Multilevel models for repeated measures research designs in psychophysiology: an introduction to growth curve modeling.

Psychophysiologists often use repeated measures analysis of variance (RMANOVA) and multivariate analysis of variance (MANOVA) to analyze data collected in repeated measures research designs. ANOVA and MANOVA are nomothetic approaches that focus on group means. Newer multilevel modeling techniques are more informative than ANOVA because they characterize both group-level (nomothetic) and individual-level (idiographic) effects, yielding a more complete understanding of the phenomena under study. This article was written as an introduction to growth curve modeling for applied researchers. A growth model is defined that can be used in place of RMANOVAs and MANOVAs for single-group and mixed repeated measures designs. The model is expanded to test and control for the effects of baseline levels of physiological activity on stimulus-specific responses. Practical, conceptual, and statistical advantages of growth curve modeling are discussed.

[1]  J. Schwartz,et al.  Workplace Social Support and Ambulatory Cardiovascular Activity in New York City Traffic Agents , 2003, Psychosomatic medicine.

[2]  R. MacCallum,et al.  Studying Multivariate Change Using Multilevel Models and Latent Curve Models. , 1997, Multivariate behavioral research.

[3]  R. Sloan,et al.  Hostility, Interpersonal Interactions, and Ambulatory Blood Pressure , 2003, Psychosomatic medicine.

[4]  B. C. Lacey,et al.  Verification and extension of the principle of autonomic response-stereotypy. , 1958, The American journal of psychology.

[5]  Carol M. Worthman,et al.  Estimating between- and within-individual variation in cortisol levels using multilevel models , 2005, Psychoneuroendocrinology.

[6]  W. Iacono,et al.  Heritability of P300 amplitude development from adolescence to adulthood. , 2006, Psychophysiology.

[7]  Peter J. Gianaros,et al.  Handbook of Psychophysiology: Methodology , 2007 .

[8]  E. Adam,et al.  Relationship functioning and home and work demands predict individual differences in diurnal cortisol patterns in women , 2001, Psychoneuroendocrinology.

[9]  Kenneth A Bollen,et al.  The role of coding time in estimating and interpreting growth curve models. , 2004, Psychological methods.

[10]  J. Smyth,et al.  Individual differences in the diurnal cycle of salivary free cortisol: a replication of flattened cycles for some individuals , 2001, Psychoneuroendocrinology.

[11]  M. Marwitz,et al.  On the status of individual response specificity. , 1998, Psychophysiology.

[12]  S G West,et al.  Putting the individual back into individual growth curves. , 2000, Psychological methods.

[13]  H. Wainer,et al.  The Centercept: An Estimable and Meaningful Regression Parameter , 2000, Psychological science.

[14]  Sean D. Kristjansson,et al.  Rapid discrimination of visual scene content in the human brain , 2006, Brain Research.

[15]  J. Houtveen,et al.  Validation of the thoracic impedance derived respiratory signal using multilevel analysis. , 2006, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[16]  S. Porges.  The polyvagal perspective , 2007, Biological Psychology.

[17]  I G Kreft,et al.  The Effect of Different Forms of Centering in Hierarchical Linear Models. , 1995, Multivariate behavioral research.

[18]  D. Heitjan,et al.  Mixed-effects models in psychophysiology. , 2000, Psychophysiology.

[19]  R. F. Thompson,et al.  Habituation: a model phenomenon for the study of neuronal substrates of behavior. , 1966, Psychological review.

[20]  T. Raghunathan,et al.  Modeling cortisol rhythms in a population-based study , 2005, Psychoneuroendocrinology.

[21]  T H Monk,et al.  The effects of age and gender on sleep EEG power spectral density in the middle years of life (ages 20-60 years old). , 2001, Psychophysiology.

[22]  K. Widaman,et al.  CHAPTER 5 – An Evaluation of Statistical Strategies to Analyze Repeated-Measures Data , 1984 .

[23]  Joseph E Schwartz,et al.  Correspondence between laboratory and ambulatory measures of cardiovascular reactivity: a multilevel modeling approach. , 2003, Psychophysiology.

[24]  Rafa M. Kasim,et al.  Application of Gibbs Sampling to Nested Variance Components Models With Heterogeneous Within-Group Variance , 1998 .