Add ATT method to the texas nb

examples/texas.ipynb

@@ -35,7 +35,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -210,6 +210,40 @@
     "synth.gaps_plot(time_period=range(1985, 2001), treatment_time=1993)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Compute the average treatment effect on the treated unit (ATT) over the post-treatment time period. This method returns a standard error also."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'att': 20339.375838131393, 'se': 3190.4946788704715}"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "synth.att(time_period=range(1993, 2001))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The summary function give more information on the predictor values. The first column shows the value of the $V$ matrix for each predictor, the column 'treated' shows the mean value of each predictor for the treated unit over the time period `time_predictors_prior`, the column 'synthetic' shows the mean value of each predictor for the synthetic control over the time period `time_predictors_prior` and finally the column 'sample mean' shows the sample mean of that predictor for all control units over the time period `time_predictors_prior` i.e. this is the same as the synthetic control with all weights equal."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 6,
@@ -389,7 +423,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.0 (tags/v3.9.0:9cf6752, Oct  5 2020, 15:34:40) [MSC v.1927 64 bit (AMD64)]"
+   "version": "3.10.4"
   },
   "orig_nbformat": 4,
   "vscode": {