diff --git a/code/chap05ex.ipynb b/code/chap05ex.ipynb
index cc00cc832..eb469e7a5 100644
--- a/code/chap05ex.ipynb
+++ b/code/chap05ex.ipynb
@@ -36,7 +36,7 @@
      "cell_type": "markdown",
      "metadata": {},
      "source": [
-      "##Exercise 5.1\n",
+      "## Exercise 5.1\n",
       "\n",
       "In the BRFSS (see Section 5.4), the distribution of heights is roughly normal with parameters \u00b5 = 178 cm and \u03c3 = 7.7 cm for men, and \u00b5 = 163 cm and \u03c3 = 7.3 cm for women.\n",
       "\n",
@@ -165,7 +165,7 @@
      "cell_type": "markdown",
      "metadata": {},
      "source": [
-      "##Exercise 5.2\n",
+      "## Exercise 5.2\n",
       "\n",
       "To get a feel for the Pareto distribution, let\u2019s see how different the world would be if the distribution of human height were Pareto. With the parameters $x_m = 1$ m and $\u03b1 = 1.7$, we get a distribution with a reasonable minimum, 1 m, and median, 1.5 m.\n",
       "\n",
@@ -287,7 +287,7 @@
      "cell_type": "markdown",
      "metadata": {},
      "source": [
-      "##Exercise 5.3\n",
+      "## Exercise 5.3\n",
       "\n",
       "The Weibull distribution is a generalization of the exponential distribution that comes up in failure analysis (see http://wikipedia.org/wiki/Weibull_distribution). Its CDF is\n",
       "\n",
@@ -310,7 +310,7 @@
      "cell_type": "markdown",
      "metadata": {},
      "source": [
-      "##Exercise 5.4\n",
+      "## Exercise 5.4\n",
       "\n",
       "For small values of n, we don\u2019t expect an empirical distribution to fit an analytic distribution exactly. One way to evaluate the quality of fit is to generate a sample from an analytic distribution and see how well it matches the data.\n",
       "\n",
@@ -365,4 +365,4 @@
    "metadata": {}
   }
  ]
-}
\ No newline at end of file
+}