Sounds like the Tao of trading.. let things take the course and don't force things
In reality, situation could NEVER be worse
- Thread starter orbit23
- Start date
If it starts it'll be over so fast the markets won't even have time to react we'll just be heaps of Ash pretty much
Markets will crash so that it never comes to this point.
I think that nothing significant has to happen, even the fear and uncertainty of something dangerous happening is enough.
Remember how people were fighting over toilet paper during covid panic?
Infinite variance processes, also known as heavy-tailed processes, have different characteristics compared to Gaussian processes with finite variances. These processes are often encountered in fields such as finance, telecommunications, and physics. Here’s a summary of how they differ and how they can be understood:
Mandelbrot was all about long-range dependency in stable distributions
### Characteristics of Infinite Variance Processes
1. **Heavy-Tailed Distributions**:
- Infinite variance processes often arise from heavy-tailed distributions, such as the Cauchy distribution or certain stable distributions.
- These distributions have tails that decay more slowly than exponential tails, leading to infinite second moments (variances).
2. **Stable Distributions**:
- One important class of distributions that can model infinite variance processes is the stable distributions.
- Stable distributions are characterized by a stability parameter \( \alpha \) (0 < \( \alpha \) ≤ 2). When \( \alpha < 2 \), the distribution has infinite variance.
3. **Self-Similarity and Long-Range Dependence**:
- Infinite variance processes often exhibit self-similarity and long-range dependence, meaning that their statistical properties are consistent across different time scales and they exhibit significant correlations over long periods.
### Covariance and Structure
1. **Covariance**:
- For infinite variance processes, traditional covariance is not well-defined due to the infinite second moments.
- Instead, other measures like the covariation or the use of fractional moments might be employed.
2. **Spectral Representation**:
- Infinite variance processes can sometimes be analyzed using their spectral representation, which provides insight into the frequency components of the process.
### Examples of Infinite Variance Processes
1. **Cauchy Process**:
- A process where the increments follow a Cauchy distribution, which is a stable distribution with \( \alpha = 1 \).
- The Cauchy process is used in various fields to model phenomena with large, unpredictable jumps.
2. **α-Stable Processes**:
- More generally, α-stable processes with \( \alpha < 2 \) are used to model heavy-tailed behavior. These processes include the Lévy process, which generalizes the Poisson process to allow for infinite variance.
### Handling Infinite Variance
1. **Tail Index and Scaling**:
- The tail index \( \alpha \) of a stable distribution gives insight into the heaviness of the tails and can be used to understand the process's scaling properties.
2. **Generalized Method of Moments**:
- Instead of relying on the second moment (variance), generalized method of moments can be used, focusing on fractional moments or other properties that are well-defined.
3. **Regular Variation**:
- Techniques from regular variation theory help in modeling and analyzing the heavy tails of the distributions.
4. **Simulation and Estimation**:
- Special methods are used to simulate and estimate parameters of infinite variance processes, given that traditional methods may not apply.
### Practical Considerations
1. **Modeling Financial Returns**:
- Infinite variance models are often used to capture the behavior of financial returns, where extreme events (large losses or gains) are more common than predicted by Gaussian models.
2. **Network Traffic**:
- In telecommunications, heavy-tailed models help in understanding network traffic patterns that exhibit bursts of high activity.
3. **Environmental and Physical Phenomena**:
- Processes such as earthquake magnitudes and other natural phenomena often follow heavy-tailed distributions, making infinite variance models appropriate.
In conclusion, infinite variance processes represent a different category of stochastic processes characterized by heavy-tailed distributions and infinite second moments. Analyzing these processes requires alternative statistical methods and tools that account for their unique properties.
Well you got the market of fear and uncertainty cornered for sure lol.
Iz zat u n dare?
Got another cookie?
Last edited:
Lmao if you find yourself in the company of Trump you might be suffering from the Dunning-Kruger effect or whatever it is where people that don't know s*** think they do
Wow!!!!!!!!!!
Does he know even his POS stock went up today? Although it first made another lower swing low.