NumXL

What is NumXL?

NumXL is a set of Excel time series add-ins. It turns your Microsoft Excel application into a first-class time series and econometric tool, offering the kind of statistical accuracy offered by the much more expensive statistical packages. NumXL natively integrates with Excel, adding dozens of econometric functions, a rich set of shortcuts, and intuitive user interfaces to guide you through the entire process.

Whether you have a simple homework problem or a large-scale business project, NumXL simplifies your efforts. This helps you achieve your goal as quickly and completely as possible.

NumXL keeps your data and results connected in Excel, allowing you to track your calculations, add new data points, or update an existing analysis, easily sharing your result with co-workers – and, yes, even with your boss.

The learning curve couldn't be easier: NumXL doesn't require programming or scripting. You do not need to move your data between any external programs.

You can also do any kind of ad-hoc analysis because all NumXL functions are accessible in your spreadsheet, and within the VBA environment, you should choose to create scripts.

What can NumXL do for me?

NumXL comes with dozens of functions that you can easily access through the functions wizard in Excel, as well as multiple user interfaces and shortcuts to facilitate the time series analysis process and automate the most common steps (e.g., summary statistics, modeling, calibration, diagnostics). , forecast and more.)

1. General Statistics

Using descriptive statistics and correlogram wizards, you can examine the summary of data series and time series statistics with just a few clicks. The wizards come with an extensive set of statistical tests, from a simple test of a sample to average to the most sophisticated ARCH normality and effect tests.

In addition, the time dependency test (automatic correlation) in the sample data is just a few clicks away.

Wizards generate professionally organized tables and charts, summarizing all your calculations, ready to be included in your presentation. To make things even easier, all outputs include NumXL functions in your formula to connect values to inputs, so you can edit, update, or customize as you wish. You can even run again the wizard if you feel lazy.

In addition to wizards, NumXL has numerous functions for measuring prediction power (e.g. SSE, RMSE, MAPE, and others).

To visualize your data distribution, NumXL offers several functions to facilitate the task of building histograms, empirical cumulative distribution (EDF), and kernel density estimation (KDE).

2. Correlogram Analysis

Using the wizard and correlogram function, building autocorrelation and partial charts is easy.

In addition, NumXL comes with support for calculating cross-correlation using three different methods: Pearson, Spearman, and Kendall.

Finally, for completion purposes, NumXL supports Hurst exponent analysis and the GINI coefficient.

3. Statistical tests

For a serious analysis of the data, it may be necessary to consider the statistical significance of a calculated parameter (e.g., autocorrelation factor, excessive shortness) or to verify an assumption of previous data (e.g., normality, parking, absence of serial correlation, and others).

NumXL packages most of these tests as a simple API to calculate the P-value of the underlying test.

4. Transformation

Data transformation is a common preliminary step in real-world analysis and/or modeling. The NumXL comes with the most common transformation functions (e.g. Box-Cox, difference and seasonal difference/integral operators and others.)

5. Soft

Smoothing and filtering are two of the time series techniques most commonly used to remove noise from the underlying data to help reveal important features and components (e.g., trend, seasonality). However, we can also use smoothing to fill missing values and/or perform a prediction.

NumXL supports a variety of smoothing functions, from a simple weighted moving average (WMA) to winter's triple exponential smoothing function.

Obviously, we can't talk about smoothing without mentioning trend functions. Trend analysis is widely used (or abused) in the industry to make a quick (and dirty) prediction. Executives can use the trending tool as a health check when they examine results from more advanced models. NumXL supports several trend forms: linear, polynomial, power, exponential and logarithmic.

6. Calendar functionality

Calendar events influence time series sample values, and a prior adjustment for these events will help us better understand the process, modeling, and forecasting.

NumXL comes with numerous functions to support calendar adjustment, scrolling and date adjustment, support for holidays in the U.S. and outside the U.S., weekends outside the west, and public and bank holiday calendars.

7. Spectral analysis

In statistics, spectral analysis is a procedure that decomposes a time series into a spectrum of cycles of different lengths. Spectral analysis is also known as frequency domain analysis.

Currently, NumXL supports the discrete transformation of Fourier (and its inverse), Hodrick-Prescott filter (HP), Baxter-King filter (BK) and convolution operator, with future plans for more extensive coverage.

WEAPON / SOUL

NumXL is loaded with numerous functions to assist you in any ARMA analysis task. You can start by specifying the order of the model using the ARMA wizard. The wizard will link the calculations related to the model - the log probability function, the Akaike information criterion (AIC), and the residual diagnosis - with the input data. Once this is done, adjusting the model parameters (calibration) is easy: just select the model and click "calibration". The same goes for the forecast: Select the model table and click "forecast".

You can always edit formulas in output cells, get intermediate calculations (for example, residuals, adjusted average), or use an NumXL function in your own formulas or VBA code if you wish.

9. Seasonal ARIMA

NumXL supports seasonal ARIMA through two different models: (1) AirLine and (2) X-12-ARIMA.

X-12-ARIMA is the widely used seasonal adjustment program, developed, supported and maintained by the U.S. Census Bureau. NumXL provides an intuitive interface with the program to help Excel users make seasonal forecasts and adjustments quickly and efficiently for economic and financial data.

NumXL also gives users access to all raw files (input/output) generated in the data analysis process.

10. ARCH / GARCH          

Similar to ARMA/ARIMA, modeling a GARCH type model is very easy. Using the GARCH Wizard, you can generate a model output table with all coefficient values and related calculations (for example, LLF and residual diagnosis). This table can be used to calibrate the model and predict values outside the sample.

NumXL also supports the ARCH/GARCH, Exponential GARCH (EGARCH) and GARCH-in-mean (GARCH-M) models natively.

In addition, The NumXL supports innovations of the Gaussian, Student t and GED type.

11. ARMA-GARCH mixing model

If you want to model the conditional average variable in time and conditional volatility in a model, an ARMA-GARCH mixing model is in order. By combining the two models, ARMA will follow the average and pass the residuals to GARCH to track the variation over time.

Arma-GARCH combined models support all ground supported ARMA and GARCH models, including non-Gaussian innovations.

12. Generalized Linear Model (GLM)

If you have a logistic regression or a general linear model in mind, you can use the generalized linear model (GLM). NumXL uses the GLM wizard to help you specify input data, link functions (for example, probit, logit, log add-on), and generate a model output table.

As with all our models, the output model table is used to calibrate and execute forecasts outside the sample.

System Requirements

Microsoft Windows (32-bit or 64-bit) Windows 7, Windows 8, Windows 10

CPU de 500 MHz

512 MB RAM

120 MB of disk space

Microsoft Excel 2010 or later