IBM SPSS Statistics 26
August 2019
“Who are JMP’s competitors? (maybe we have them in narrow areas) — but there is nothing else like it.
Who is as interactive?
Who else does as great a job at DOE?
Who does analysis faster and bigger on the desktop?
Who else does Graph Builder as well?
No one, because JMP is truly unique in the crowded marketplace.” -John Sall
Company
- Global Service, Software and Hardware provider.
- Since IBM acquired SPSS, they have primarily promoted predictive modelling capabilities. SPSS Statistics is one of SPSS’ core packages for doing predictive modelling and statistical analysis. Characterized as easy-to-use, it has desktop and server versions with modules that can be sold as bundles as well as add-ons. They position their tool as being useful for both beginning and experienced users of statistics. See how the Base, Standard, Professional and Premium editions compare.
Product
- IBM SPSS Statistics is modular. They offer SPSS Statistics Base with three add-ons: Custom tables and advanced statistics, Complex sampling and testing, and Forecasting and decision trees.
- Highlights in version 26 (released April 2019):
- New quantile regression analysis
- Compare two ROC curves
- Enhanced Bayesian procedures for one-way repeated measures, one-sample binomial, and one-sample Poisson
- Fleiss Multiple Rater Kappa for survey analysis
- Scripting enhancements for Mixed, Genlinmixed, and Matrix
- New Production Facility enhancements (to replace IBM SPSS Collaboration and Deployment Services for processing SPSS Statistics jobs)
Target Audience
- Primarily statisticians, social scientists, modelers, market researchers, and other analysts.
- SPSS is used and taught in many schools, especially in the social sciences.
Feature Strength and JMP Response
- SPSS Statistics Base provides linear and nonlinear modeling, simulation, customized tables, free product extensions based on SPSS, Python, or R syntax (comparable to JMP’s File Exchange). JMP 15 provides most everything Statistics Base has and more.
- SPSS Advanced Statistics provides general and generalized linear models (GLM), linear mixed models, generalized estimating equations (GEE) procedures, generalized linear mixed models (GLMM) and survival analysis procedures. JMP provides the equivalent or near-equivalent with the exception of GEE and GLMM.
- SPSS Regression provides categorical outcome support for multinomial logistic regression, nonlinear and constrained nonlinear regression, weighted and two-stage least squares, and probit analysis. JMP provides most of these, though JSL may be required in some cases.
- SPSS Statistics Professional includes SPSS Base Statistics as well as decision trees, forecasting, missing value imputation and a few other things. JMP has many capabilities to deal with missing values, though more options to deal with missing data are in the Explore Missing Values affording scientists and engineers most of what they need.
- SPSS Statistics Premium builds on the Professional bundle and adds structural equation modeling (SEM), bootstrapping, advanced sampling assessment and testing, and more. JMP Pro now has SEM. JMP Pro also has bootstrapping, and one could credibly make the case that it is more intuitive and easy-to-use because it is as easy as right clicking a statistic in a report.
- SPSS has tools to find the right sample size and determine the exact test for small samples. In every grant, and most psychology journals it is required to show effect sizes of the phenomenon and factors you are studying. JMP Pro has exact tests and with the general simulation functionality in JMP Pro, you can perform power calculations.
- SPSS premium includes RFM (Recency, Frequency and Monetary value) analysis for direct marketing and product decision-making procedures. RFM analysis is a technique used to group or segment existing customers based on historic behavior in the hopes that history can, with the right motivators, be caused to repeat or even improve upon itself. Uplift in JMP Pro can identify the consumer segments most likely to respond favorably to an offer/ treatment and can use historic data to help maximize this treatment effect.
- With Multiple Factor Analysis added in JMP 14, sensory analysts can more easily do this analysis in JMP. Doing such an analysis in SPSS, requires writing code. We have continued to build our capabilities for consumer and market research and are more competitive in this area. SPSS has not invested further in their market research capabilities.
- IBM SPSS Statistics also runs on servers. JMP can be a full client to SAS on a server and with special licensing can be installed on a server. Also, with increasingly more compute power available on PCs as well as the low price of memory, it is reasonably easy to equip key users with powerful hardware, which bridges the gap between what is possible on a desktop and what tasks require the use of server-based software.
Feature Weakness and JMP Response
- To get missing value analysis, advanced data preparation, decision trees, forecasting, and categorical analysis, users must purchase the Professional edition of SPSS. To get power analysis, bootstrapping, advanced sampling and a few other capabilities, users must purchase the Premium edition. Most of these capabilities (even if at a basic level) are in JMP—so with JMP you get more in our “base” offering without being forced to decide on which modules to purchase or add on.
- IBM does not offer much in the way of mapping and partners with ESRI for mapping and location analytics, though they have added a few spatial features. JMP’s support for mapping, including custom shape files and OpenStreetMap allow users to see more of their data in a geospatial context.
- Data and modelling utilities are generally better in JMP due to the in-flow philosophy of JMP. Unlike SPSS, JMP is not a code generator and doesn’t require you to fill out a template to get more than what you desire in each step of the analysis process. Our implementations are generally very well thought through and have many smart defaults. With decades of customer input, we continue to make refinements to streamline the analysis flow.
- Still mainly static graphs versus JMP’s interactive, dynamic ones.
Opportunities for JMP
- Compete on price, dynamic interactive visualization, superior customer support, service, and training.
- Even with base JMP, you get more capabilities and features. Depending on what the prospect is using or is looking to use, there may be opportunities to sell JMP Pro and still compete on price.
- Consider expanding to other groups to reveal potential for software rationalization. If SPSS is used in one group, Minitab, Angoss, Reliasoft, etc. in other groups, the 80-20 rule of getting them most of what they need may work in our favor.
- Show how nicely JMP incorporates maps in our graphics, and other capabilities that are generally appealing. Show Profilers, Graph Builder, Tabulate, Excel Import Wizard, Functional Data Explorer, and the ability to easily import SPSS .sav files and get right to analyzing the data they have now with no downtime. Show them that the transition will be easy. Importing SPSS files preserves much of the metadata that is in the .sav file, so other than learning the JMP interface they can get up and running with minimal effort.
- Share with prospects Moving from SPSS to JMP: A Transition Guide.
Threats for JMP
- IBM has been known to give the software away for free if they make their margin on services and/or hardware.
- To the best of our knowledge, IBM puts no restrictions on the use of their software for consulting or using on third-party data as SAS does. This may make it more attractive for consultants.
Pricing
- According to their pricing page, a monthly Base subscription is $99/month per user with add-ons available for $79 each per user per month. An annual per-user license for
- Base Statistics is $1,290.
- Standard is $2,850.
- Professional is $5,730.
- Premium is $8,540.
- You would still have to buy SPSS Modeler to get some of the near-equivalent algorithms in JMP (more advanced implementations in JMP Pro).
- Information about how they define users and license types.
Competitive references where we’ve won against them or displaced them.
University of Antwerp
