Theoretical Versus Mathematical Approach to Modeling Psychological and Physiological Data

Variable selection for predictive modeling has traditionally relied on theory in the psychological domain. Given the recent advancements in computing technology and availability, researchers are able to utilize more sophisticated mathematical modeling techniques with greater ease. The challenge becomes evaluating whether theory or mathematics should be relied upon for model development. The presented analyses compared the use of hierarchical and stepwise variable selection methods during a predictive modeling task using linear regression. The results show that the stepwise variable selection method is able to obtain a more efficient model than the hierarchical variable selection method. Implications and recommendations for researchers are further discussed.

[1]  C. Ferguson.  An effect size primer: A guide for clinicians and researchers. , 2009 .

[2]  Francesco Di Nocera,et al.  Another look at scanpath: distance to nearest neighbour as a measure of mental workload , 2006 .

[3]  J. Veltman,et al.  Physiological workload reactions to increasing levels of task difficulty. , 1998, Ergonomics.

[4]  K. F. Tan,et al.  Detection of the QRS complex, P wave and T wave in electrocardiogram , 2000 .

[5]  Joel S. Warm,et al.  Cerebral Hemodynamic Indices of Operator Fatigue in Vigilance , 2017 .

[6]  J. Elashoff,et al.  Multiple Regression in Behavioral Research. , 1975 .

[7]  Gerhard Tröster,et al.  Monitoring of mental workload levels during an everyday life office-work scenario , 2013, Personal and Ubiquitous Computing.

[8]  J. Holden,et al.  Relations between PET-derived measures of thalamic glucose metabolism and EEG alpha power. , 1998, Psychophysiology.

[9]  T. Ergenoğlu,et al.  Alpha rhythm of the EEG modulates visual detection performance in humans. , 2004, Brain research. Cognitive brain research.

[10]  Michael A Babyak,et al.  What You See May Not Be What You Get: A Brief, Nontechnical Introduction to Overfitting in Regression-Type Models , 2004, Psychosomatic medicine.

[11]  Lauren Reinerman-Jones,et al.  Developing Methods for Utilizing Physiological Measures , 2010 .

[12]  A J Tattersall,et al.  An experimental evaluation of instantaneous self-assessment as a measure of workload. , 1996, Ergonomics.

[13]  J. Abich.  Investigating The Universality And Comprehensive Ability Of Measures To Assess The State Of Workload , 2013 .

[14]  John M. Ferron,et al.  Selection of variables in exploratory factor analysis: An empirical comparison of a stepwise and traditional approach , 2004 .

[15]  Howard B. Lee,et al.  Foundations of Behavioral Research , 1973 .

[16]  Robert J. K. Jacob,et al.  Eye tracking in human-computer interaction and usability research : Ready to deliver the promises , 2002 .

[17]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[18]  S. P. Marshall,et al.  The Index of Cognitive Activity: measuring cognitive workload , 2002, Proceedings of the IEEE 7th Conference on Human Factors and Power Plants.

[19]  M. Rugg,et al.  Electrophysiological correlates of memory encoding are task-dependent. , 2001, Brain research. Cognitive brain research.

[20]  S. Hart,et al.  Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research , 1988 .

[21]  Lauren Reinerman-Jones,et al.  Psychophysiological Metrics for Workload are Demand-Sensitive but Multifactorial , 2014 .

[22]  Scott Makeig,et al.  Eye Activity Correlates of Workload during a Visuospatial Memory Task , 2001, Hum. Factors.

[23]  M. Thompson.  Selection of Variables in Multiple Regression: Part I. A Review and Evaluation , 1978 .

[24]  William F. Moroney,et al.  A comparison of two scoring procedures with the NASA task load index in a simulated flight task , 1992, Proceedings of the IEEE 1992 National Aerospace and Electronics Conference@m_NAECON 1992.

[25]  J. Beatty.  Task-evoked pupillary responses, processing load, and the structure of processing resources. , 1982 .

[26]  Raja Parasuraman,et al.  Using Transcranial Doppler Sonography to Measure Cognitive Load in a Command and Control Task , 2010 .

[27]  José del R. Millán,et al.  Improving Human Performance in a Real Operating Environment through Real-Time Mental Workload Detection , 2007 .

[28]  H. Asada,et al.  Frontal midline theta rhythms reflect alternative activation of prefrontal cortex and anterior cingulate cortex in humans , 1999, Neuroscience Letters.

[29]  Michael E. Smith,et al.  Monitoring Task Loading with Multivariate EEG Measures during Complex Forms of Human-Computer Interaction , 2001, Hum. Factors.

[30]  Britton Chance,et al.  Functional Optical Brain Imaging Using Near-Infrared During Cognitive Tasks , 2004, Int. J. Hum. Comput. Interact..

[31]  Grant Taylor,et al.  Establishing Workload Manipulations Utilizing a Simulated Environment , 2013, HCI.