A DB estimation method for the E-MN probability distribution parameters with applications in humanities

Document Type : Research Paper

Author

Department of Statistics, Payame Noor University, Tehran, Iran

Abstract

One of the humanities' most basic topics is the response time to creative problem-solving and decision-making in this field. In recent years, response time modeling by fitting an exponentially-modified normal (E-MN) probability distribution and the results obtained from this process have been widely used. The E-MN probability distribution results from the convolution of a normal probability distribution and an exponential probability distribution and contains three parameters. In this paper, a developed Bayesian (DB) estimation method is introduced to estimate the parameters of an E-MN probability distribution. This new estimation method uses the adaptive rejection Metropolis-Hastings (ARM-H) sampling method. The reason for this is that in normal mode and based on the classical Bayesian estimation method, the chosen prior probability density functions (pdfs) lead to posterior pdfs with unknown form and, they are not always logarithmically concave. Also, respectively, simulation and real data sets study have been done to demonstrate the better performance of the DB estimation method than the two other well-known estimation methods used in this context, including the maximum likelihood (ML) estimation method and the quantile maximum likelihood (QML) estimation method. To show the better efficiency of the proposed estimation method compared with the two other estimation methods, the root mean squared error (RMSE) criterion is used.

Keywords

Main Subjects


[1] S. Ali, J. Ara and I. Shah, A comparison of di erent parameter estimation methods for exponentially modi ed Gaussian distribution. Afrika Matematika, 33(2): (2022) 1{34.
[2] J. Ara, S. Ali and I. Shah, Monitoring schedule time using exponentially modi ed Gaussian distribution. Quality Technology & Quantitative Management, 17(4): (2020) 448{469.
[3] M. Bagnoli, and T. Bergstrom, Log-concave probability and its applications. Economic Theory, 26 (2): (2005) 445{469.
[4] A. Berger, and M Keifer, Comparison of di erent response time of outlier exclusion methods: a simulation study. Frontiers in Psychology, 12: (2021) 1{13.
[5] B. Cai, R. Meyer and F. Perron, Metropolis-Hastings algorithm with adaptive proposals. Statistics and Computing, 18 (4): (2008) 421{433.
[6] M.S.N Chowdhury, A. Dutta, M.K. Robison, C. Blais, G.A. Brewer and D.W. Bliss, Deep neural network for visual stimulus-based reaction time estimation using the periodogram of single-trial EEG. MDPI, 20 (21): (2020) 1{20.
[7] D. Cousineau and T.A. Allan, Likelihood and its use in parameter estimation and model comparison. Measurement and evaluation education, 37 (3): (2015) 63{98.
[8] M.R.W. Dawson, Fitting the ex-Gaussian equation to reaction time distributions. Behavior Research Methods, Instruments, & Computers, 20 (1): (1988) 54{57.
[9] P. De Boeck and M. Jeon, An overview of models for response times and processes in cognitive tests. Frontiers in Psychology, 10: (2019) 1{11.
[10] P. Erickson, The world the game theorists made. University of Chicago Press, 2015.
[11] T.J. Faulkenberry, Psychological statistics, the basics (1st edition). Routledge, 2022.
[12] L.M. Fernandez, M.A. Vadillo, Flexibility in reaction time analysis: many roads to a false positive? The Royal Society Open Science, 7 (20): (2020) 1{8.
[13] D. Fitousi, Decomposing the composite face e ect: evidence for non-holistic processing based on the ex-Gaussian distribution. Quarterly Journal of Experimental Psychology, 73 (6): (2020) 819{840.
[14] C. Gosse, M.V. Reybroeck, Do children with dyslexia present a handwriting de cit? Impact of word orthographic and graphic complexity on handwriting and spelling performance. Research in Developmental Disabilities, 97: (2020) 1{14.
[15] N. Guy, O.C. Lancry-Dayan and Y. Pertzof, Not all  xations are created equal: the bene ts of using ex-Gaussian modeling of  xation durations. Journal of Vision, 20 (10): (2020) 1{16.
[16] A. Heathcote, S. Brown, and D.J.K. Mewhoet, Quantile maximum likelihood estimation of response time distributions. Psychonomic Bulletin & Review, 9 (2): (2002) 394{401.
[17] J. Holden, E. Francisco, R. Lensch, A. Tommerdahl, B. Kirsch, L. Zai, R. Dennis and Tommerdahl, Accuracy of di erent modalities of reaction time testing: implications for online cognitive assessment tools. bioRxiv, (2019) 1-21.
[18] A. Hutt, W. Stannat and R. Potthast, Data assimilation and control: theory and applications in life sciences. Frontiers Media SA. 2019.
[19] S. Jackman, Bayesian analysis of the social sciences. John Wiley & Sons. 2009.
[20] D. Keirnan, and D.R. Bear, What spelling tells us about the orthographic development and word study instruction with emergent bilingual secondary students. Reading psychology, 39 (3): (2018) 227{252.
[21] M.R. Kramer, P.H, Cox, A.B. Yu, D.J. Kravitz and S.R. Mitro , Moving beyond the keypress: as technology advances, so should psychology response time measurements. Perception. 50 (6): (2021) 555{565.
[22] H. Lewandowsky, and S. Farrel, Computational modeling in cognition: principles and practice. SAGE. 2011.
[23] T.D. Little, The Oxford handbook of quantitative methods, volume 1: foundations. Oxford University Press, 2013.
[24] F. Marmolejo-Ramos, D. Cousineau, L. Benites and R. Maehara, On the ecacy of procedures to normalize ex-Gaussian distributions. Frontiers in Psychology, 5: (2015) 1{13.
[25] L. Martino, J. Read and D. Luengo, Independent doubly adaptive rejection Metropolis sampling within Gibbs sampling. IEEE Transactions on Signal Processing, 63 (12):(2015) 3123{3138.
[26] T. Moins, J. Arbel, A. Dutfoy and S. Girard, A local version of R-hat for MCMC convergence diagnostic. SFdS 2022 - 53emes Journees de Statistique de la Societe Francaise de Statistique, (2022) 1{6.
[27] E.M. Palmer, T.S. Horowitz, A. Torralba and J.M. Wolfe, What are the shapes response time distributions in visual search? J Exp Psychol Hum Percept Perform, 73 (1): (2011) 58{71.
[28] S. Panis, F. Schmidt, M.P. Wolkersdolfer and T. Schmidt, Analyzing Response Times and Other Types of Time-to-Event Data Using Event History Analysis: A Tool for Mental Chronometry and Cognitive Psychophysiology. i-Perception, 11 (6): (2020) 1{24.
[29] M. Ra que, S. Ali, I. Shah and B. Ashraf, A comparison of di erent Bayesian models for leukemia data. American Journal of Mathematical and Management Sciences, (2021) 1{15.
[30] J. Ranger, J.T. Kuhn and T.M. Ortner, Modeling responses and response times with the hierarchical model and the three-parameter lognormal distribution. Educational and Psychological , 80 (6): (2020) 1059{1089.
[31] B.V.R. Reddy, P. Pagadala and G.M. Rayalu, Analysis of transformations and their applications in statistics: extended Box and Cox transformation regression. LAP LAM-BERT Academic Publishing, 2013.
[32] A. Roelofs, One hundred  fty years after Donders: insights from unpublished data, a replication, and modeling of his reaction times. Acta Psychologica, 191: (2018) 228{233.
[33] G.A. Rousselet, R.R. Wilcox, Reaction times and other skewed distributions: problems with the mean and the median. Meta-Psychology, 4: (2019) 1-39.
[34] D.P. Spangler, K.R. Cox, J.F. Thayer, J.R. Brooks and B.H. Freidman, Interplay between state anxiety, hear rate variability, and cognition: an ex-Gaussian analysis of AR times. International Journal of Psychophysiology, 159: (2021) 60{70.
[35] P.M. Steiner, Y. Kim, C.E. Hall and D. Su, Graphical models for quasi-experimental designs. Sociological Methods & Research, 46 (2): (2017) 155{188.
[36] R.J. Sternberg, The Cambridge handbook of the intellectual history of psychology. Cambridge University Press, 2019.
[37] A. Vatakis, F. Balci, M.D. Luca and A. Correa, Timing and time perception: procedures, measures, & applications. BRILL, 2018.
[38] K. Wada, Outliers in ocial statistics. Japanese Journal of Statistics and Data Science, 3. (2020) 669{691.
[39] A. Wolf, Textbook of logic. Routledge, 2020.
[40] A. Yamashita, D. Rothlein, A. Kucye, E.M. Valera, L. Germine, J. Wilmer, J. DeGutis and M. Esterman, Variable rather than extreme slow reaction times distinguish brain states during sustained attention. Scienti c Reports, 11 (1): (2021) 1{13.