC (measure goodness of fit), GARCH_LLF (log-likelihood), GARCH_RESID (standardized residuals), GARCH_FORE (forecast), GARCH_FORECI (confidence interval limits).
- Added EGARCH Model Support APIs: EGARCH_AIC (measure goodness of fit), EGARCH_LLF (log-likelihood), EGARCH_RESID (standardized residuals), EGARCH_FORE (forecast), EGARCH_FORECI (confidence interval limits).
- Added GARCH-M Model Support APIs: GARCHM_AIC (measure of goodness of fit), GARCH_LLF (log-likelihood functions), GARCHM_RESID (standardized residuals), GARCHM_FORE (forecast), GARCHM_FORESD (volatility forecast), etc.
- Added <MODEL>_CHECK (ARMA_CHECK, GARCH_CHECK, EGARCH_CHECK, GARCHM_CHECK) to examine the selected model coeffient for stability.
Whitepapers
Russell 2000 monthly returns
Russell 2000 is by far the most common benchmark for mutual funds that identify themselves as "small-cap". Similar to S&P 500, Russell 2000 is a value weighted index and many index funds and exchange-traded funds (e.g. iShares Russell 2000 Index (IWM)) attempt to replicate (before fees and expenses) the performance of the Russell 2000 by holding the same stocks as the index, in the same proportions.
Buy LO & Sell HI - Optimal Strategy
In this paper, we construct a hypothetical strategy that buys at daily LOLowest price for the strategy/holding period and exists at daily HIHighest price for the same strategy/holding period (i.e. optimal strategy), compute and analyze its returns and construct an econometric model to capture time dynamics. Next, using the model, we forecast the strategy returns and examine a relationship between the forecasted returns and actual volatility for the same holding period. Although, the strategy can never be realized, it can help us forecast volatility using a new source of data (i.e. HI-LO).
Active Strategy (B) Returns Analysis
Strategy B is a small-Cap equity portfolio. In this study, we employ econometric techniques to explore whether the returns themselves have any predictive information of future returns/volatilities.
L-48 NG weekly storage level
The Energy Information Administration (EIA) publishes a weekly storage report for natural gas.The NG and power market participants monitor those reports closely, and, strive to forecast them; espeecially the ending season levels, as an indicator of where of gas scarcity, and thus price levels.
Russell 2000 weekly returns
Russell 2000 is by far the most common benchmark for mutual funds that identify themselves as "small-cap". Similar to S&P 500, Russell 2000 is a value weighted index and many index funds and exchange-traded funds (e.g. iShares Russell 2000 Index (IWM)) attempt to replicate (before fees and expenses) the performance of the Russell 2000 by holding the same stocks as the index, in the same proportions.
CPI-U monthly
The U.S. Consumer Price Index (CPI) is a time series measure of the price level of consumer goods and services. The Bureau of Labor Statistics, which started the statistic in 1919, publishes the CPI on a monthly basis
S&P 500 monthly returns
The S&P 500 is a value weighted index published since 1957 of the prices of 500 large cap common stocks actively traded in the United States.Many index funds and exchange-traded funds attempt to replicate (before fees and expenses) the performance of the S&P 500 by holding the same stocks as the index, in the same proportions.
Active Strategy (A) Returns Analysis
This paper analyzes the realized returns of an active trading strategy in an attempt to uncover any time patterns in the time series, i.e. finding if returns have any predictive information.
Strategy's returns and P&L
The paper discusses the back-testing process of the strategy by demonstrating the steps, issues and assumptions made during the preparation of the data sample and the calculation of the hypothesized strategy's returns. Finally, we turn our attention to risk aspect of the strategy and application within an established trading environment with common risk management policies.
Futures returns and P&L
In this paper, we examine the issues raised in preparing the returns data for strategies with futures/options (e.g. Contract specifications, margin requirement, contract size, leverage, mark-to-market (MTM) etc.). Finally, we define returns on margin and compute strategy's P&LProfit & Loss and max P&L draw throughout the holding period.
S&P 500 Daily Returns Analysis
In the paper, we consider the daily log returns for the S&P 500, examine its statistical properties, construct an EGARCHi model, examine several innovationsshocks or noise distribution models (e.g. gaussian, Student's t, GEDi), and verify whether the models assumptions are satisfied. Finally, we forecast daily volatility for out-of-sample.
Books
The following books are recommended as useful reading for NumXL users. Just click on the title of the book to order it through our partner Amazon.com.
Requirements
We highly recommend that you evaluate your computer before installing NumXL products to verify that you meet or exceed the minimum system requirements.
NOTE: NumXL 1.5 is a 32-bit Add-in. Although it can run on a Windows 64-bit platform (Windows XP, Windows Server 2003, Windows Vista, Windows 7), there may be some feature limitations as noted in the system requirements below.
| Component | Requirement |
| Computer and Processor | 500 megahertz (MHz) processor or higher |
| Memory | 512 megabytes (MB) RAM or higher |
| Hard Disk | 7 megabytes (MB); a portion of this disk space will be freed after installation if the original download package is removed from the hard drive |
| Display | 1024x768 or higher resolution monitor |
| Operating System | Microsoft Windows XP with Service Pack (SP) 3, Windows Vista with SP1, or later, Windows 7 |
| Microsoft Excel | Microsoft Excel 2002-2003 with Service Pack (SP) 2, Microsoft Excel 2007 with SP1, or later, Microsoft Excel 2010 |
| Additional | Requirements and product functionality may vary based on your system configuration and operating system |
EULA
LICENSE AGREEMENT
IMPORTANT: THIS END USER LICENSE AGREEMENT ("EULA") IS A LEGAL AGREEMENT BETWEEN YOU AND SPIDER FINANCIAL. READ IT CAREFULLY BEFORE COMPLETING THE INSTALLATION PROCESS AND USING THE PRODUCT. IT PROVIDES A LICENSE TO USE THE PRODUCT. BY INSTALLING AND USING THE PRODUCT, YOU ARE CONFIRMING YOUR ACCEPTANCE OF THE PRODUCT AND AGREEING TO BECOME BOUND BY THE TERMS OF THIS AGREEMENT. IF YOU DO NOT AGREE TO BE BOUND BY THESE TERMS, DO NOT INSTALL THE PRODUCT.
GRANTOR: SPIDER FINANCIAL CORP [hereafter “SFC”] is an organization incorporated in the state of Illinois, United States of America. SFC’s international headquarters is at 1507 E. 53rd Street, Suite 480, Chicago, Illinois 60615 USA, with subsidiary and affiliate offices in other cities in the USA and other countries. SFC’s primary internet addresses are www.spiderfinancial.com.
PRODUCT: NumXL [hereafter “the Product”] is a set of computer programs, information, tutorials, and help files [hereafter “Product Elements”] designed to assists Microsoft Excel end-users with statistical and/or econometrics functionality.
Grant: SFC hereby grants a nonexclusive license to use this Product on the following terms:(1) the Software may be used only on computers owned, leased, or otherwise controlled by you and only on one computer at a time. (2) Concurrent use on two or more computers is not permitted without separate authorization and the payment of additional license fees. (3) You may not reverse assemble, reverse compile, or otherwise translate the Software. (4) You may make copies of the software for backup purposes. Except as authorized under this License Grant, no copies of the Software or the User Documentation may be made by you or any person under your authority or control.
WARRANTY: SFC warrants that the Product, if used as directed and in conjunction with the operating systems for which it was designed, will substantially achieve the functionality described in the documentation. SFC does not warrant, however, that your use of the Product will be uninterrupted or that its operation will be error free. In no event shall SFC or any Contributors be liable to the licensed user for any special, indirect, incidental, or consequential damages, including (but not limited to) loss of revenues or loss of profits. SFC's sole obligation under this warranty will be, at its sole discretion, to replace any defective media which is provided by SFC to the user and which is reported by the user to SFC within 60 days from the date of shipment.
YOU ARE ADVISED TO PRINT OUT A COPY OF THIS LEGAL AGREEMENT FOR YOUR OWN RECORDS.
Copyright © 2009-2011 SPIDER FINANCIAL CORP.
All rights reserved
Rev: 10 January 2011
Documents
Reference Manual
Reference Manual version 1.5 for all things NumXL, including information on statistical testing, utilities, advanced models and more.
Getting Started
Examples-based tutorial to help you get started with NumXL.
Installation Guide
An easy to use, no hassle NumXL installation guide on a computer running Microsoft Windows and Microsoft Excel.
User Interface Guide
A complete introduction to NumXL's functions and interface.
Select Cases
Select cases for NumXL 1.5
White Paper
Need help deciding whether our products are right for you? Read through all of our white papers available online to help you make an informed decision.
Tips and Tricks
Useful tips and tricks to get the most out of NumXL. The following tips are available...