Deciding on appropriate statistical techniques during the data analysis process remains one of the most challenging steps for researchers, particularly for those with limited statistical and methodological proficiency (Dowdy et al., 2004; Pallant, 2010). Using inappropriate techniques can lead to biased inferences, ethical problems and diminished research quality (Gardenier&Resnik, 2002; Cramer, 2003; Good&Hardin, 2012). To overcome this challenge, researchers might try to find some solutions such as consulting textbooks, academic articles and similar written documents, asking for help from peers or academic advisors, or taking advantage of internet-based resources including social media and AI-based chatbots (Güngör&Demir, 2024a, 2024b). Although there are a variety of such sources that can be considered, these solutions can be ineffective and misleading due to limited statistical and methodological background.

There are many statistical techniques that can be employed in data analysis. And it’s not easy to classify them into a practical decision tree or flowchart. Several resources include classification of a limited number of statistical techniques into a decision tree or a flowchart based on the data and variable characteristics (Rosner, 2016; Field, 2019; Hair et al., 2019). A few others give classifications that matched to the research objectives or purpose of data analysis (Tabachnick&Fidell, 2019; Mertler et al., 2019). All these approaches may include a limited number of techniques due to the difficulties of bringing them together in a single decision tree or flowchart. Moreover, there is an ongoing uncertainty regarding the determination of the classification approach.

Technology comes up with some certain advantages to handle such kind of challenges. With the support of digital technologies, it has become possible to classify a huge number of techniques in a practical web-based application with the necessary brief explanations and additional links. ‘Statistical Technique Advisor’ is an interactive and web-based application to assist researchers in finding appropriate statistical technique in their research. This app was developed under a project that lasted 11 months and was supported by TÜBİTAK (Project no. 223K382), The Scientific and Technological Research Council of Türkiye. Within the scope of this project, comprehensive studies were carried out in three main stages to develop a web-based application. With the studies under the project, ‘Statistical Technique Advisor’ was developed and released with free access on the internet at the following web address.  https://erguldemir.shinyapps.io/StatisticalTechniqueAdvisor/

This study aims to identify the challenges faced by researchers, discuss the solutions they have implemented, and outline the development process of ‘Statistical Technique Advisor’ an interactive and web-based application. It is also aimed to evaluate the quality, usability and potential effectiveness of the application based on feedback from experts and users. To achieve this aim, the following research questions were taken into consideration:

1. To what extent do researchers have difficulty in finding the appropriate statistical technique for their research and to what extent do they consider themselves proficeint?
2. What solutions do they use to overcome these difficulties?
3. What is the development process and features of 'Statistical Technique Advisor’?
4. According to the evaluations of experts and users, how qualified is the ‘Statistical Technique Advisor’ application in assisting researchers?

This study aligns with the ECER2025 Network 16 theme, specifically focusing on the assessment and evaluation of the impact of ICT in education and training. By exploring the role of the ‘Statistical Technique Advisor’ as a digital support tool, the study examines its potential to address researchers’ methodological challenges and improve decision-making in statistical techniques. Furthermore, the evaluation of the tool’s potential effectiveness provides insights into the broader implications of ICT-based solutions for research education and training.

This study conducted as an applicational research defined as research that focuses on solving a practical problem and practical application or product, as opposed to basic research that aims to reveal new knowledge or a theory (Fraenkel et al., 2012). All sub-studies for the development of application were carried out within the scope of a project in three main stages: (1) theoretical preparations and field studies, (2) practical software development process, and (3) experts’ and users’ evaluations. The first phase involved conducting literature reviewing and followed by field studies with 52 doctoral and master’s students and 30 academicians. The study groups were identified by the maximum variation sampling method, considering some selection criteria such as (1) being from different universities and disciplines as possible, (2) having as many different statistical competency backgrounds as possible, (3) having a certain level of data analysis experience, and (4) being familiar with the concept of statistical data analysis in research. This field study included face-to-face interviews, group interviews, and application of an online questionnaire form to gain insights into the difficulties researchers encounter and solutions they employed. In the second stage, the application’s architectural structure was designed based on flowcharts to classify statistical techniques effectively (Şengül&Demir, 2024). This was followed by the code writing process of the application involved extensive coding, primarily in the R programming language (R Core Team, 2024), alongside R-shiny package (Chang et all., 2024), HTML and JavaScript for user interface enhancements. The application was tested extensively to ensure functionality and reliability before being released to the public usage. The third stage of the project involved a 3-day workshop with 15 experts in 3 desks, who evaluated the quality of the application. The experts provided valuable feedback on the application’s strengths, such as its comprehensive content and ease of use, and offered suggestions for improvement. A final evaluation was conducted with 101 users, primarily doctoral students, as well as master’s students and academicians, using an online user evaluation form. The qualitative data obtained from interviews and open-ended items in questionnaires were analysed with thematic document analysis (Patton, 1990; Bowen, 2009). Quantitative data obtained from the questionnaires were analysed with descriptive techniques and visualised with graphs. All analyses and reporting studies, as well as coding and releasing steps of the application were done in R.

Findings indicated that a vast majority of the participants struggled with finding appropriate statistical techniques, mostly due to limited statistical knowledge and proficiency. These difficulties frequently lead them to seek external support through consulting books, academic articles, and similar written resources. They also rely heavily on peers, academic advisors, and internet-based solutions, including social media platforms and AI-powered chatbots. However, although these resources can be useful, they may not provide sufficient support, especially for researchers with low and medium levels of competence, as they often require a certain level of basic statistical and methodological competence. This gap underscores the need for practical, more accessible and comprehensively structured tools to support researchers in finding appropriate statistical techniques. The development of the ‘Statistical Technique Advisor’ addresses this need by providing an interactive, web-based application that assists researchers in identifying appropriate statistical techniques based on the purpose of data analysis and data structure. Unlike traditional resources, this application offers a tailored and user-friendly experience, significantly reducing reliance on prior expertise. By integrating over 200 statistical techniques into its flowchart-based architecture, the tool simplifies the identification process and assists researchers to make informed decision with confidence. Field studies and user evaluations revealed the application’s potential to assist researchers in finding appropriate statistical techniques. The results from an expert workshop and feedback from users indicated that the application is high-quality, easy to use, and particularly beneficial for researchers with low to moderate level of statistical proficiency. While users expressed their satisfaction with the clarity and practicality of the tool, experts also emphasised the comprehensive content and interactive design of the application. Besides, improvements are planned to update the 'Statistical Technique Advisor', such as adding more techniques, strengthening the interface design, supporting with data analysis examples, and creating pop-up windows for technical terminology.

Bowen, G. A. (2009). Document analysis as a qualitative research method. Qualitative Research Journal, 9(2), 27-40. DOI:10.3316/QRJ0902027 Chang, W; Cheng, J.; Allaire, J., et.al. (2024). shiny: Web Application Framework for R. R package version 1.10.0, https://CRAN.R-project.org/package=shiny Cramer, D. (2003). Advanced quantitative data analysis. Open University Press, Mc-Graw Hill. Dowdy, S., Wearden, S., & Chilko, D. (2004). Statistics for research (3rd ed.). Wiley. Field, A. (2019). Discovering statistics using IBM SPSS statistics (5th ed.). SAGE Publications. Fraenkel, J. R., Wallen, N. E., & Hyun, H. H. (2012). How to design and evaluate research in education (8th edition). New York, NY, The McGraw-Hill Companies, Inc. Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2019). Multivariate data analysis (8th ed.). Cengage Learning. Gardenier, J., & Resnik, D. (2002). The misuse of statistics: Concepts, tools, and a research agenda. Accountability in Research, 9(2), 65-74. DOI: 10.1080/08989620212968 Good, P. I., & Hardin, J. W. (2012). Common errors in statistics (and how to avoid them) (4th edition). Hoboken, New Jersey, John Wiley & Sons, Inc. Güngör, M., & Demir, E. (2024a). Opinions of graduate students about the challenges they encounter in determining and using statistical techniques. In proceeding of XI. International Eurasian Educational Research Congress (EJER) (pp. 332-339). Kocaeli University, Kocaeli, Türkiye. Güngör, M., & Demir, E. (2024b). Faculty members' perspectives on the challenges faced by students and researchers in statistical data analysis and determining appropriate statistical techniques. In A. M. de E. Fernandez et al. (Eds.), 6th International Mediterranean Scientific Research Congress Full Texts Book Volume-1 (pp. 91-96). IKSAD Publishing House. Mertler, C. A., Vannatta, R. A., & Lavenia, K. N. (2019). Advanced and multivariate statistical methods (7th ed.). Routledge. Pallant, J. (2010). SPSS survival manual: A step by step guide to data analysis using SPSS (4th edition). New York, NY, Open University Press, McGraw-Hill Education. Patton, M. (1990). Qualitative evaluation and research methods. Beverly Hills, CA, Sage R Core Team (2023). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/ Rosner, B. (2016). Fundamentals of biostatistics (8th ed.). Cengage Learning. Şengül, M., & Demir, E. (2024). Investigation of flowcharts and decision trees for classification of statistical techniques. In Y. Tahtalı (Ed.), V. International Applied Statistics Congress (pp. 857-863). Marmara University, İstanbul, Türkiye. Tabachnick, B. G. & Fidell, L. S. (2019). Using multivariate statistics (7th ed.). Pearson Education.