Significance and Usage of Time Series
Time series analysis aims to understand patterns evolving over time and use these patterns to predict future behavior. Time series models are the simplest longitudinal models, and longitudinal modeling is important in many fields, from modeling business process to understanding the evolution of diseases.
Main Challenges in Time Series Analysis
- Decomposition of the time series into trend, seasonal and random components
- Most time series are not stationary and usually have a seasonal component. We have to transform these series into stationary non–seasonal before we can model them.
These demand subject matter expertise in Healthcare and associated ecosystems.
Services we provide
- Healthcare Domain Consulting: Domain variables which can have an impact on the time series observations/trends
- Disaggregating an observation on the time series to its possible constituents
- Model building
- To either understand what is going on in the data and/or produce a forecast
- Prepare a time series matrix and run regression (statistical analysis and forecasting exercise) on it
- Policy scenario analysis using Interrupted time series
Time Series use cases in Healthcare
- Interrupted time series design (Segmented Regression) is the strongest approach for evaluating longitudinal effects of health interventions
- Use of Interrupted Time Series Analysis in Evaluating Health Care Quality Improvements
- Time series forecasting for Hospital Management activities
- Supply Chain forecasting
- Weather forecasting
- For emergency preparedness, room occupancy prediction, staff allocation in hospitals
- Public Health
- Modeling the dynamic behavior of Public Health variables and their response to Public Health interventions