Prediction and Modelling

Prediction and Modelling

Statistical models underpin one of our main and best service offers at ROI. Whatever you may be interested in and whatever data you have, we can construct a model that will help you understand precisely what’s going on and why. Among some of the questions, our clients usually approach us with and can be answered through statistical modelling include

  • What effect will increase prices have on-demand?
  • What key factors drive people to behave the way they,
  • What factors influence voting behaviour?

Statistical models enable the understanding of the relationship between the different types of variables within the collected data. Also, statistical models explain the process of the process that generates the collected data, showing how several variables relate to each other and the outcome. While we strive to simplify and explain to our clients from a diverse background (including non-statistical), statistical models can be complex and thus turn to demand a high degree of expertise to produce accurate results. Our team of statisticians at ROI is also capacitated to perform prediction modelling analysis of any kind, from

  • simple linear relationships to complex multidimensional systems.
  • Understanding of complex relationships
  • Identify driver or variable that influence results while ruling others out
  • Quantify the nature and size of the effect that different factors have on behaviour
  • Forecast future behaviour and explore the “what if” scenarios
  • Extrapolate data into “yet to be an observed situation”
  • Quantify risk and uncertainty about different potential outcomes

Whether a client is interested in human behaviour or a physical processes, with the right selection of model we are can formulate a structure on their data so they are better able to understand, explain how systems behave. Among the models we perform for our clients includes;

  • Regression models (including linear, generalised linear and logistic models)
  • Non-parametric models
  • Semi-parametric models
  • Fixed, random and mixed-effects models
  • Bayesian and graphical models
  • Time Series models
  • Survival models
  • Classification and regression trees