bugfix FIGARCH(1, d, 1) formula in the function description

[pavelkrotkov]

E.g. in the original paper of Baililie et al. / Journal of Econometrics 74 (1996) 3-30 at the top o p.14 in the table caption:

$\sigma_t^2 = \omega + [1 - \beta L - (1 - \phi L)(1 - L)^d] R_t^2 + \beta \sigma_{t-1}^2$

so $\phi(L)=1-\phi L$ for first order model.

In ARCH($\infty$) form:

$\sigma_t^2 = (1 - \beta(L))^{-1} \omega + \lambda(L) R_t^2$

where

$\lambda(L) = (1 - (1 - \beta L)^{-1} (1 - \phi L)(1 - L)^d) = \sum_{k=0}^\infty \lambda_k L^k$

Having $1-\phi L$ is necessary for $\lambda_0$ to be 0, as is correctly written in the recursive formulas.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 99.51%. Comparing base (8ff5a5e) to head (5e0c969).

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #759   +/-   ##
=======================================
  Coverage   99.51%   99.51%           
=======================================
  Files          74       74           
  Lines       15634    15634           
  Branches     1274     1274           
=======================================
  Hits        15558    15558           
  Misses         51       51           
  Partials       25       25           

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