JMP Review: Good for Visual Charts/Graphs, Data Mining, and Experiment Design (DOE)
March 26, 2014

JMP Review: Good for Visual Charts/Graphs, Data Mining, and Experiment Design (DOE)

Eric Burton | TrustRadius Reviewer
Score 8 out of 10
Vetted Review
Verified User

Software Version


Overall Satisfaction with JMP

In our company, JMP is used primarily for data analysis by the engineering support group. We use JMP's analysis capability to leverage data to make better decisions, AND to help show that data to tell a story to others in the organization.
  • JMP is GREAT with graphical representations of data. It has a very graphical interface that allows for intuitive interaction. For example, if I graph a distribution of data, and I have some outliers, circling that area of the graph will hilight the rows of data on the corresponding table.
  • JMP's graph builder is a big hit. If I have a complex data set, I may know that I want to display it visually, but might not be sure about the best way to do that. The graph building feature is a fantastic way to "poke and prod" at the graph and get it to look just right. The map support is great. You want to show sales volumes by state in a map? JMP does it in a snap. The inner geek in you will get a kick out of all the ways you can show your data!
  • JMP is tuned to letting your numbers tell a story. If you have data, and a clear decision, but have trouble showing that to others, JMP can be extremely valuable. You can export your analyses as PDF files for easy viewing, and some modeling can even be saved as interactive HTML files, so that others can explore the data on their own.
  • One thing that you get with JMP that is hard to quantify, is access to a tremendous community of problem solvers, statisticians, and people using data to make better decisions. Most communities have a JMP Users Group (JUG) that provides a forum to learn from peers how to apply JMP's capabilities in new ways. Also, JMP will occasionally provide speakers and trainers as part of their discovery series, where you can hear presentations from some really high caliber people who are on the cutting edge of experiment design, data representation, and data mining. (All of these things I've just mentioned are provided at no additional cost.) Elsewhere in my review I mentioned that JMP's price structure, (high initial seat prices with prorated prices as you add users) might be prohibitive. I HAVE to think that their pricing model represents their commitment to support their software and get you up and using it.
  • In general JMP is much better fit for a general "data mining" type application. If you want a specific statistics based toolbox, (meaning you just want to run some predetermined test, like testing for a different proportion) then JMP works, but is not the best. JMP is much more suited to taking a data set and starting from "square 1" and exploring it through a range of analytics.
  • The CPK (process capability) module output is shockingly poor in JMP. This sticks out because, while as a rule everything in JMP is very visual and presentable, the CPK graph is a single-line-on-grey-background drawing. It is not intuitive, and really doesn't tell the story. (This is in contrast with a capability graph in Minitab, which is intuitive and tells a story right off.) This is also the case with the "guage study" output, used for mulivary analysis in a Six Sigma project. It is not intuitive and you need to do a lot of tweaking to make the graph tell you the story right off. I have given this feedback to JMP, and it is possible that it will be addressed in future versions.
  • I've never heard of JMP allowing floating licenses in a company. This will ALWAYS be a huge sticking point for small to middle size companies, that don't have teams people dedicated to analytics all day. If every person that would do problem solving needs his/her own seat, the cost can be prohibitive. (It gets cheaper by the seat as you add licenses, but for a small company that might get no more than 5 users, it is still a hard sell.)
  • Analyzing models from DOE with JMP has allowed more robust product design. I'm not at liberty to give the specific numbers, but the difference was significant
  • Numerous times we have been spared the lost resources of pursuing a problem that was NOT statistically justified by being able to show the data
  • With the visualization capabilities of JMP we reported rigorous testing from our R&D lab and were able to convince board members of a necessary process change that was previously held up, not from lack of data, but from excess emotion.
JMP is better with visual data representation, and as a general statistics exploration package. Technical needs like Design of Experiments are just easier to do in JMP
I've mentioned this earlier, but the licensing agreements are very prohibitive. I work with a company where my role has become less and less doing my own analytics and more and more trying to help other people in that role. As we are bringing more people "up to speed" it's hard to justify licenses for 2-3 people when they aren't full time, Six Sigma black belts just looking at stats all day. A floating license option would make this a no-brainer, since these people could continue their other work and add JMP usage as they grow their skills, but this is not something JMP/SAS has offered.
Are you interested in high level data mining? Does your team participate in a lot of Statistically Designed Experiments? (DOE) JMP does very well here. Are you performing response modeling and creating prediction equations? JMP does this very well. Are you focused on good looking, graphical representations of your data? JMP SHINES in the presentation arena. Do you have some "stats geeks" on staff that know the numbers, but want a fast way to share reporting with others? JMP is a good avenue for this.

However, are you looking for a "quick and dirty" stats toolbox for SPC/control charting, for CPK analyses, t-tests or proportion testing? Are you looking for a "vending machine" interaction where you know exactly what you want and you just want one output? If the above describes you more closely, I'd suggest something closer to Minitab.