> For the complete documentation index, see [llms.txt](https://zavalab.gitbook.io/statschemebook/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://zavalab.gitbook.io/statschemebook/chapter-5-estimation-for-structural-models/01-estimation-techniques-for-structural-models.md).

# Estimation Techniques for Structural Models

{% hint style="success" %}
**Slides:** [stats\_ch5\_estimationstruct.pdf](https://github.com/vzavala/StatsBook/blob/master/Slides/stats_ch5_estimationstruct.pdf) · [4-up handout](https://github.com/vzavala/StatsBook/blob/master/Slides/handouts/stats_ch5_estimationstruct_4up.pdf) · **Code:** [Python notebooks](https://github.com/vzavala/StatsBook/tree/master/Python) · [MATLAB scripts](https://github.com/vzavala/StatsBook/tree/master/Matlab) · [MATLAB live scripts](https://github.com/vzavala/StatsBook/tree/master/Matlab-Live)
{% endhint %}

* Our discussion so far has centered on using data to characterize random phenomena.
* Our approach has been to determine an RV model that best explains the data and we have used estimation techniques to determine the parameters for such models.
* From discussion on multivariate RVs we observed that correlations between RVs uncover connections between variables (e.g., pressure and conversion).
* We now turn our attention to developing techniques that use data to develop models that capture *structural* relationships between variables.
* Structural models embed *knowledge* that allows us to make predictions for a set of variables from another set of variables.
* Structural models might originate from fundamental laws (mechanistic models), from empirical observations (empirical models), or from combinations.
* As with RV models, we will postulate a structural model (with parameters) and we will use estimation techniques to determine parameters that best fit the data.