Tabitha Garwe, PhD

Full Professor of Epidemiology & Surgery | Statistical Editor| Scratch Golfer Has Been - running it back|US Equities Predictive AI - DBN/BRNN

[Tabitha Garwe, PhD @therealtabgee]

@0x45__ To be clear, price movement is cyclical (mean reversion), within DAGs this can be broken up by using different timeframes

[Tabitha Garwe, PhD @therealtabgee]

Weekend projects…

[Tabitha Garwe, PhD @therealtabgee]

@0x45__ I exhausted traditional statistical approaches with really nothing to show for it LOL; statistical parent-child relationships are real in the stock market - pay attention to 4-factor relationships in particular

[Tabitha Garwe, PhD @therealtabgee]

@Shinobbs Shhh

[Tabitha Garwe, PhD @therealtabgee]

@ludvigfix @RohOnChain You can then fit a discrete Bayesian Network which you completely explain and tweak if needed

[Tabitha Garwe, PhD @therealtabgee]

Unfortunately I can’t point you to specific resources as I used primarily my training/skills as an epidemiologist starting with a first principles approach to solving a problem. I have not read not even one book on quantitative trading- I used probability theory and after deeply studying price cycle, it was clear to me why linear models work sometimes but eventually fail; Enter network analysis, derived from my experience teaching directed acyclic graphs for causal research-this was the real breakthrough. The market is organized as network linking different timeframes through volatility expansion and contraction; e.g. a failed day chart breakout is simply a blocked path by the parent (the week). Except for highest TF , every timeframe can be a parent or a child depending on the model. For general reading I would familiarize myself with DAGs and then analyze the market with this framework
Day as a parent - look at all “day children” 15min , 30min, 1hr,2hr, 4hr and see how they behave when the price moves or when it reverses. I promise you the answers are there and they are statistical

[Prof. Feynman @ProfFeynman]

Being wrong is fine; being comfortably wrong is where trouble begins.

[Journal of Trauma and Acute Care Surgery @JTraumAcuteSurg]

This is a large, single-center, cohort study demonstrating improved shock index after administration of blood prior to emergency department arrival. Further study will be helpful in determining which patients stand to benefit the most from transfusion in transit. #pediatrictrauma @NatalieADrucker @ksutyak @UTH_Pedisurg

https://t.co/wvc6iMOvOG

[Tabitha Garwe, PhD @therealtabgee]

https://t.co/SIteH7vBGD

[Journal of Trauma and Acute Care Surgery @JTraumAcuteSurg]

An introduction to clinical prediction models using logistic regression in acute care surgery research: Methodologic considerations and common pitfalls https://t.co/Ad7BLK0iEJ

[Tabitha Garwe, PhD @therealtabgee]

@ryanmouquegolf Thanks Ryan, this is super useful. I feel like I should pay you:)

[Tabitha Garwe, PhD @therealtabgee]

@AnthonyCrudele 💯

[Tabitha Garwe, PhD @therealtabgee]

Spring thoughts…running it back to scratch

[Tabitha Garwe, PhD @therealtabgee]

@LacksonMudenda Congrats!

[Tabitha Garwe, PhD @therealtabgee]

Bacon mode re-activated…

[Tabitha Garwe, PhD @therealtabgee]

@FelipeGuirao 💯 And we are not even talking advanced statistics

[Tabitha Garwe, PhD @therealtabgee]

@TheVixhal All of it is overrated anyway, been there done that

[Tabitha Garwe, PhD @therealtabgee]

"Empty your mind. Be formless, shapeless like water. You put water into a cup, it becomes the cup. You put water into a bottle, it becomes the bottle. You put it in a teapot, it becomes the teapot. Water can flow, or it can crash. Be water, my friend."

[Tabitha Garwe, PhD @therealtabgee]

@RealSimpleAriel @markminervini But I simply learned from observing the market and coding the observations over time into a statistical model 🤷🏽‍♀️

[Tabitha Garwe, PhD @therealtabgee]

@hjluks Super useful, thanks