Add tests for AR mean forecast simulation paths

[aeshef]

While reading through the forecasting code, I noticed the comment with the AR mean simulation path construction was "not tested, but probably right". The added tests verify this branch directly for AR(1) and AR(2) models with GARCH volatility, covering both method="simulation" and method="bootstrap".

The tests recompute the simulated mean paths and long-run variance paths from the simulated residuals and residual variance paths, and compare these against the values returned by forecast.simulations.

Tested locally with:

pytest arch/tests/univariate/test_forecast.py::TestForecasting::test_ar1_garch_mean_forecast_simulation_paths arch/tests/univariate/test_forecast.py::TestForecasting::test_ar2_garch_mean_forecast_simulation_paths -v

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 99.54%. Comparing base (543f44c) to head (3da6c09).

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #849   +/-   ##
=======================================
  Coverage   99.54%   99.54%           
=======================================
  Files          78       78           
  Lines       15818    15912   +94     
  Branches     1294     1301    +7     
=======================================
+ Hits        15746    15840   +94     
  Misses         38       38           
  Partials       34       34           

Flag	Coverage Δ
adder	99.50% <100.00%> (+<0.01%)	⬆️
subtractor	99.50% <100.00%> (+<0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.