Add MAMean (MA(q)) model with volatility & forecasting support

[premdev1234]

This PR introduces an implementation of the Moving Average (MA) mean model—MAMean—as a new subclass of ARCHModel.
It fills a longstanding gap in ARCH’s mean model suite, enabling direct modeling of MA(q) dynamics in return series.

---

Key Features

• New Model: MAMean, supporting flexible lag order q, with optional constant term.
  -API: .fit(), .simulate(), .forecast(), .resids
  -Volatility support: Tested with GARCH(1,1) (others welcome)
• Public API Ready: Registered via __init__.py and __all__

---

🧪 Testing

• Tested pipeline: MAMean + GARCH(1,1):
• Smoke‑tested simulation, forecasting, and residual pipelines.
• Coverage :
  • Parameter handling (lags, bounds)
  • Simulation pipeline
  • Forecast integration

---

📝 Notes

• 🔍 Currently validated only against GARCH(1,1) and Future tests with EGARCH, APARCH is encouraged
• 📐 Design mirrors ARX/HARX, making future extensions trivial
• 🙌 Happy to iterate on interface, test depth, or documentation if requested