DeepSeek与SPSS在统计分析中的优劣比较研究
A Comparative Study of the Advantages and Disadvantages of DeepSeek and SPSS in Statistical Analysis
DOI: 10.12677/sa.2025.146157, PDF,    科研立项经费支持
作者: 庞沙沙, 叶孟良*:重庆医科大学公共卫生学院,重庆
关键词: DeepSeek统计分析能力比较研究DeepSeek Statistical Analysis Capability Comparative Study
摘要: 目的:比较DeepSeek与SPSS软件在数据分析方面的优劣。方法:比较两者对同一数据集的分析结果验证两者的性能差异。结果:与SPSS软件相比,DeepSeek进行数据预处理的准确性较差;定量资料的统计描述误差不超过2%,但定性资料的误差较大;Logistic回归模型预测准确率较低为67%;因子分析的各个部分输出结果误差均较大,且提取的公因子累计解释方差未达到60%。结论:DeepSeek进行数据处理和分析的准确性不如传统分析软件SPSS,但在易用性和可访问性方面具有优势。
Abstract: The objective of this study is to compare the strengths and weaknesses of DeepSeek and SPSS software in data analysis. To achieve this, the analysis results of the two software on the same dataset were compared to verify their performance differences. The results show that, compared with SPSS software, DeepSeek has lower accuracy in data preprocessing. While the error in the statistical description of quantitative data does not exceed 2%, the error in qualitative data is relatively large. Additionally, the prediction accuracy rate of the Logistic regression model is relatively low, at 67%. The error in each part of the factor analysis output is also relatively large, and the cumulative variance explained by the extracted common factors does not reach 60%. In conclusion, DeepSeek is less accurate than the traditional analysis software SPSS in data processing and analysis. However, it has advantages in terms of user-friendliness and accessibility.
文章引用:庞沙沙, 叶孟良. DeepSeek与SPSS在统计分析中的优劣比较研究[J]. 统计学与应用, 2025, 14(6): 172-178. https://doi.org/10.12677/sa.2025.146157

参考文献

[1] Yu, P., Xu, H., Hu, X. and Deng, C. (2023) Leveraging Generative AI and Large Language Models: A Comprehensive Roadmap for Healthcare Integration. Healthcare, 11, Article No. 2776. [Google Scholar] [CrossRef] [PubMed]
[2] Busch, F., Hoffmann, L., Rueger, C., van Dijk, E.H., Kader, R., Ortiz-Prado, E., et al. (2025) Current Applications and Challenges in Large Language Models for Patient Care: A Systematic Review. Communications Medicine, 5, Article No. 26. [Google Scholar] [CrossRef] [PubMed]
[3] Wang, H., Wu, W., Dou, Z., He, L. and Yang, L. (2023) Performance and Exploration of ChatGPT in Medical Examination, Records and Education in Chinese: Pave the Way for Medical AI. International Journal of Medical Informatics, 177, Article ID: 105173. [Google Scholar] [CrossRef] [PubMed]
[4] Sumbal, A., Sumbal, R. and Amir, A. (2024) Can ChatGPT-3.5 Pass a Medical Exam? A Systematic Review of ChatGPT’s Performance in Academic Testing. Journal of Medical Education and Curricular Development, 11, 1-12. [Google Scholar] [CrossRef] [PubMed]
[5] Gilson, A., Safranek, C.W., Huang, T., Socrates, V., Chi, L., Taylor, R.A., et al. (2023) How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge Assessment. JMIR Medical Education, 9, e45312. [Google Scholar] [CrossRef] [PubMed]
[6] Lin, S., Chan, P.K., Hsu, W. and Kao, C. (2024) Digital Health, 10, 1-11. [Google Scholar] [CrossRef] [PubMed]
[7] Huang, Y., Wu, R., He, J. and Xiang, Y. (2024) Evaluating Chatgpt-4.0’s Data Analytic Proficiency in Epidemiological Studies: A Comparative Analysis with SAS, SPSS, and R. Journal of Global Health, 14, Article No. 04070. [Google Scholar] [CrossRef] [PubMed]
[8] Ignjatović, A. and Stevanović, L. (2023) Efficacy and Limitations of ChatGPT as a Biostatistical Problem-Solving Tool in Medical Education in Serbia: A Descriptive Study. Journal of Educational Evaluation for Health Professions, 20, Article No. 28. [Google Scholar] [CrossRef] [PubMed]
[9] Jahangiri, Y. (2023) Can Chat Generative Pretraining Transformer (ChatGPT) Be Used for Statistical Analysis of Research Data? Journal of Vascular and Interventional Radiology, 34, 2242-2246.e2. [Google Scholar] [CrossRef] [PubMed]
[10] Ordak, M. (2023) ChatGPT’s Skills in Statistical Analysis Using the Example of Allergology: Do We Have Reason for Concern? Healthcare, 11, Article No. 2554. [Google Scholar] [CrossRef] [PubMed]
[11] 丁炜. DeepSeek对生成式人工智能应用的影响与启示[J]. 银行家, 2025(3): 129-134.
[12] 林戴忠. 生成式AI应用于政府统计服务的理论初探[J]. 统计科学与实践, 2023(7): 53-56.
[13] 董昌其, 李大宇, 米加宁. 大模型嵌入政务服务: 能力边界、协同治理与发展路径——基于地方政府大规模部署DeepSeek的观察[J/OL]. 电子政务, 1-9.
https://kns.cnki.net/kcms2/article/abstract?v=UThtwiquHbcEJxykW7L6ZXHPCEuefTn9uDA92BLOVb3prTdtL4IZjz6Nf67BQKnSF4tPXuZOrOHPRQnYEaWvbPf1SU3aUWHpRp4_r9M8bXKXNykYIwMEFCAvMOUJXD3LvcSivWoNsBdInrC-BD_OjZg64sOFSecEdA2QOOnBX17Awi1pB4dIPQ==&uniplatform=NZKPT&language=CHS, 2025-03-19.