Re:Time Series Prediction Using LSTM Deep Neural Networks
by RA_Fisher on Sunday September 02, 2018 @11:03AM
(#17897219)
I highly recommend this econometrics text for getting started with statistics: https://www.amazon.com/Principles-Econometrics-5th-Carter-Hi...
For modeling I found Wooldridge's panel and cross-section data book very useful: https://www.amazon.com/Econometric-Analysis-Cross-Section-Pa...
Greene is a really useful reference text: https://www.amazon.com/Econometric-Analysis-8th-William-Gree...
For advanced stats theory, I recommend Casella and Berger https://www.amazon.com/Statistical-Inference-George-Casella/...
Hope that helps!
The more specific a model can be made to the problem at hand, the better it'll perform. Supervised ML models are great starting / baseline models.
Re:Time Series Prediction Using LSTM Deep Neural Networks
by tomrod on Sunday September 02, 2018 @02:11PM
(#17897928)
I second Wooldridge. Greene I found to be much denser without providing much additional insight. It is a popular MS/PhD entry text though.
I add any of Ken Train's work to this mix, especially on estimating discrete choice theory.
On one hand, it's almost a tautoloy that specific models should be better than general models, but I worked on some 2d time series classification with a statistician and afterwards, for kicks, I replaced the entire thing with a CNN+LSTM and it worked just as well as the whole complicated model he had come up with.