diff --git a/sklearn/linear_model/least_angle.py b/sklearn/linear_model/least_angle.py
index 0c004d82468ccc995d53a45960b2983bb38b159b..50b772152e584b7510f8bcb90e2af914c56bcfb7 100644
--- a/sklearn/linear_model/least_angle.py
+++ b/sklearn/linear_model/least_angle.py
@@ -513,7 +513,7 @@ class Lars(LinearModel, RegressorMixin):
     verbose : boolean or integer, optional
         Sets the verbosity amount
 
-    normalize : boolean, optional, default False
+    normalize : boolean, optional, default True
         This parameter is ignored when ``fit_intercept`` is set to False.
         If True, the regressors X will be normalized before regression by
         subtracting the mean and dividing by the l2-norm.
@@ -744,7 +744,7 @@ class LassoLars(Lars):
     verbose : boolean or integer, optional
         Sets the verbosity amount
 
-    normalize : boolean, optional, default False
+    normalize : boolean, optional, default True
         This parameter is ignored when ``fit_intercept`` is set to False.
         If True, the regressors X will be normalized before regression by
         subtracting the mean and dividing by the l2-norm.
@@ -899,7 +899,7 @@ def _lars_path_residues(X_train, y_train, X_test, y_test, Gram=None,
         'lasso' for expected small values of alpha in the doc of LassoLarsCV
         and LassoLarsIC.
 
-    normalize : boolean, optional, default False
+    normalize : boolean, optional, default True
         This parameter is ignored when ``fit_intercept`` is set to False.
         If True, the regressors X will be normalized before regression by
         subtracting the mean and dividing by the l2-norm.
@@ -983,7 +983,7 @@ class LarsCV(Lars):
     verbose : boolean or integer, optional
         Sets the verbosity amount
 
-    normalize : boolean, optional, default False
+    normalize : boolean, optional, default True
         This parameter is ignored when ``fit_intercept`` is set to False.
         If True, the regressors X will be normalized before regression by
         subtracting the mean and dividing by the l2-norm.
@@ -1195,7 +1195,7 @@ class LassoLarsCV(LarsCV):
     verbose : boolean or integer, optional
         Sets the verbosity amount
 
-    normalize : boolean, optional, default False
+    normalize : boolean, optional, default True
         This parameter is ignored when ``fit_intercept`` is set to False.
         If True, the regressors X will be normalized before regression by
         subtracting the mean and dividing by the l2-norm.
@@ -1328,7 +1328,7 @@ class LassoLarsIC(LassoLars):
     verbose : boolean or integer, optional
         Sets the verbosity amount
 
-    normalize : boolean, optional, default False
+    normalize : boolean, optional, default True
         This parameter is ignored when ``fit_intercept`` is set to False.
         If True, the regressors X will be normalized before regression by
         subtracting the mean and dividing by the l2-norm.
diff --git a/sklearn/linear_model/omp.py b/sklearn/linear_model/omp.py
index 78cf3fb650795f4452cf3cf9f403413c1f773f79..8cf73754538c00965c62ada9228097d9c4f38efc 100644
--- a/sklearn/linear_model/omp.py
+++ b/sklearn/linear_model/omp.py
@@ -557,7 +557,7 @@ class OrthogonalMatchingPursuit(LinearModel, RegressorMixin):
         to false, no intercept will be used in calculations
         (e.g. data is expected to be already centered).
 
-    normalize : boolean, optional, default False
+    normalize : boolean, optional, default True
         This parameter is ignored when ``fit_intercept`` is set to False.
         If True, the regressors X will be normalized before regression by
         subtracting the mean and dividing by the l2-norm.
@@ -693,7 +693,7 @@ def _omp_path_residues(X_train, y_train, X_test, y_test, copy=True,
         to false, no intercept will be used in calculations
         (e.g. data is expected to be already centered).
 
-    normalize : boolean, optional, default False
+    normalize : boolean, optional, default True
         This parameter is ignored when ``fit_intercept`` is set to False.
         If True, the regressors X will be normalized before regression by
         subtracting the mean and dividing by the l2-norm.
@@ -758,7 +758,7 @@ class OrthogonalMatchingPursuitCV(LinearModel, RegressorMixin):
         to false, no intercept will be used in calculations
         (e.g. data is expected to be already centered).
 
-    normalize : boolean, optional, default False
+    normalize : boolean, optional, default True
         This parameter is ignored when ``fit_intercept`` is set to False.
         If True, the regressors X will be normalized before regression by
         subtracting the mean and dividing by the l2-norm.
diff --git a/sklearn/linear_model/randomized_l1.py b/sklearn/linear_model/randomized_l1.py
index 877908a61c7e40a35119d121c0f74a9cbbc8ed4a..8f8f5c12efe87756f71a13196fba5e53a8cee883 100644
--- a/sklearn/linear_model/randomized_l1.py
+++ b/sklearn/linear_model/randomized_l1.py
@@ -416,7 +416,7 @@ class RandomizedLogisticRegression(BaseRandomizedLinearModel):
     verbose : boolean or integer, optional
         Sets the verbosity amount
 
-    normalize : boolean, optional, default False
+    normalize : boolean, optional, default True
         If True, the regressors X will be normalized before regression.
         This parameter is ignored when `fit_intercept` is set to False.
         When the regressors are normalized, note that this makes the