An exploratory data visualization (EDV) of childhood stunting and mortality in developing countries based on the Demographic and Health Survey (DHS) program's tabulated indicators.

In this lab session, students were introduced to the fundamentals of R and RStudio.

Preparation of xcess deaths file for the State of Texas using CDC data.

The lab introduces students to fundamentals of R and RStudio as complementary analytical tools with relevance to the Fall 2020 class on "the Demography of COVID-19".

The objective of this exercise is to fit a Discrete-Time Hazards (DTH) model for under-five mortality in Nigeria. The analysis was based on the pooled Nigeria Demographic and Health Surveys data of 2003-2018.

The objective of this exercise is to execute the procedures for estimating **time-to-event functions** in event history analysis with a focus on infant mortality experience.

This exercise highlights the procedure for fitting a semi-parametric proportional hazards (PH) model for under-five mortality. The Cox PH model and kids-recode data sets of 2003, 2008, 2013, and 2018 Nigeria Demographic and Health Surveys (NDHS) were employed to conduct the analysis.

This exercise attempts to fit the most appropriate parametric hazard model for under-five mortality in Nigeria based on pooled kids-recode data sets of 2003, 2008, 2013, and 2018 Nigeria Demographic and Health Surveys (NDHS). The distributions of under-five mortality risk from various theoretical parametric models were compared with the distributions from empirical non-parametric models using model diagnostic approaches. The best-fit parametric model was objectively determined and applied to the pooled data sets to offer some explanations for the dynamics of under-five deaths in Nigeria.

Illustration of mortality risks differential using estimates of basic functions of survival time- the survival, hazard, cumulative hazards functions- and Kaplan-Meier survival analysis.

This exercise illustrates modal and multiple imputation approaches to addressing missing data issues in binary logistic regression analysis. Model estimates from model fit on the imputed data and conventional filtered data with no missing data are compared to assess the potential impact of data missingness on model fit.

Poisson Regression; Quasi-Poisson Regression; Negative Binomial Regression; Offset Term

Ordinal Logit, Proportional Odds, Nonproportional Odds, and Multinomial Logit Models

Exercise on Basic Representation of Spatial Data

Exercise on analysis of Simple and Complex Survey Data Analysis