Applied Statistical Modelling

Project Title: Applied Statistical Modelling
Funding Agency: IOE FRP, Delhi University, Delhi
Amount: ₹1.75
L                                                                                             Year: 2021-22
Sanction Letter No and Date: IoE/2021/12/FRP dated 29.10.2021

Objectives of the Proposal:

I. Scientific classification and clustering of selected human emotions to guide neurologists and psychologists in identifying significant factors:
a) that aid in coping with stress and adversities,
b) that influence stress levels in high-risk individuals.

II. Development of a model for:
a) identification of spatial dependence among independent groups,
b) risk assessment in parameter estimation.

III. Statistical analysis of COVID-19 incidence data globally and specifically for India.

Innovations / Outcomes:

Markov Chain Monte Carlo (MCMC) estimates obtained under the SELF loss function were found to be the most efficient for parameter estimation compared to all other methods. For estimating the unknown parameter ‘b’, MCMC estimates obtained under the LINEX loss function provided the highest precision. Numerical comparisons based on Mean Squared Error (MSE) values were made using simulated datasets, and findings were validated with real data.

The study analyzed the psychological impact of the COVID-19 crisis on global populations and their coping mechanisms. Results confirmed that individuals perceived the crisis as a significant stressor, with stress levels higher than those in non-emergency situations. Approximately 87.43% of the surveyed population exhibited high stress levels, while 88.13% demonstrated strong coping mechanisms. These findings align with current research on the psychological effects of COVID-19.

Publications:

  1. Pandey R., Srivastava P., Ali D. (2022). Bayesian Risk Analysis for Length Biased Log Logistic Distribution Under Different Loss Functions. Journal of Scientific Research, 66(3).
  2. Pandey R., Srivastava P. (2022). Bayesian Estimation for the Two Log-Logistic Models Under Joint Type II Censoring Schemes. Journal of Reliability and Statistical Studies, April 16, pp. 229-260.
  3. Tigga N.P., Garg S. (2022). Prediction of global psychological stress and coping induced by the COVID-19 outbreak: a machine learning study. Alpha Psychiatry, 23(4), 193.

Conference Paper:

  1. Garg S., Pandey R., Gara A. (2022). Assessment of the Impact of Personality Characteristics on Emotion Resilience. 8th International Conference on Advanced Computing and Communication Systems (ICACCS), IEEE, Vol. 1, pp. 440-444.