+91-79-6632 4803




Apratim Guha

Production and Quantitative Methods

Educational Qualifications

Doctorate: Ph.D. in Statistics from the University of California, Berkeley: July 2005.

Dissertation title: Analysis of dependence structures of hybrid stochastic processes using mutual information.

Advisor: Prof. David Brillinger
Master of Arts: M.A. in Statistics from the University Of California, Berkeley: May 2002.
Master of Statistics: M.Stat. from the Indian Statistical Institute, Calcutta: May 2000. (First Division with Distinction).
Bachelor of Statistics: B.Stat. (Hons.) from the Indian Statistical Institute, Calcutta: May 1998. (First Division with Distinction). 

Academic Affiliation

I am an associate professor in the Production and Quantitative Methods area. I am also a member of the Centre for Management of Health Services.

I primarily teach topics related to Statistics, Mathematics and Operation Research. My primary research area is time series analysis, modelling and forecasting. I am also interested in categorical data analysis, modeling of discrete valued stochastic processes, medical statistics and, in general, applications of statistics.

I joined IIMA in 2012. Before coming here, I have worked at the School of Mathematics, University of Birmingham, UK as a lecturer (2008-2012), and, before that, at the Department of Statistics and Applied Probability, National University of Singapore as an assistant professor (2005-2008). 

I obtained my PhD from the Department of Statistics, University of California, Berkeley in 2005. My PhD supervisor was Prof. David Brillinger, and here is my PhD geneology.

Please note: I do not need any research interns for my research. I apologise to the interested students for the same. I would not be able to reply to internship requests individually.

Past Affiliations

Lecturer, School of Mathematics, University of Birmingham, UK (2008-2012)

Assistant Professor, Department of Statistics and Applied Probability, National University of Singapore (2005-2008)


Presently Teaching:

PGP 1: 

QM1A: Compulsory course on Probability Theory. Co-taught earlier with Karthik Sriram. To be co-taught this year with Gautam Dutta.

PGP 2: 

Forecasting Techniques for Practitioners: Elective course on forecasting techniques. The course covers basic theory of time series forecasting. Students also learn to use various R packages and get a hands on experience of making forecasts with real life data sets. Co-taught with Tathagata Bandyopadhyay.


Statistics: Compulsory course on statistical techniques for first year FPM students at IIM Ahmedabad. Co-taught with Karthik Sriram.

Time Series Analysis: This course introduces the theory and methods of time series analysis for research in economics and finance. The course starts with basic linear time series models and then moves on to studying linear combinations of unit root processes, i.e. Cointegrated Systems (VECMs), and models with conditional heteroskedasticity (GARCH). The course is rounded up with a discussion of State Space representations of time series models and Bayesian methods. Although the main focus of the course is on theory, data analysis using R is explored. Co-taught with Vineet Virmani. 

Applied Statistical Inference: This course explores the concepts of statistical inference with applications in management research in mind. Theory is supplemented with data analysis using R. Co-taught with Vineet Virmani.

Advanced Topics in Quantitative Methods: This course provides a hands-on training on advanced methods of empirical research like mediated-moderation, moderated-mediation, multi-level modelling and longitudinal data analysis. The course is based on a combination of theoretical and practice-oriented sessions that provides working knowledge of statistical software like R and SPSS. Co-taught with Vishal Gupta.

Past Teaching at IIMA:

PGP1: PSII (Statistical Inference), PSIII (Regression), DMII (Decision Analysis Under Uncertainty), QMII (Decision Analysis).

PGP2: Econometrics (jointly with Viswanath Pingali.)

PGPX: Making Decisions (Decision making using linear programming and decision trees), Analysis of Data (Probability and statistics)

Teaching at other IIMs:

 IIM Nagpur: Basic Statistics Course for PGP1.

@IIM Shillong: Course on Graph Theory for FPM. Co-taught with Diptesh Ghosh.

Areas of Research

Statistics and applications: time series, categorical data analysis, applications in medical science and computer science.

Google Scholar Citations

Published Papers:

1. Assessing the Dependence Structure of the Components of Hybrid Processes Using Mutual Information. Sankhya Series B, pg. 256-292, Vol. 77(2), 2015.

2. Time Series Characterization of Gaming Workload for Runtime Power Management. (With B. Dietrich, D. Goswami, S. Chakraborty and M. Gries.) IEEE Transactions on Computers, pg. 260-273, Vol. 64(1), 2015.

3. A mutual information-based k-sample test for discrete distributions. (With R. Drake.) Journal of Applied Statistics, pg. 2011-2027, Vol. 41(9), 2014

4. Auto-association measures for stationary time series of categorical data. (With A. Biswas, and M. C. Pardo) TEST, pg. 487-514, Vol. 23(3), 2014.

5. Meta-analysis of test accuracy studies with multiple and missing thresholds: a multivariate-normal model. (With R. D. Riley, Y. Takwoingi, T. Trikalinos, A. Biswas, J. Ensor, R. K. Morris and J. J. Deeks.) Journal of Biometrics & Biostatistics 5:196. doi:10.4172/2155-6180.1000196.

6. Modelling and coherent forecasting of zero inflated count time series. (With R. Maiti, A. Biswas and S. H. Ong.) Statistical Modelling: An International Journal, pg. 375-398, Vol. 14(5), 2014.

7. A Two Sample Test based on Mutual Information. (With T. Chothia). Calcutta Statistical Association Bulletin, pg. 39-54, Vol. 66 (261-262), 2014.

8. Some Analyses of the Interaction among Local Field Potentials and Neuronal Discharges in a Mouse using Mutual Information. Journal of the Indian Society of Agricultural Statistics. Vol. 68(2), Pg. 117-129. 2014.

9. A statistical test for information leaks using continuous mutual information. (With T. Chothia) Computer Security Foundations Symposium (CSF), Pg. 177-190, IEEE 24th. 2011.

10. Time series analysis of hybrid neurophysiological data and application of mutual information. (With A. Biswas.) Journal of Computational Neuroscience, Pg. 35-47, Vol. 29, 2010.

11. Statistical measurement of information leakage. (With K. Chatzikokolakis and T. Chothia.) Tools and Algorithms for the Construction and Analysis of Systems, Lecture Notes in Computer Science, 6015. Springer. Pg. 390-404. 2010.

12. Time series analysis of categorical data using auto-mutual information. (With A. Biswas.) Journal of Statistical Planning and Inference. Volume 139 Pg. 3076-3087. 2009.

13. Time series of categorical data using auto-mutual information with application of fitting an AR(2) model. (With A. Biswas.) Advances in Multivariate Statistical Methods, Statistical Science and Interdisciplinary Research, Vol. 4, pg. 421-435, 2009.

14. An overview of modeling techniques for hybrid brain data. (With A. Biswas.) Statistica Sinica, pg. 1311-1340, Vol. 137, 2008.

15. Deterministic neural dynamics transmitted through neural networks (With Dr. Yoshiyuki Asai and Prof. Alessandro E.P. Villa.) Neural Networks, pg. 799–809. Vol 21, 2008.

16. Mutual information in the frequency domain (With Prof. David Brillinger). Journal of Statistical Planning and Inference, pg. 1076-1984, Vol. 137(1), 2007.

17. Analysis of scoring rate in a limited over cricket match. Calcutta Statistical Association Bulletin, pg. 249-259, Vol. 5, 2003.


Technical Reports/Working Papers (unpublished):

1. Calculation of Probabilistic Anonymity from Sampled Data. (With K. Chatzikokolakis and T. Chothia.) University of Birmingham Technical Report, 2009, CSR-09-10.

2. On Estimation of Number of Species and Biodiversity. (With A. Biswas.) IIMA Working paper 2013, WP2013-05-03.

3. Modelling and Analysis of Multivariate Ordinal Categorical Data in Longitudinal Set up. (With A. Biswas.) IIMA Working paper, 2013, WP2013-05-04.

4. ROC Curve Analysis for Randomly Selected Patients. (With T. Bandyopadhyay and S. Adhya.) IIMA Working paper, 2015, WP2015-07-02.


1. Titled ‘Employing Mutual Information in Multivariate Time Series Analysis and Model Fitting', sponsored by National University of Singapore Academic Research Fund (2005).

2. Titled ‘Analysis of Categorical and Clustered Time Series Data' sponsored by Ministry of Education (Singapore) Academic Research Fund (2007).

3. Two grants to host visitors at the University of Birmingham, sponsored by the London Mathematical Society (2009, 2011).

4. Grant to host a visitor at the University of Birmingham, sponsored by the India Travel Fund of the University of Birmingham (2011).


Staging Enabled