Time-Series, Longitudinal & Mixed-Effects Modeling — Hands-on

Learn how to correctly model repeated and time ordered biomedical data. This module covers core time series tools (autocorrelation, ARIMA style models) and longitudinal mixed effects modeling for repeated measures, with hands on practice in R and Python for omics, clinical and sensor datasets.

Time-Series, Longitudinal & Mixed-Effects Modeling

Help Desk · WhatsApp

Session Index

Session 1 — Time-Series Foundations & Autocorrelation Session 2 — ARIMA Style Models & Forecast Diagnostics Session 3 — Longitudinal & Mixed-Effects Models Session 4 — Case Studies: Clinical & Omics Time-Course

Session 1

Fee: Rs 8800

Time-Series Foundations & Autocorrelation

What makes time ordered data special

cross sectional vs time series vs longitudinal equally vs unequally spaced observations trend, seasonality and noise

Autocorrelation and dependence structure

ACF and PACF plots lagged features serial correlation impact on inference

Stationarity concepts and transforms

weak stationarity intuition differencing and detrending variance stabilizing transforms

Session 2

Fee: Rs 11800

ARIMA Style Models & Forecast Diagnostics

AR, MA and ARIMA building blocks

autoregressive vs moving average ARIMA (p,d,q) notation seasonal components (SARIMA)

Model identification and selection

reading ACF and PACF AIC, BIC and parsimony auto ARIMA style helpers

Forecasts and residual diagnostics

one step ahead predictions prediction intervals checking residual autocorrelation

Session 3

Fee: Rs 14800

Longitudinal & Mixed-Effects Models

Repeated measures and correlation structures

within subject correlation marginal vs subject specific views balanced vs unbalanced follow up

Linear mixed effects models (LMM)

random intercept and random slope covariance structures (AR1, compound symmetry) likelihood vs REML estimation

Generalized mixed models (GLMM) overview

binary and count outcomes link functions and interpretation convergence and complexity

Session 4

Fee: Rs 18800

Case Studies: Clinical & Omics Time-Course

Clinical longitudinal example

patient level biomarkers over visits

Omics time course example

expression or metabolite trajectories group by time interactions visualization of fitted curves

Deliverables: analysis scripts and report

R (forecast / fable / lme4 / nlme style) Python (pandas, statsmodels, linearmodels) PDF or HTML summary with diagnostics

PDF

Time-Series, Longitudinal & Mixed-Effects Modeling Training | Biostatistics & ML for Omics

Time-Series, Longitudinal & Mixed-Effects Modeling — Hands-on