Time series models. Time series models help us deal with data that is related to time and is collected in chronological order. Some examples include moving averages, autoregressive models, and exponential smoothing. These statistical models are all built to help predict trends based on time-based data.
Risk models. Risk models look at portfolio risk and possible outcomes, good and bad. Common risk models you might see include value at risk (VAR) and Monte Carlo simulations, which are used to predict the likelihood of outcomes, based on thousands of iterations of the same data in random scenarios.
Limits of statistical models
A statistical model can give you incredible insight into your potential investment, but only if it's applied appropriately, uses the correct datasets, and the real world doesn't deviate too far from your modeling assumptions.
For example, all statistical models are based on past data, which means that you can't really predict things that might be unexpected (known as a black swan event). These might be things you could have seen coming if the data had been combined in the right order, but are only visible in hindsight. Statistical models are really just one tool in your arsenal that you should use to make important financial and investing decisions.