Dr Sachin Kumar

Dr Sachin Kumar
Dr Sachin Kumar
Dr Sachin Kumar

Research Fellow

About
Email Address
sachin.kumar@abdn.ac.uk
Office Address

The University of Aberdeen

Medical Statistics Team

Institute of Applied Health Sciences

Polwarth Building, Foresterhill

University of Aberdeen

Aberdeen

AB25 2ZD

School/Department
School of Medicine, Medical Sciences and Nutrition

Biography

Before joining the University of Aberdeen, I worked as a Research Officer with Indo-Dutch Cohort study at All India Institute of Medical Sciences, New Delhi, India. Broadly, my research, consultancy and teaching focus in the areas of applied statistics, predication modelling, linear and non-linear regression, survival theories, and cohort study involving high-dimensional datasets.

Qualifications

  • PhD Applied Statistics 
    2017 - Birla Institute of Technology and Science Pilani, India 
  • MSc Statistics 
    2004 - C.C.S. University Meerut, India 

External Memberships

Fellow of Royal Statistical Society

Research

Research Overview

I have specialised in advanced statistical techniques, like, sample survey and methodology, sample size calculation, data collection, survival theory, prediction modelling, testing of hypothesis, linear and non-linear regression, cohort study and structural equation modelling etc. I would like to supervise the students related to my specialised areas.

Research Areas

Applied Health Sciences

Research Specialisms

  • Applied Statistics
  • Medical Statistics
  • Human Demography

Our research specialisms are based on the Higher Education Classification of Subjects (HECoS) which is HESA open data, published under the Creative Commons Attribution 4.0 International licence.

Past Research

The main objective of my doctoral study was to formulate the various types of model to understand the migration, fertility and fecundity pattern of the region under study.

  • We have collected the primary data of 3200 households from the rural areas of district Meerut, Uttar Pradesh (India) by adopting a suitable sampling plan.
  • To understand the pattern of male migration, we tested the performance of two existing models and proposed two new models. After that, we compared all the models to find a suitable one for this region.
  • In India, almost every female has to migrate to the groom’s family; this is called marriage migration. It is very less studied kind of movement. We have tested one existing model on our data and proposed two new models to understand the marriage distance pattern in India. We applied gamma regression to understand the determinants of marriage distance, so far which was not considered in India.
  • One more model was developed to explain the behaviour pattern of male migrants, and the factors which induce them to migrate. Using this model, we tried to identify the covariates which directly or indirectly push the young men to migrate. In this work, we compared the performance of several additive and multiplicative models.
  • We have developed a new model to compare the fecundability of migrant and non-migrant couples to observe the fertility pattern in both kinds of couples.
  • A new model to describe the pattern of male age at marriage was formulated and then the factors responsible for the event was studied with the help of the Cox proportional hazard model. EM algorithm was used to estimate the parameters of the model.
  • The first birth interval of two Indian states Kerala and Rajasthan was studied and then a comparison was made. Cox hazard model, life table and Kaplan-Meier survival curve was employed for the purpose. For this study, data was taken from NFHS-3.
  • A study of socio-economic determinants of age at first birth in India was done. The data for this work also was used from NFHS-3

These are some of the highlights of my doctoral work.

Collaborations

I have research collaborations in All India Institute of Medical Sciences, New Delhi, Banaras Hindu University, Varanasi, Central University of Hyderabad, and LNMIIT Jaipur India.

Funding and Grants

Nil

Teaching

Courses