Perhaps without calling it by name, we’ve already seen the role of the stochastic model in earlier topics. For example, it showed up in the form of a variance-covariance matrix as the weighting parameter in the constraint we applied to help us solve our linearized functional model equations:

    \begin{equation*} \mathbf{e}^T\mathbf{C}_\mathbf{l}^{-1}\mathbf{e} = minimum \end{equation*}

When looking at the parametric least squares estimation equations we also saw how important the stochastic model was for specifying \mathbf{C}_\mathbf{l} and for propagating that variance-covariance matrix to get \mathbf{C}_{\hat{\mathbf{x}}} and \mathbf{C}_{\hat{\mathbf{l}}}.

And the following part of our “big picture view” shows the important role that stochastic modeling plays in designing and analyzing geomatics networks. It’s fundamental to preanalysis and the design of an optimal network, and, as discussed above, it’s key to the estimation and adjustment process.


(See the rest of the “big picture view” here » and again in the first lesson below.)

This mini course

In this mini course we’re going to take things a step further than the application of variance-covariance models, by taking a more careful look at what is a stochastic model. I want two things from this:

  1. That you understand all the related fundamentals, which I have pulled and summarized from various course so we can keep things succinct
  2. That you can apply them throughout the rest of the course


Just work your way through the lessons (under “Resource content”) below.