New features in XLSTAT 2019
New features added to XLSTAT in 2019 include:
- Linear regression & ANOVA: Use millions of data points, compute influence diagnostics and validate assumptions
- Customer Lifetime Value: A new and useful feature to assess the financial value of your customers. (Included in XLSTAT-Marketing & XLSTAT-Premium)
- Price Elasticity of Demand: Determine the price of your products at which maximum revenue is generated
- Multiple Factor Analysis: You can now run this analysis on frequency data tables. (Included in XLSTAT-Sensory, XLSTAT-Marketing and XLSTAT-Premium)
- STATIS: Use this method in conventional and projective mapping or free choice profiling. (Included in XLSTAT-Sensory, XLSTAT-Marketing and XLSTAT-Premium)
- DOE sensory: Improved designs for all sensory discrimination tests are now available. (Included in XLSTAT-Sensory, XLSTAT-Marketing and XLSTAT-Premium)
- Variables characterization: Extra filtering and sorting options for a more customized output
- Nonlinear regression: New interface and additional built-in models to be used in various fields
You can now carry out an analysis by groups. The curves of each group are displayed in a single graph. Global fit with shared settings has been added in order to adjust several curves at the same time, and to calculate for each shared parameter an overall optimal value applying to each of the groups. Finally, power functions are now available in the predefined functions.
- Scatterplots: Customize your scatterplot choosing your own color for groups
- Linear regression: Load csv or text data files with millions of data points and run a Linear regression. Available under the Modeling data menu.
- Mixed models: The Cholesky (Eskow & Schnabel) method has been integrated to deal with saddle points during the convergence of the Newton-Raphson algorithm.
Compute t-tests and F-tests for fixed effects using the Satterthwaite formula for denominator degrees of freedom. Appropriate for mixed models with unbalanced data or complex covariance structures.
It is now possible to choose between ordinary least squares or MIVQUE0 starting values for the Newton-Raphson algorithm.
Computations of random effects have been corrected.
You can now compute Type III test of fixed effects.
- Customer Lifetime Value: Summary statistics of the Average revenue per account have been added in the output as well as the possibility to generate a box plot per segment. (Included in XLSTAT-Marketing & XLSTAT-Premium)
- 2D Plots for Contingency tables: You can now select several quantitative variables to weigh the observations. In addition, multiple criteria are available to resize the points on the plot. Available under the Visualizing data menu.
- Cleaning text data: Trim spaces from text data, correct space repetitions or replace a text by another.
- Lower and upper case: Convert text data to lower or upper case.
- Principal Component Analysis: You can now import large text file (csv or txt) and run a PCA on millions of data.
- Multiple Correspondence Analysis: You can now import large text file (csv or txt) and run a MCA on millions of data.
- Data Sampling: It is now possible to display the generated samples side by side within the same table. This display will facilitate the data selection for further analysis. In addition, a new import method has been added to allow data sampling from large text files.
- Data analysis on Excel filtered data: It is now possible to perform XLSTAT analyses on filtered data. Once you have filtered your data in an Excel spreadsheet, simply select the feature from the XLSTAT menu and run the analysis.
- Probability Calculator: This tool allows you to compute for a given distribution function, the density function, the cumulative distribution function or the inverse cumulative distribution function. It is useful for determining the probability of a random event (for example, the occurrence of a 2 when throwing a die or the arrival of 3 customers to a shop within an hour).
- Stepwise Cox Regression: Select the best variables for your Cox model using a stepwise procedure.
- TCATA: A new feature for analyzing temporal check-all-that-apply (TCATA) data. This dynamic method allows users (assessors) to select and update the attributes that characterize products as they evolve over time. (Included in XLSTAT-Sensory, Marketing and Premium)
- CATATIS: A new feature for processing CATA data in order to study the links between products and attributes and investigate the agreements between assessors. The benefit of CATATIS, compared to the usual method for CATA data, is that atypical assessors have a lower weight than those who agree with the rest of the panel. (Included in XLSTAT-Sensory, Marketing and Premium)
The changes from version 2017 to 2018, and those added in 2018, can be found here.