Generalized Mahalanobis depth in point process and its application in neural coding

Shuyi Liu; Wei Wu

doi:10.1214/17-AOAS1030

June 2017 Generalized Mahalanobis depth in point process and its application in neural coding

Shuyi Liu, Wei Wu

Ann. Appl. Stat. 11(2): 992-1010 (June 2017). DOI: 10.1214/17-AOAS1030

Abstract

In this paper, we propose to generalize the notion of depth in temporal point process observations. The new depth is defined as a weighted product of two probability terms: (1) the number of events in each process, and (2) the center-outward ranking on the event times conditioned on the number of events. In this study, we adopt the Poisson distribution for the first term and the Mahalanobis depth for the second term. We propose an efficient bootstrapping approach to estimate parameters in the defined depth. In the case of Poisson process, the observed events are order statistics where the parameters can be estimated robustly with respect to sample size. We demonstrate the use of the new depth by ranking realizations from a Poisson process. We also test the new method in classification problems using simulations as well as real neural spike train data. It is found that the new framework provides more accurate and robust classifications as compared to commonly used likelihood methods.

References

1.

Berrar, D. P., Dubitzky, W. and Granzow, M. (2009). A Practical Approach to Microarray Data Analysis. Springer, Berlin.Berrar, D. P., Dubitzky, W. and Granzow, M. (2009). A Practical Approach to Microarray Data Analysis. Springer, Berlin.

2.

Box, G. E. P., Hunter, W. G. and Hunter, J. S. (1978). Statistics for Experimenters: An Introduction to Design, Data Analysis, and Model Building. Wiley, New York.Box, G. E. P., Hunter, W. G. and Hunter, J. S. (1978). Statistics for Experimenters: An Introduction to Design, Data Analysis, and Model Building. Wiley, New York.

3.

Brown, E. N., Barbieri, R., Ventura, V., Kass, R. E. and Frank, L. M. (2001). The time-rescaling theorem and its application to neural spike train data analysis. Neural Comput. 14 325–346.Brown, E. N., Barbieri, R., Ventura, V., Kass, R. E. and Frank, L. M. (2001). The time-rescaling theorem and its application to neural spike train data analysis. Neural Comput. 14 325–346.

4.

Cascos, I. (2007). The expected convex hull trimmed regions of a sample. Comput. Statist. 22 557–569.Cascos, I. (2007). The expected convex hull trimmed regions of a sample. Comput. Statist. 22 557–569.

5.

Diez, D. M., Schoenberg, F. P. and Woody, C. D. (2012). Algorithms for computing spike time distance and point process prototypes with application to feline neuronal responses to acoustic stimuli. J. Neurosci. Methods 203 186–192.Diez, D. M., Schoenberg, F. P. and Woody, C. D. (2012). Algorithms for computing spike time distance and point process prototypes with application to feline neuronal responses to acoustic stimuli. J. Neurosci. Methods 203 186–192.

6.

Drazek, L. C. (2013). Intensity estimation for Poisson Processes. The University of Leeds, School of Mathematics.Drazek, L. C. (2013). Intensity estimation for Poisson Processes. The University of Leeds, School of Mathematics.

7.

Dyckerhoff, R., Mosler, K. and Koshevoy, G. (1996). Zonoid data depth: Theory and computation. In OMPSTAT: Proceedings in Computational Statistics 12th Symposium held in Barcelona, Spain, 1996 235–240. Physica-Verlag, Heidelberg.Dyckerhoff, R., Mosler, K. and Koshevoy, G. (1996). Zonoid data depth: Theory and computation. In OMPSTAT: Proceedings in Computational Statistics 12th Symposium held in Barcelona, Spain, 1996 235–240. Physica-Verlag, Heidelberg.

8.

Dyckerhoff, R. and Mosler, K. (2011). Weighted-mean trimming of multivariate data. J. Multivariate Anal. 102 405–421.Dyckerhoff, R. and Mosler, K. (2011). Weighted-mean trimming of multivariate data. J. Multivariate Anal. 102 405–421.

9.

Efron, B. (1979). Bootstrap methods: Another look at the jackknife. Ann. Statist. 7 1–26.Efron, B. (1979). Bootstrap methods: Another look at the jackknife. Ann. Statist. 7 1–26.

10.

Ferguson, T. S. (1996). A Course in Large Sample Theory. Chapman & Hall, London.Ferguson, T. S. (1996). A Course in Large Sample Theory. Chapman & Hall, London.

11.

Julienne, H. and Houghton, C. (2013). A simple algorithm for averaging spike trains. J. Math. Neurosci. 3 Art. 3, 14.Julienne, H. and Houghton, C. (2013). A simple algorithm for averaging spike trains. J. Math. Neurosci. 3 Art. 3, 14.

12.

Karlin, S. (1966). A First Course in Stochastic Processes. Academic Press, New York.Karlin, S. (1966). A First Course in Stochastic Processes. Academic Press, New York.

13.

Kass, R. E., Ventura, V. and Brown, E. N. (2005). Statistical issues in the analysis of neuronal data. J. Neurophysiol. 94 8–25.Kass, R. E., Ventura, V. and Brown, E. N. (2005). Statistical issues in the analysis of neuronal data. J. Neurophysiol. 94 8–25.

14.

Lauritzen, S. L. (1996). Graphical Models. Oxford Statistical Science Series 17. The Clarendon Press, Oxford Univ. Press, New York.Lauritzen, S. L. (1996). Graphical Models. Oxford Statistical Science Series 17. The Clarendon Press, Oxford Univ. Press, New York.

15.

Lawhern, V., Nikonov, A. A., Wu, W. and Contrares, R. J. (2011). Spike rate and spike timing contributions to coding taste quality information in rat periphery. Frontiers in Integrative Neuroscience 5 1–14.Lawhern, V., Nikonov, A. A., Wu, W. and Contrares, R. J. (2011). Spike rate and spike timing contributions to coding taste quality information in rat periphery. Frontiers in Integrative Neuroscience 5 1–14.

16.

Liu, R. Y. (1990). On a notion of data depth based on random simplices. Ann. Statist. 18 405–414.Liu, R. Y. (1990). On a notion of data depth based on random simplices. Ann. Statist. 18 405–414.

17.

Liu, R. Y. and Singh, K. (1993). A quality index based on data depth and multivariate rank tests. J. Amer. Statist. Assoc. 88 252–260.Liu, R. Y. and Singh, K. (1993). A quality index based on data depth and multivariate rank tests. J. Amer. Statist. Assoc. 88 252–260.

18.

López-Pintado, S. and Romo, J. (2009). On the concept of depth for functional data. J. Amer. Statist. Assoc. 104 718–734.López-Pintado, S. and Romo, J. (2009). On the concept of depth for functional data. J. Amer. Statist. Assoc. 104 718–734.

19.

Mateu, J., Schoenberg, F. P., Diez, D. M., González, J. A. and Lu, W. (2015). On measures of dissimilarity between point patterns: Classification based on prototypes and multidimensional scaling. Biom. J. 57 340–358.Mateu, J., Schoenberg, F. P., Diez, D. M., González, J. A. and Lu, W. (2015). On measures of dissimilarity between point patterns: Classification based on prototypes and multidimensional scaling. Biom. J. 57 340–358.

20.

Moghadam, S. A. and Pazira, H. (2011). The relations among the order statistics of uniform distribution. Trends in Applied Science Research 6 719–723.Moghadam, S. A. and Pazira, H. (2011). The relations among the order statistics of uniform distribution. Trends in Applied Science Research 6 719–723.

21.

Mosler, K. and Polyakova, Y. (2012). General notions of depth for functional data. Available at arXiv:1208.1981.Mosler, K. and Polyakova, Y. (2012). General notions of depth for functional data. Available at arXiv:1208.1981.

22.

Robert, C. (1995). Simulation of truncated normal variables. Stat. Comput. 121–125.Robert, C. (1995). Simulation of truncated normal variables. Stat. Comput. 121–125.

23.

Ross, S. M. (1983). Stochastic Processes. Wiley, New York.Ross, S. M. (1983). Stochastic Processes. Wiley, New York.

24.

Tukey, J. W. (1975). Mathematics and the picturing of data. International Congress of Mathematicians 2 523–531.Tukey, J. W. (1975). Mathematics and the picturing of data. International Congress of Mathematicians 2 523–531.

25.

Victor, J. D. and Purpura, K. P. (1997). Metric-space analysis of spike trains: Theory, algorithms and application. Network 8 127–164.Victor, J. D. and Purpura, K. P. (1997). Metric-space analysis of spike trains: Theory, algorithms and application. Network 8 127–164.

26.

Wesolowski, S., Contreras, R. J. and Wu, W. (2015). A new framework for Euclidean summary statistics in the neural spike train space. Ann. Appl. Stat. 9 1278–1297.Wesolowski, S., Contreras, R. J. and Wu, W. (2015). A new framework for Euclidean summary statistics in the neural spike train space. Ann. Appl. Stat. 9 1278–1297.

27.

Wu, W. and Srivastava, A. (2011). An information-geometric framework for statistical inferences in the neural spike train space. J. Comput. Neurosci. 31 725–748.Wu, W. and Srivastava, A. (2011). An information-geometric framework for statistical inferences in the neural spike train space. J. Comput. Neurosci. 31 725–748.

28.

Wu, W. and Srivastava, A. (2013). Estimating summary statistics in the spike-train space. J. Comput. Neurosci. 34 391–410.Wu, W. and Srivastava, A. (2013). Estimating summary statistics in the spike-train space. J. Comput. Neurosci. 34 391–410.

29.

Zuo, Y. and Serfling, R. (2000). General notions of statistical depth function. Ann. Statist. 28 461–482.Zuo, Y. and Serfling, R. (2000). General notions of statistical depth function. Ann. Statist. 28 461–482.

Citation Download Citation

Shuyi Liu and Wei Wu "Generalized Mahalanobis depth in point process and its application in neural coding," The Annals of Applied Statistics 11(2), 992-1010, (June 2017). https://doi.org/10.1214/17-AOAS1030

Received: 1 December 2016; Published: June 2017

Access the abstract

JOURNAL ARTICLE
19 PAGES

DOWNLOAD PDF + SAVE TO MY LIBRARY