minor

README.md

@@ -1,4 +1,6 @@
-# `gmwmx2` Overview <img src="man/figures/logo.png" align="right" style="width: 20%; height: 20%"/>
+# `gmwmx2` Overview <img src="man/figures/logo.png" align="right" style="width: 15%; height: 15%"/>
+
+
 
 The `gmwmx2` `R` package implements the Generalized Method of Wavelet Moments with Exogenous Inputs estimator (GMWMX) presented in [Voirol, L., Xu, H., Zhang, Y., Insolia, L., Molinari, R. and Guerrier, S. (2024)](https://arxiv.org/abs/2409.05160).
 The GMWMX estimator is a computationally efficient estimator to estimate large scale regression problems with complex dependence structure in presence of missing data.

vignettes/fit_model.Rmd

@@ -139,7 +139,7 @@ $$
 $$
 When the argument `stochastic_model` is set to `"wn + pl"`, the stochastic model considered includes both white noise and colored noise with the specified above autocovariance structure. The model is therefore stationary and the parameters estimated are: $\sigma^2_{W N}$, $\kappa$ (constrained to be greater than $-1$) and $\sigma^2_{P L}$.
 
-When the argument `stochastic_model` is set to `"wn + fl"`, the stochastic model considered includes both white noise and flicker noise (not stationary power-law noise with spectral index $\kappa=-1$) where the variance covariance of the flicker noise $\omega$ is obtained as follows (see e.g., [@bos2008fast]):
+When the argument `stochastic_model` is set to `"wn + fl"`, the stochastic model considered includes both white noise and flicker noise (not stationary power-law noise with spectral index $\kappa=-1$) where the variance covariance of the flicker noise $\omega$ is obtained as follows (see e.g., [@bos2008fast]): 
 
 $$
 \operatorname{Cov}(\omega) = \sigma^2_{F L}\mathbf{U}^T \mathbf{U}