Timeline for Principle of Analogy and Method of Moments
Current License: CC BY-SA 3.0
12 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 13, 2017 at 12:44 | history | edited | CommunityBot |
replaced http://stats.stackexchange.com/ with https://stats.stackexchange.com/
|
|
| Apr 11, 2017 at 20:10 | comment | added | Alecos Papadopoulos | Lutkepohl's "Introduction to Multiple Time Series Analysis" tricks you into believing at first that it is not too heavy in matrix algebra...until it is too late. | |
| Apr 10, 2017 at 22:36 | history | edited | Alecos Papadopoulos | CC BY-SA 3.0 |
deleted 9 characters in body
|
| Apr 10, 2017 at 15:00 | comment | added | Frank Swanton | @AlecosPapadopoulos Alecos, thanks a lot! By the way, do you have any good reference reading for VAR (Vector Autoregressions) that are sort of introductory brushing through without too much matrix algebra? Just asking! | |
| Apr 10, 2017 at 14:59 | vote | accept | Frank Swanton | ||
| Apr 9, 2017 at 20:11 | comment | added | Matthew Gunn | Something worth noting is that you can apply the theory of GMM to many different moment conditions. GMM is not limited to the orthogonality condition $\operatorname{E}[\mathbf{x}u]= \mathbf{0}$ that gives you OLS. Eg. maximum likelihood can be interpreted as GMM on the score. | |
| Apr 9, 2017 at 19:56 | history | edited | Alecos Papadopoulos | CC BY-SA 3.0 |
added 7 characters in body
|
| Apr 9, 2017 at 19:54 | comment | added | gammer | @MichaelChernick, incorrect. It's a method of moments estimator with moment condition $E( X' (Y - X' \beta) ) = 0$. Did you read the answer? | |
| Apr 9, 2017 at 19:49 | history | edited | Alecos Papadopoulos | CC BY-SA 3.0 |
deleted 1 character in body
|
| Apr 9, 2017 at 19:48 | comment | added | Alecos Papadopoulos | @MichaelChernick The point I am making is that we can obtain OLS starting from an orthogonality condition. So they may be historically distinct, but mathematically equivalent, in the context of this model. | |
| Apr 9, 2017 at 19:43 | comment | added | Michael R. Chernick | Method of moments is an estimation technique that goes back to Karl Pearson in the early 1900s. I don't think it has anything to do with the least squares estimate of regression parameters. | |
| Apr 9, 2017 at 19:39 | history | answered | Alecos Papadopoulos | CC BY-SA 3.0 |