Please share with the community what you think needs improvement with IBM SPSS Statistics.
What are its weaknesses? What would you like to see changed in a future version?
The data preparation skills need improvement. When I compare the solution with other tools or competitors, this solution needs to simplify data preparation. The solution needs more planning tools and capabilities.
I think the duration and time-series need improvement. Some things need more explanation. For instance, if you are using the automated part in SPSS, you have automatic linear modeling. It gives you the meaning of the result, explaining if it is significant. But most of the package will give you the fixed value, or the p-value, without an explanation as to whether it significant or not. Some beginners might need not just the results, but also an explanation for them. This already exists in two parts of the SPSS. One for the automatic linear modeling, and the second for nonparametric. The automation, the automatic part, gives you not only the results and the output but also what this output means. For me as a professional, I can explain the results even if it's not included in the output. But if they were to include some explanation for the results, such as is it significantly based on the P-value, that would make SPSS great. Additionally, there is something else that really needs improvement - the part related to multivariate analysis. The chi-squared for instance. Some packages can give you the chi-squared directly, but in the multivariate part of SPSS, it's not as clear as it should be. So working with the multivariate could be improved or expanded. This last semester I was teaching multivariate to postgraduate students and it was not as clear as it should be. In conclusion, regarding improvements for the package, I can say that multivariate needs improving. Lastly, some results need to be presented in a more diverse way. For instance, if you are working in biostatistics then sensitivity, specificity, and relative risk need to also be included. Some people don't use SPSS because they need some medical calculations and they think that SPSS cannot calculate it. But if you are working with the older, survival analysis, you can add this part to the medical field. Actually, it is really easy to include it and calculate it for it. As I told you, you can add a medical field part for the study design, such as screening tests, sensitivity, specificity and so on.
The licensing model is not popular and should be changed to SaaS. This solution is not suitable for use with Big Data.
In terms of what can be improved, currently, I don't have any ideas because I think that it's in very good shape. It compares with its peers. I do think that the design of the experience can be improved. Also, I think that it can improve its ability to import or export the results from other software.
The areas of SPSS Statics that have room for improvement — where it can be simplified to make it better — have to do with how you connect the SPSS solution with the data. They could provide enhancements like a query console so we can connect to the database and feed data more easily into SPSS. That could be really beneficial and save time and effort. Just enhancing the tools to collect the data would be significant. One other enhancement I would like to see is the ability to create higher-level presentations. When you are finished processing the data, you come up with the result. If you are a technician or a data analyst it is not so hard to look at the data. But what I think would be a nice addition is to create presentations. The bosses at a higher level do not want to see the raw data and to show the data is not so nice and easy for them to understand. Some ways to do more to create a presentation — something that is easier to look at and understand — would be good. The ability to do this should be improved. They need to improve the ability to connect to the databases, provide a query console and query windows. The engine for processing is there already, but the data feed has to be better. Then provide ways to present the result differently. Maybe graphic presentation options would be good so understanding the results can be more intuitive for the user.
One of the areas that should be similar to Minitabs is the use of blogs. The Minitabs blog helps users understand the tools and gives lots of practical examples. Following the SPSS manual is cumbersome. It's a good, exhaustive manual, but it's not practical to use. With Minitabs, you can go to the blogs and find specific articles written about various components and it's very helpful. Without blogs, we find SPSS more complicated.
Each algorithm could be more adaptable to some industry-specific areas, or, in some cases, adapted for maintenance.
I don't know if this solution is available on the cloud. If it is then we should be using it because it would be even better. The on-premises version is lax in terms of computational capability, so we have to use a more powerful computer. Some new tools will be available soon with self-explanatory statistical results, and they have multi-language generations that create automatic reports with detailed explanations of the statistical reports. I wish that they were more advanced. Some areas that need improvement or should be more advanced are in the reporting. The statistics should be more self-explanatory with detailed automated reports. You should be able to walk through with the statistical schematics because some of the matters are advanced, and if you don't have a full understanding or you don't remember how to get the desired results then there should be a guide or a walkthrough to help and explain how it should be applied. In the next release, they should have some new statistical approaches that can be applied, some new memory detection, and new clustering techniques. Also, some new statistical methods to increase the different model's explainability would be helpful.
There are some scheduling issues that created some complex flows. Creating a simple scheduling mechanism would be an improvement for this tool. Technical support needs some improvement, as they do not respond as quickly as we would like. The price is too expensive so they should consider reducing the cost, make it more competitive.
I believe the product could be improved. I think there is an issue with the charting and visualization, and I don't think it works as well as the competitive product. There is a lot of competition with other software, and I think the visualization and charting should be changed and made easier and more effective. They should also try to include better concepts for big data. I don't know if this can be matched or integrated with the flexibility of Python, because now Python is free. When I try to use another software such as JMP software, JMP makes managing, manipulating and changing the perspectives or the analysis points easier. When you compare or make any statistical search for two variables or more, one by one, X and Y and so on, you refer the variables to the original situation and change it. In JMP, you can just drag and drop and switch columns, rows to columns, and vice versa. It's really easy to use. I think the product license is expensive for some people who would be interested in using it, but there is a cheaper version for searches. I think reducing the cost or making a cheaper version for companies should not be a problem. In terms of additional features, I think some enhancement on the panel or the main menu would be helpful. Another thing I would hope to be able to do would be to facilitate the results for the user in one main window. There is a window for data and another window for output. I think maybe there could be an enhancement to make SPSS easier to manage and easier to move between data.