# Explaining generalized method of moments to a non-statistician

How do I explain Generalized Methods of moments and how it is used to a non statistician?

So far I am going with: it is something we use to estimate conditions such as averages and variation based on samples we have collected.

How do I explain the part where you estimate the parameter vector by minimizing variance?

• Why does a non statistician need to know about minimizing variance? Does this person understand normal method of moments estimation? What will they need to do with the knowledge you're trying to impart? Jan 7, 2016 at 2:06

In the classical method of moments you specify a moment condition for each parameter you need to estimate. The resulting set of equations are then "just-identified". GMM aims to find a solution even if the system is not just-identified. The idea is to find a minimum distance solution by finding parameter estimates that bring the moment conditions as close to zero as possible.

• A non-statistical audience is going to freak out if you use technical verbiage like this -- "moment conditions," "just-identified," etc. The simpler you make the explanation the easier it will be for them to digest it. I would begin by explaining the meaning of the slope parameter in a one variable regression as a rate of change and then suggesting that the audience generalize that to a multivariate model. This leaves everything to their imagination without your getting mired in the kind of details that can completely derail what you're trying to communicate. Oct 16, 2015 at 12:47

There are several methods to estimate the parameters of a model. This is a core part of statistics/econometrics. GMM (Generalized Method of Moments) is one such method and it is more robust (statistically and literally[for non-statistics audience]) than several others.

It should be intuitive that the process of estimation involves how good your model fits the data. The GMM uses more conditions than the ordinary models while doing this.

(You have mentioned average and variance. I am assuming that is a familiar idea). Average and Variance are some basic metrics of the data. A person models the data to understand it's nature. A perfect(hypothetical model) would explain the data through and through.

Let us take an example of modeling heights of all the people in a building. There are two metrics average and variance. Average is the first level metric, variance is the second level metric. An average is adding all the heights and dividing it by the number of people. It tells you something like 11 feet is ridiculous. 5 feet is sensible.

Now consider the variance, it will tell an additional layer of information: 6 feet is not ridiculous(based on average) but how likely is it for the height of the person to be 6 feet. If the building is a middle school building, it is less likely right ? If it is office building more likely.

These are examples of something technically called moments of the data(after explaining average and variance, should be comfortable ?). One's model should do well if it caters to these conditions of average and variance observed. Beyond average and variance, there are several other metrics.

The GMM fits the model for these higher metrics(moments). Simpler methods cater to smaller metrics. The name as it suggests is generalized method - it tries to be as general as possible.