Beyond p-values: A comparative framework for estimation-based inference using the a priori procedure and gain–probability analysis

Tonghui Wang; S.T. Boris Choy; David Trafimow; Xiangfei Chen; Ziyuan Wang

doi:10.63065/ajafe.2026.1.2.001

Asian Journal of Applied Financial Econometrics (AJAFE)

Volume 1_Number 2 , Tháng 8/2026, Trang 2-15

Beyond p-values: A comparative framework for estimation-based inference using the a priori procedure and gain–probability analysis

Tonghui Wang, S.T. Boris Choy, David Trafimow, Xiangfei Chen, Ziyuan Wang

DOI: 10.63065/ajafe.2026.1.2.001

Ngày nhận bài: 08/05/2026

Ngày nhận bài sửa: 12/08/2026

Ngày duyệt đăng: 18/08/2026

Email: twang@nmsu.edu

Đơn vị công tác:

Lượt xem: 177

Downloads: 0

Các định dạng trích dẫn

Tóm tắt

Purpose - This paper compares three inferential paradigms, Null Hypothesis Significance Testing (NHST), the A Priori Procedure (APP) and Gain–Probability (G–P) analysis, and advocates a conceptual shift away from binary hypothesis testing toward inference frameworks grounded in estimation and probability.

Design/methodology/approach - NHST, which relies on p-values and dichotomous decision rules, is contrasted with APP, which emphasizes pre-data estimation reliability, and with G–P analysis, which quantifies the probability that one outcome exceeds another and the extent to which it does. APP is derived for parameter estimation in linear regression models under skew-normal error structures, including results on the distribution of regression estimators. The G–P framework is examined for gamma-distributed variables in both independent and dependent settings. Both are supported by simulation studies and real-world applications.

Findings - Beyond their conceptual advantages, the APP and G–P paradigms are highly applicable in practice, as shown by the simulation studies and empirical illustrations. The shift they represent aligns with broader methodological reforms that prioritize estimation, transparency and interpretability.

Originality/value - The paper extends APP to linear regression with skew-normal errors and G–P analysis to gamma-distributed variables under independence and dependence. Together, these frameworks offer a rigorous and interpretable alternative to conventional significance testing by prioritizing estimation accuracy, probabilistic interpretation and practical relevance.

Từ khóa

Null Hypothesis Significance Testing (NHST), A Priority Procedure (APP), Gain Probability (G-P) Analysis, Estimation Based Inference, Skew Normal distribution, Gamma Distribution, Statistical Methodology.

Download

Tài liệu tham khảo

Amrhein, V., Greenland, S., and McShane, B. (2019). Scientists rise up against statistical significance. Nature, 567(7748):305–307.

Cohen, J. (1994). The earth is round (p < .05). American Psychologist, 49(12):997–1003.

Cumming, G. (2014). The new statistics: Why and how. Psychological Science, 25(1):7–29.

Fisher, R. A. (1925). Theory of statistical estimation. In Mathematical proceedings of the Cambridge philosophical society, volume 22, pages 700–725. Cambridge University Press.

Gigerenzer, G. (2004). Mindless statistics. Journal of Socio-Economics, 33(5):587–606.

Goodman, S. N. (2008). A dirty dozen: twelve p-value misconceptions. Seminars in Hematology, 45(3):135–140.

Hubbard, R. and Bayarri, M. J. (2003). To p or not to p? Psychological Bulletin, 133(4):605–617.

Kotz, S., Balakrishnan, N., and Johnson, N. L. (2019). Continuous multivariate distributions, Volume 1: Models and applications, volume 1. John wiley & sons.

Ma, Z., Wang, T., Wei, Z., and Zhu, X. (2022). Inferences on location parameters based on independent multivariate skew normal distributions. Asian Journal of Economics and Banking, 6(2):270–281.

Nadarajah, S. and Gupta, A. K. (2006). Some bivariate gamma distributions. Applied mathematics letters, 19(8):767–774.

Neyman, J. and Pearson, E. S. (1933). Ix. on the problem of the most efficient tests of statistical hypotheses. Philosophical Transactions of the Royal Society of London. Series A, Containing Papers of a Mathematical or Physical Character, 231(694-706):289–337.

Tong, T., Trafimow, D., Wang, T., Wang, C., Hu, L., and Chen, X. (2022a). The a priori procedure (app) for estimating regression coefficients in linear models. Methodology, 18(3):203–220.

Tong, T., Wang, T., Trafimow, D., and Wang, C. (2022b). The probability of being better or worse off, and by how much, depending on experimental conditions with skew normal populations. In International Conference of the Thailand Econometrics Society, pages 261–284. Springer.

Trafimow, D. and Marks, M. (2015). Editorial in basic and applied social psychology. Basic and Applied Social Pschology, 37:1–2.

Trafimow, D., Roth, N., Xu, L., Toomasian, D., Perrello, A., Tong, T., Wang, T., Choy, S. B., Chen, X., Wang, C., et al. (2023). Surprising implications of differences in locations versus differences in means. Methodology, 19(2):152–169.

Trafimow, D., Tong, T., Wang, T., Choy, S. T. B., Hu, L., Chen, X., Wang, C., and Wang, Z. (2024). Improving inferential analyses: Predata and postdata. Psychological Methods. Advance online publication.

Trafimow, D., Wang, T., and Wang, C. (2019). From a sampling precision perspective, skewness is a friend and not an enemy! Educational and Psychological Measurement, 79(1):129–150.

Wasserstein, R. L. and Lazar, N. A. (2016). The asa’s statement on p-values: context, process, and purpose. The American Statistician, 70(2):129–133.

Wasserstein, R. L., Schirm, A. L., and Lazar, N. A. (2019). Moving to a world beyond “p < 0.05”.