We’d love to hear your ideas and experience with NumXLⁱ and our support. To keep the reviews objective and let us truly assess where we stand in terms of service quality, we are asking you to leave anything special aside from from honest opinion of our product and services.

Where can I submit reviews?

You can leave your review at your favorite directory site: Google+, Amazon, Yelp, Yahoo, CNet, etc.

Google+

1. Go to NumXL Google+ homepage.
2. Click on ‘Write a review’

Amazon.com

1. Go to NumXL product listing on Amazon.com
2. Click on ‘Write a review’

Yelp

1. Go to Spider Financial homepage on Yelp
2. Click on ‘Write a review’

Yahoo

1. Go to Spider Financial homepage on Yahoo
2. Click on ‘Write a review’

We are excited to announce the start of beta testing for NumXLⁱ's next update - 1.59 TUCSON.

In addition to numerous fixes, the new release will support 64-bit version of Microsoft Excel 2010 and 2013, making it easier to analyze large data sets into NumXL.

The motivation for this new version came from our customers and the fact that 64-bit processors are quickly becoming the standard for many servers and desktop computers.

After the completion of beta testing, NumXL 1.59 will be available in about a week.

We encourage anyone who is interested in joining the beta program to contact our beta support team at beta@numxl.com for information about the program, and instruction for downloading Numxl-beta.

With our latest release of NumXLⁱ 1.58 BAJA behind us, we are now putting all of our energy into the next NumXL update – Tucson.

What is going to be so cool about NumXL Tucson? Aside from minor fixes in worksheet functions and wizards, the new version will support the 64-bit version of Excel.

We can't thank you enough - our customers. Your indispensable flow of ideas, thoughts and criticisms keeps us honest and inspired to deliver the best possible solution to you.

Check out the latest NumXL tutorials on our YouTube page. For more information on NumXL 1.58 BAJA, visit NumXL reference notes.

[October 16th, 2012]: We are pleased to announce the release of a new version of NumXLⁱ: 1.58 BAJA.

NumXL 1.58 BAJA now finally has Wizards for constructing Histogram and QQ plot, and performing common statistical tests: Normality test, White Noise Test, ARCHⁱ Effect test and Stationary test. We've also added new functions to help deal with missing values in your data, and further enhanced the exponential smoothing functions with new Support for finding optimal values of its smoothing factors. For a complete list of the changes, please refer to the NumXL release notes.

We highly recommend our users download and install this release.

[September 17th, 2012]: Today we are excited to announce the release of a new version of NumXLⁱ: 1.57 SINGA (1.57.41168.2).

This new release includes several new features: support for U.S. Census X12-ARIMAⁱ modeling and seasonal adjustment, kernel density estimates, statistics of fit and more. For a complete list of the changes, please refer to the NumXL release notes.

We highly recommend our users go to download to install this release.

[September 5,2012] This is our second issue of an ongoing series on select case studies. We'llⁱ use real financial data to construct models with the help of NumXLⁱ.

In this issue, we’ll examine the U.S. crude oil reserve stock level time series (i.e. crude oil inventories in the U.S. including the Strategic Petroleum Reserve (SPRⁱ)).

We will model the dynamics in the crude oil stockpile (including SPR) level over time and project a forecast for the next 12 months.

Why do we care? The level of inventories helps investors estimate the prices for petroleum products (e.g. gasoline, heating oil, diesel, etc.). Like for other goods and services, prices for petroleum products are determined by supply and demand.

U.S. Crude Reserve Modeling

[August 21,2012] This week, we present a first issue of an on-going series on select case studies. These select cases will utilize real-world examples and real financial data when applying the models and methods supported by NumXLⁱ.

In this issue, we examine a claim by a portfolio manager (trader X) about his ability to generate an absolute return (i.e. alpha). Trader X agreed to share his monthly realized net returns history for our analysis.

Why do we care?

To achieve superior returns, professional managers in the financial market are constantly inventing new proprietary strategies. And they charge their clients a hefty fee for their professional advice. So before you hire any professional manager, it is pivotal for you to examine their track records (i.e. returns) and benchmark them against other managers or passive investment strategies (e.g. S&P 500, etc.) to justify his or her fees.

Demystifying Trading Strategy Returns

We are excited to announce a couple of new developments on the NumXLⁱ support front: (1) We revamped the Getting Started user's guide, and (2) We are pooling all the NumXL tutorial videos and making them available on a single Youtube channel.

Why?

Many of our users could not view the tutorial videos on their iPhone and/or iPad devices, while other users reported slow download times. To accommodate a broader pool of viewers, we converted our video format (and uploaded) everything to YouTube.

How do I access this service?

You don’t have to do anything different than before: Just navigate to your NumXL web page of interest, and if a tutorial video is available, just click on the video thumbnail image.

We are excited to announce a new development on the NumXLⁱ support front. We'llⁱ be pooling external links and resources and posting them on our Facebook page.

Many of our users requested links to resources and literature on time series and the different algorithms. You'll now have access to a whole range of time series bookmarks and resources.

We will be adding more resources over time.

NumXL's Facebook page

[July 12,2012] This week, we’ll take the prior discussion further and develop an understanding of autoregressive conditional heteroskedasticity (ARCHⁱ) volatility modeling.

Why do we care?

Volatility cannot be directly observed, and volatility modeling is more complicated than those of a conditional mean. The concepts and the ARCH model discussed here are pivotal to a solid understanding of financial time series volatility.

Volatility 102 - ARCH Volatility Modeling

[July 6,2012] This week, we continue our on-going series on volatility modeling and forecast. In this issue, we start by defining the various terms in an asset’s return time (e.g. holding period), and explain the multi-period forecast of returns and volatility. Finally, we define the different types of volatility terms (e.g. local volatility, term structure, long-run and forward volatility) that we will come across in our future volatility modeling.

Why do we care? The concepts discussed here are pivotal to a solid understanding of financial time series volatility. The concepts are not unique to one model, but rather generic and applicable to the entire volatility modeling domain.

Volatility 102 - Types and Definitions

[June 22,2012] Today, NumXLⁱ 1.57 SINGA has gone into Beta testing in preparation for official release, which is about a week away.

In addition to numerous fixes, NumXL 1.57 comes with an important feature: seasonal adjustment for time series using X11ⁱ / X12-ARIMAⁱ methodology.

The X11/X12-ARIMA (x12a) is developed by the U.S. Census Bureau, but NumXL brings the vast functionality of the x12a program into Excel through a friendly user-interface and add-in functions. As a result, an Excel user can run a time series seasonal adjustment and/or forecast in a snap. Furthermore, NumXL offers access to all raw files (input/output) that are generated in the process shall a user wish to examine them manually.

Why not develop x11/x12a natively in NumXL? X12a has a long history. Scores of bright people worked on it, and they continue to support and enhance it further. The program and the methodology have gained a wide acceptance in many applications. Why reinvent the wheel? We believe there is enormous value in just bridging the gap between Excel users and this great application.

Do I need to download anything to use X12-ARIMA with NumXL? No. You don’t need to download or install any program other than NumXL. Our installer will copy the supported version of the X12-ARIMA program.

I have X12-ARIMA already installed, do I need to uninstall it first? No. NumXL will only call/invoke the X12 program that was installed by the setup program.

What is the NumXL beta program? How can I join it? We’d love to hear from you. You can learn more about the NumXL Beta program on our website

[June 20, 2012] This week, we will show how to make a backward forecast using only NumXLⁱ functions in Excel. We will also discuss the relationship between a regular time series model and an implied backward/reversed time series model.

Why do we care? Backward forecasting is a vital tool in time series analysis. For instance, we can apply it to fill-in missing values using both sides of the gap for imputation. In addition, backcasting allows the re-creation of historical events within a model, and thus, finding increasing applications in macroeconomic time series models.

Time series backward forecasting

[June 13,2012] we start a new on-going series on volatility modeling and forecast. In this issue, we start with the definition and general dynamics of volatility in financial time series. Next, we will use historical data to develop a few methods to forecast volatility. These methods will pave the road to a more advanced treatment in future issues.

Why do we care? Predicting volatility is crucial for many functions in financial markets. For start, volatility is used by many for risk management (e.g. VaRⁱ), options pricing, asset allocation, and many other applications. Understanding volatility is vital for virtually all time series analysis.

Financial time series volatility 101

[June 7,2012] This week, we tackle the probability distribution inference.

Why do we care? As a start, no matter how good a stochastic model you have, you will always end up with an error term (aka shock or innovation) and the uncertainty (e.g. risk, forecast error) of the model is solely determined by this random variable. Second, uncertainty is commonly expressed as a probability distribution, so there is no escape!

In this issue, we attempt to derive an approximate of the underlying density probability using a sample data histogram and the (cumulative) empirical density function, but histogram suffers from major drawbacks.

The Ins and Outs of Histogram

We are excited to announce a new development on the NumXLⁱ support front. We are pooling all the examples we have developed over the years and are making them available to our users via a cloud-based storage service (Box.net).

Why should I care?

You now have access to a whole range of examples. Each example comes with an elaborate description, so you can decide whether you need a certain example before you download it.

In addition, this service is our central repository. We will be adding more examples as we develop them.

How do I access this service?

You don’t have to do anything different than before: Just go to the reference manual on our website and navigate to any Function of interest. In the reference page, you will find a small window (toward the bottom of the page) listing files with examples.

Hovering your mouse over a file or a folder in this window provides a unique description for it in a pop-up tip.

Why don’t we bundle the examples with the installed software?

The sheer size of the installer would grow dramatically, making it slower to download. In addition, the installed software will occupy a larger space on your computer, and you won’t have access to the newly added examples.

[May 31th, 2012]: Today we are excited to announce the release of a new version of NumXLⁱ: 1.56 ZEBRA (1.56.41060.2).

This new release includes several new features: date rolling and adjustment, U.S. and non-U.S based holidays support, non-western weekends, public and bank holiday calendars. For a complete list of the changes, please refer to the NumXL release notes.

We highly recommend our users go to download to install this release.

[May 31,2012] This week, we go over time series smoothing functions, highlight its assumptions and parameters, and demonstrate its application through examples.

Why should we care? Smoothing is very often used (and abused) in the industry to make a quick visual examination of the data properties (e.g. trend, seasonality, etc.), fit in missing values, and conduct a quick out-of-sample forecast.

In this issue, we will discuss five (5) different smoothing methods: weighted moving average (WMAⁱ), simple exponential smoothing, double exponential smoothing, linear exponential smoothing, and triple exponential smoothing..

Time Series Smoothing

[May 23,2012] This week, we dig deeper into the ARIMAⁱ stochastic process as the second entry in our "Unplugged" (or "Under the Hood") tutorial series. We've featured ARIMA models in a few of our tutorials before, but this week we'llⁱ explore them in rich detail, starting with a clear definition of the process and moving on from there.

Why should we care? In financial time series and other fields, we often face a non-stationary time series, for example traded security (e.g. stock, bond, commodity, etc.) prices. In this case, the time series exhibits either trending, seasonality or merely misguided (random) walk. The stationarity assumption is critical for the bulk of the time series and econometric methods, so how do we handle this scenario? ARIMA.

Once again, we will start here with the process definition, stating the inputs, outputs, parameters, stability constraints, and assumptions. Then we will introduce the integration operator and draw a few guidelines for the modeling process.

ARIMA to the rescue

[May 17,2012] This week, we tackle the trend issue. No, we aren’t talking about the latest trend in technology or fashion; we’re talking about trend analysis for time series data! Disappointed? Don’t be, this is an exciting and fun topic.

Put simply, trending is the practice of fitting a curve (e.g. line, polynomial, exponential, etc.) to your data over time, in an effort to project a forecast and establish a confidence interval.

How does this relate to time series analysis?While the fitting curve is a function of time, the parameters of the curve were found using prior information and is thus related.

Why should we care? The trend is very often used (or abused) in the industry to make a quick (and dirty) forecast. Executives might use the trending tool as a sanity check when he/she examines results from more advanced models.

In this paper, we will go over the “NxTrend” built-in function that was first introduced in NumXLⁱ 1.55 (LYNX) and demonstrate, through numerous examples, its use and the intuition behind it. We will focus on the back testing aspect and the forecast confidence interval.

Keep up with the trends

[May 11th, 2012]: Today we are excited to announce the release of a new version of NumXLⁱ: 1.55 LYNX (1.55.41040.2).

This new release is features-rich, as we added several new functionality: trend analysis (for linear, polynomial, logarithmic, and exponential trends), histograms, spectral analysis (discrete Fourier transform), and more. We also revised the existing correlation function (XCFⁱ) to extend support for new methods (e.g. Kendall, Spearman, etc.), and added a statistical test for examining its significance. Finally, NumXL now includes a new unit-root and stationarity test: the Augmented Dickey-Fuller (ADFⁱ) test. For a complete list of the changes, please refer to the NumXL release notes.

We highly recommend our users go to download to install this release.

[May 10,2012]This week, we dig deeper into the ARMAⁱ stochastic process for the first entry in our "Unplugged" (or "Under the Hood") tutorial series. We've featured ARMA models in a few of our tutorials before, but this week we'llⁱ explore them in rich detail, starting with a clear definition of the process and moving on from there.

We'll take you through ARMA's underlying assumptions, exploring the role of innovations or shocks as they affect the overall ARMA machine. Finally, we take a close look at how an ARMA process produces a stationary time series with a stable, finite, long-run mean and variance.

ARMA unplugged

[May 2nd, 2012]: We are excited to announce today the launch of NumXLⁱ new release 1.54 RED (1.54.41030.1).

The new release includes several new features: time series smoothing (e.g. Winter's triple exponential smoothing), data transformation functions (e.g. logit, probit, complementary log-log), robust descriptive statistics (e.g. MADⁱ, MDⁱ, RMDⁱ, RMSⁱ, Gini coefficient and Hurst exponent), and few minor fixes. For a complete lists of the changes, please refer to the NumXL release notes.

We highly recommend our users to download and install this release.CA7XKWNCPMDK

[May 2,2012]

This week, we take a look at a case inspired by a discussion in one of our online forums, which you can access at www.spiderfinancial.com/forums/financial-time-series/forex/. One of our users asked if they could use NumXLⁱ to predict the next-day market open and market close exchange rate (i.e. spot) for the EUR/USD. We started by creating a trading strategy where we buy EUR at market open, and close the position (selling EUR) at market close.

Then we take a slightly different approach, avoiding the kind of complex non-linear models we would need to make sense of the noise-like distribution of the daily returns. Instead, we employ a stop-loss strategy that will limit our daily loss and, most importantly, generate positive returns.

Predict This!

[April 25th, 2012]: We are excited to announce today the launch of NumXLⁱ release 1.53 SAC (1.53.41023.1).

The new release includes several new features: time series smoothing, data transformation functions, and few minor fixes. For a complete lists of the changes, please refer to the NumXL release notes.

We highly recommend our users to download and install this release.

[April 24,2012] In this week's issue, the final entry in our series of data preparation tutorials, we discuss the influence of outliers on our time series analysis. Dealing with outliers can be tricky, as they might result from a number of factors, from simple data entry errors to influential an unexpected "black swan" events. In this tutorial, we discuss the problem of outliers, how to detect them, and what we can do with them.

We start with a basic definition of outliers, which typically appear as a result of human error, instrument error or through natural deviations in populations. Then we explain a few means of testing for outliers and developing robust models capable of dealing with black swan events.

Data preparation: Outliers

[April 18,2012]This week, we continue with the fourth issue in our ongoing data preparation series by addressing two important anomalies commonly found in sample data: (1) concentration of values - either a tight range (e.g. proportions) or a wide dispersal over several order of magnitude (e.g. population, income, rainfall volume, etc.), and (2) the mean/variance relationship.

For this tutorial, we’ll start by going through a few different value concentration cases, explain their impact on analysis and forecast, and, finally, present common transformation methods and discuss concerns for mapping results from a transformed data scale back to raw data.

You can find more details and a step-by-step tutorial, along with a downloadable spreadsheet and PDF, at the link below:

Data preparation: concentration of values

[April 18, 2012] We are pleased to announce the launch of our new NumXLⁱ Community support forums. We hope this platform will provide help to users from within the NumXL community. The Forums are available to all users, even those who don’t have a paid support services.

Please note that the official support will be available only through our help-desk support system.

To access and -hopefully- join the NumXL forums, please go to this page.

[April 11,2012] This week, we unveil the third issue in our ongoing series of tutorials on data preparation. This time, our focus is another bedrock assumption in time series modeling: homogeneity, or the assumption that a time series sample is drawn from a stable/homogeneous process.

We start by laying out a workable definition of a homogeneous stochastic process, then running through the minimum requirements for time series analysis. Then we'llⁱ use sample data drawn from our previous tutorials to draw a few observations about homogeneity and examine the underlying assumptions behind them.

You can find more details and a step-by-step tutorial, along with a downloadable spreadsheet and PDF, at the link below:

Data preparation no. 3: Homogeneity

Questions? Comments? We'd love to hear your ideas for future issues or feedback on past issues. Contact us at support@spiderfinancial.com.

[April 7,2012] We've heard a few questions from many of our users about the new 7-day grace period offered with our latest NumXLⁱ release. Simply put, you can now run a full version of NumXL immediately for seven days, no license key required.

Don't worry about entering a subscription key; all you need to do is open Excel and start using the Pro/Full mode of NumXL. Like what you see? After seven days you can keep working in Full mode by starting a free 30-day trial, or by downloading an annual or perpetual license key if you're full on board.

Also, be sure to check out the NumXL release notes for more details on the newest features.

[April 5,2012] Today we launch the second tutorial in our ongoing series about data preparation in time series analysis. Our focus this time around is one of the most fundamental assumptions in time series analysis: Stationarity, or the assumption that a data sample is drawn from a stationary process.

First, we lay down a bedrock definition of stationarity and demonstrate the minimum requirements for stationarity in our time series analysis. Then we'llⁱ tackle a time series data sample - namely the closing prices for IBM stock from January 3rd, 2012 to the present date - which we'll use to develop some observations about stationary processes, and explore the underlying intuitions behind them.

You can find more details and a step-by-step tutorial, along with a downloadable spreadsheet and PDF, at the link below:

Data preparation no. 2: Stationarity

Questions? Comments? We'd love to hear your ideas for future issues or feedback on past issues. Contact us at support@spiderfinancial.com.

[April 3,2012] The NumXLⁱ team has released NumXL 1.52.41002.5 (ORB). This is a minor maintenance release, which comes with the following:

• Improved support for annual license/subscription keys
• Allowing users to run NumXL in Full/Pro mode after a fresh install, without a license key, for a 7-day grace period.
• Miscellaneous minor fixes

For more details, please check out the NumXL release notes

We strongly recommend that our users download and update the latest version.

[March 29,2012] This issue is the first in a series of articles that explore the data preparation aspect of time series analysis. Data preparation is often overlooked by analysts, but we believe it is a vital phase that wields a vast influence on the overall analysis and modeling process. The vast majority of time series and econometric theories assume input time series to be stationary and homogenous, with equally-spaced observations and values that are present and real. In practice, we often handle samples with missing values, unequally-spaced observations possible outliers, mean/variance dependency, restricted values ranges and other phenomena. The aim of this series of articles is to address each of these problems and introduce practical methods to overcome them.

In this issue, we start with the sampling assumptions of the time series: equal spacing and completeness. Then we consider a time series with missing values and discuss how to represent them in Excel, with the aid of NumXLⁱ processing. Finally, we look at unequally-spaced time series, how they come into existence, how they are related to the missing values scenario, and what to do with them.

For more details and a step-by-step tutorial, along with a downloadable spreadsheet and PDF, click this link: #N/A - Missing values

This issue is brimming with info about a key tool in our time series arsenal toolbox: correlogram analysis. We take you first through the auto-correlation and the partial auto-correlation functions definition.Next, we derive and highlight the common patterns in the ACFⁱ and PACFⁱ plots generated by AR, MA and ARMAⁱ type of processes. Finally, we draw a number of observations and drive quick intuitions to further help us identifying the candidate model(s) and its order using only ACF/PACF plots set.

The exercise will leave you with a thorough understanding of correlogram analysis, while demonstrating how NumXLⁱ can help you find an ideal model for your data.

For more details and a step-by-step tutorial, along with a downloadable spreadsheet and PDF, click this link: A Correlogram Tale

March 15th, 2012 This week, we focus our attention to your burning questions about goodness-of-fit functions, like: What are the different functions for goodness of fit? How does each function differ from the rest? Which one do I use, and for what purpose?

Put simply, A goodness-of-fit function is a quantitative measure of the discrepancy (or the agreement) between the observed values and the values expected under a model in question. In general, a measure of goodness of fit helps us to find good (or optimal) values for a model's coefficients and facilitate the comparison of competing models in an effort to select the best one.

In this tutorial, we’ll start with the log-likelihood function (LLFⁱ), and then expand to cover other derivative measures (e.g. Akaike's Information Criterion (AICⁱ) and Bayesian/Schwarz Information Criterion (BICⁱ/SICⁱ/SBCⁱ)). For an example, we use the time series of the ozone levels in downtown Los Angeles for the period between January 1955 and December 1972.

The exercise will leave you with a thorough understanding of goodness of fit, while demonstrating how NumXLⁱ can help you find an ideal model for your data.

For more details and a step-by-step tutorial, along with a downloadable spreadsheet and PDF, click this link: For goodness of fit's sake

March 8th, 2012: In our continuous effort to make NumXLⁱ easy to use, we have created a tutorial video for our latest Tips and Hints Issue: ARCH Test Explained. In this video, we follow the workbook step-by-step, and help you better understand how to do an ARCH Test using NumXL.

On a separate note, we have also launched a NumXL channel @YouTube, with demos and tutorial videos. please visit us there.

February 9, 2012: This week, the "Tips & Tricks" newsletter tackles the issue of the volatility forecast using GARCHⁱ Modeling techniques. Starting with S&P 500 ETFⁱ monthly prices, the paper illustrates the few steps it takes to process the raw data; specify a model; fit or to calibrate the the model coefficients values; validate the assumptions of underlying model; and, finally, to construct a 12-month volatility forecast. We did all of the steps using NumXLⁱ, right in Excel.

For details or to download the document and/or the spreadsheet for this tutorial, go to tips NumXL Cookbook: Volatility Forecast with GARCH on our website.

January 27, 2012: In the next couple of weeks, expect some exciting enhancements to NumXLⁱ! We are adding support for three frequently-requested time series models: ARIMAⁱ, ARFIMAⁱ and SARIMAⁱ.

We are constantly working on improving our product, and continuing to use your feedback as a key component of our efforts here. Please keep your comments coming!

Thank you for support and stay tuned.

Excel 2010 is not supported in the current NumXL 1.0 installation program, which was written before Excel 2010 was officially released. You will see an error message when you try to install NumXL 1.0 under Excel 2010 - we are working on the upgraded installation program as you read this and we will be able to release the upgrade in the next week for all of you who want to use NumXL 1.0 with Excel 2010.

A new version of NumXLⁱ 1.5 with full-support to license keys is available online. The new edition includes no code changes, and it is introduced primarily to unlock the professional-only functions during the 30-day trial period. After the end of the trial period, NumXL will revert to the Lite (freeware) mode.

We are actively working on the second major release of NumXLⁱ. The plans for NumXL 2.0 were driven primarily by the large amount of feedback we received from our users.

In this coming edition, there will inevitably be a few changes despite our relentless attempts to keep the functions set static. We are hoping that the simplicity and added functions in the new version will offset any inconvenience experienced by our users.

Tentatively, we are planning to have our first release of NumXL for beta users early in January 2010.

[August 12th, 2009] NumXLⁱ - the econometrics analytics software - is currently under active development in preparation for its official Release on September 7th, 2009.

What's changed in this release?

The latest release includes a few minor fixes, revised documentation (i.e. help file, tutorials, and case studies) and enhanced user-interfaces (UI), improving the usability of the software. To see a full list of changes in this release, please check the  release notes.

How to download and install 1.0

The official release will be available for download on September 7th. We recommend all users download this update for the minor fixes included. You can download and install NumXL 1.0 at the NumXL 1.0 Download site.

NOTE: Before you install the new version, please uninstall the old version on your machine.

The optimal trading strategy is to buy low and sell high. This is easier said than done, and many of us invest lot of effort experimenting with strategies in an attempt to get closer to this end. In this paper, we construct this hypothetical optimal strategy, analyze its returns and construct an econometric model to capture its time dynamics. Next, using the model, we forecast the conditional returns and compare them with returns of actual strategies. Finally, we discuss their application in stop-loss optimization for actual trading strategies.

The white-paper and the supporting financial model are available on our website to all our registered users.