diff --git a/.github/workflows/dynare-6.2-matlab-r2024b-macos.yml b/.github/workflows/dynare-6.2-matlab-r2024b-macos.yml
index 8f91619..1b095e1 100644
--- a/.github/workflows/dynare-6.2-matlab-r2024b-macos.yml
+++ b/.github/workflows/dynare-6.2-matlab-r2024b-macos.yml
@@ -106,4 +106,13 @@ jobs:
           command: |
             addpath("Dynare-6.2-arm64/matlab");
             cd("progs/matlab");
-            USOil;
\ No newline at end of file
+            USOil;
+
+      - name: Run week 9 codes
+        uses: matlab-actions/run-command@v2
+        with:
+          command: |
+            addpath("Dynare-6.2-arm64/matlab");
+            cd("progs/matlab");
+            keatingSR;
+            BlanchardQuahLR;
\ No newline at end of file
diff --git a/.github/workflows/dynare-6.2-matlab-r2024b-ubuntu.yml b/.github/workflows/dynare-6.2-matlab-r2024b-ubuntu.yml
index dfe0a13..4bcd667 100644
--- a/.github/workflows/dynare-6.2-matlab-r2024b-ubuntu.yml
+++ b/.github/workflows/dynare-6.2-matlab-r2024b-ubuntu.yml
@@ -135,4 +135,13 @@ jobs:
           command: |
             addpath("dynare/matlab");
             cd("progs/matlab");
-            USOil;
\ No newline at end of file
+            USOil;
+
+      - name: Run week 9 codes
+        uses: matlab-actions/run-command@v2
+        with:
+          command: |
+            addpath("dynare/matlab");
+            cd("progs/matlab");
+            keatingSR;
+            BlanchardQuahLR;
\ No newline at end of file
diff --git a/.github/workflows/dynare-6.2-matlab-r2024b-windows.yml b/.github/workflows/dynare-6.2-matlab-r2024b-windows.yml
index 4e7a1b2..08f2f27 100644
--- a/.github/workflows/dynare-6.2-matlab-r2024b-windows.yml
+++ b/.github/workflows/dynare-6.2-matlab-r2024b-windows.yml
@@ -97,4 +97,13 @@ jobs:
           command: |
             addpath("D:\hostedtoolcache\windows\dynare-6.0\matlab");
             cd("progs/matlab");
-            USOil;
\ No newline at end of file
+            USOil;
+
+      - name: Run week 9 codes
+        uses: matlab-actions/run-command@v2
+        with:
+          command: |
+            addpath("D:\hostedtoolcache\windows\dynare-6.0\matlab");
+            cd("progs/matlab");
+            keatingSR;
+            BlanchardQuahLR;
\ No newline at end of file
diff --git a/README.md b/README.md
index fb28e9c..0eebcb1 100644
--- a/README.md
+++ b/README.md
@@ -120,7 +120,7 @@ Please feel free to use this for teaching or learning purposes; however, taking
 ### To Do
 
 * [x] review the solutions of [last week's exercises](https://github.com/wmutschl/Quantitative-Macroeconomics/releases/latest/download/week_4.pdf) and write down all your questions
-* [x] re-read Lütkepohl (2004) and quickly go through Kilian and Lütkepohl (2007, Ch. 12.2); make note of all the aspects and concepts that you are still not familiar with or that you find difficult to understand
+* [x] re-read Lütkepohl (2004) and briefly go through Kilian and Lütkepohl (2007, Ch. 2.6, 2.7, 12.2); make note of all the aspects and concepts that you are still not familiar with or that you find difficult to understand
 * [x] Do exercise 1 of the problem set for week 5; we will do exercises 2 and 3 in class
 * [x] participate in the Q&A sessions with all your questions and concerns
 * [x] for immediate help: [schedule a meeting](https://schedule.mutschler.eu)
@@ -152,50 +152,57 @@ Familiarize yourself with
 </details>
 
 
-<!---
-
 <details>
   <summary> Week 7: The identification problem in SVAR models</summary>
 
 ### Goals
 
 * understand the identification problem in SVAR models
+* understand recursive identification, short-run restrictions and the impact matrix
+* implement recursive identification via Cholesky or numerical optimization
+
 
 ### To Do
 
 * [x] Review the solutions of [last week's exercises](https://github.com/wmutschl/Quantitative-Macroeconomics/releases/latest/download/week_6.pdf) and write down all your questions
-* [x] Read Kilian and Lütkepohl (2007, Ch. 2.3 and Ch. 2.6); make note of all the aspects and concepts that you are not familiar with or that you find difficult to understand
-* [x] Do exercises 1 and 2 of problem set 7; we will do exercise 3 in class
+* [x] Read Kilian and Lütkepohl (2007, Ch. 4.1, 7.6, 8, 9); make note of all the aspects and concepts that you are not familiar with or that you find difficult to understand
+* [x] We will do the exercises in class
 * [x] If you have questions, get in touch with me via email or (better) [schedule a meeting](https://schedule.mutschler.eu)
 
 </details>
 
+
 <details>
-  <summary> Week 8: Short-run restrictions in Structural Vector Autoregressive (SVAR) Models</summary>
+  <summary> Week 8: MIDTERM EXAM</summary>
+</details>
+
+
+<details>
+  <summary> Week 9: Short-run and Long-run restrictions in Structural Vector Autoregressive (SVAR) Models</summary>
 
 ### Goals
 
-* understand recursive identification, short-run restrictions and the impact matrix
-* implement recursive identification both via Cholesky or numerical optimization
 * implement short-run restrictions using numerical optimization
+* understand long-run restrictions and the long-run multiplier matrix
+* implement long-run restrictions using Cholesky or numerical optimization
 
 ### To Do
 
 * [x] Review the solutions of [last week's exercises](https://github.com/wmutschl/Quantitative-Macroeconomics/releases/latest/download/week_7.pdf) and write down all your questions
-* [x] Read Kilian and Lütkepohl (2007, Ch. 4.1, Ch. 7.6, Ch.8, Ch.9); make note of all the aspects and concepts that you are not familiar with or that you find difficult to understand
-* [x] Do exercises 1 and 2 from problem set 8; we will do exercise 3 in class
+* [x] Read Kilian and Lütkepohl (2007, Ch. 4.1, Ch. 7.6, Ch.8, Ch.9) and Blanchard and Quah (1989); make note of all the aspects and concepts that you are not familiar with or that you find difficult to understand
+* [x] We will do the exercises in class
 * [x] If you have questions, get in touch with me via email or (better) [schedule a meeting](https://schedule.mutschler.eu)
 
 </details>
 
+<!---
 
 <details>
-  <summary> Week 9: Short-run and Long-run restrictions in Structural Vector Autoregressive (SVAR) Models, Asymptotic and Bootstrap Inference in SVARs Identified By Exclusion Restrictions: Theory</summary>
+  <summary> Week 10: Asymptotic and Bootstrap Inference in SVARs Identified By Exclusion Restrictions: Theory</summary>
 
 ### Goals
 
-* understand long-run restrictions and the long-run multiplier matrix
-* implement short-run and long-run restrictions using numerical optimization
+* implement both short-run and long-run restrictions using numerical optimization
 * understand pros and cons of asymptotic inference for the impulse-response function of SVAR models
 * understand pros and cons of bootstrap inference for the impulse-response function of SVAR models
 
diff --git a/exercises/svar_longrun.tex b/exercises/svar_longrun.tex
index b4a149a..cae5773 100644
--- a/exercises/svar_longrun.tex
+++ b/exercises/svar_longrun.tex
@@ -5,43 +5,49 @@
   whereas \(gdp_t\) exhibits a unit root;
   that is, GDP growth, \(\Delta gdp_t = gdp_{t} - gdp_{t-1}\), is covariance-stationary.
 \textcite{Blanchard.Quah_1989_DynamicEffectsAggregate} set up a SVAR model for \(y_t = (\Delta gdp_t, ur_t)'\)
-  and analyze the effects of two structural shocks, an aggregate supply shock \(\varepsilon_t^{AS}\) and an aggregate demand shock \(\varepsilon_t^{AD}\).
+  and analyze the effects of two structural shocks,
+  an aggregate supply shock \(\varepsilon_t^{AS}\)
+  and an aggregate demand shock \(\varepsilon_t^{AD}\).
 
 \begin{enumerate}
 \item Why are short-run restrictions sometimes (or even often) \emph{problematic}?
 What about long-run restrictions?
 
-\item Assume for simplicity a VAR(1) model for \(y_t\).
-Derive the effect of the structural shocks on the behavior of \(ur_{t+h}\), \(\Delta gdp_{t+h}\) and \(gdp_{t+h}\) for \(h=0,1,2\cdots \).
+\item Assume for simplicity a VAR{(1)} model for \(y_t\).
+Derive the effect of the structural shocks on the behavior of
+  \(ur_{t+h}\), \(\Delta gdp_{t+h}\) and \(gdp_{t+h}\) for \(h=0,1,2\cdots \).
 What happens in the long-run, i.e.\ for \(h\rightarrow \infty \)?
 
-\item Discuss the implications on the structural impulse responses of requiring \(gdp_t\) to return to its initial level in the long-run in response to an aggregate demand shock.
+\item Discuss the implications on the structural impulse responses of requiring \(gdp_t\)
+  to return to its initial level in the long-run in response to an aggregate demand shock.
 
 \item Given knowledge of the reduced-form VAR model parameters,
-  show how to recover the short-run impact matrix \(B_0^{-1}\) from the long-run structural impulse response matrix
+  show how to recover the short-run impact matrix \(B_{0}^{-1}\) from the long-run structural impulse response matrix
   \begin{align*}
-  \Theta(1)={(I-A_1-\cdots -A_p)}^{-1}B_0^{-1} = {A(1)}^{-1}B_0^{-1}
+  \Theta(1)={(I-A_{1}-\cdots -A_{p})}^{-1}B_{0}^{-1} = {A(1)}^{-1}B_{0}^{-1}
   \end{align*} 
   where \(A(1)\) denotes the lag polynomial evaluated at \(L=1\).
 
 \item Consider the data given in \texttt{BlanchardQuah1989.csv}.
-Estimate a SVAR(8) model with a constant term.
+Estimate a SVAR{(8)} model with a constant term.
 The structural shocks are identified by imposing that \(\varepsilon_t^{AD}\) has no long-run effect on the level of real GDP\@.
-Estimate the impact matrix \(B_0^{-1}\) using 
+Estimate the impact matrix \(B_{0}^{-1}\) using 
 \begin{enumerate}
-\item the Cholesky decomposition on \({\hat{A}(1)}^{-1} \hat{\Sigma}_u {\hat{A}(1)}^{-1'}= \Theta(1) \Theta(1)'\)
+\item the Cholesky decomposition on \({\hat{A}(1)}^{-1} \hat{\Sigma}_{u} {\hat{A}(1)}^{-1'}= \Theta(1) \Theta(1)'\)
 
 \item a nonlinear equation solver that minimizes
 \begin{align*}
-F(B_0^{-1}) = \begin{bmatrix}
-vech(B_0^{-1}B_0^{-1'}-\hat{\Sigma}_u)\\
+F(B_{0}^{-1}) =
+\begin{bmatrix}
+vech(B_{0}^{-1}B_{0}^{-1'}-\hat{\Sigma}_u)
+\\
 \text{restrictions on } \Theta(1)
 \end{bmatrix}
 \end{align*}
 
 \end{enumerate}
-where \(\Theta(1)={(I-A_1-\cdots -A_p)}^{-1}B_0^{-1} = {A(1)}^{-1}B_0^{-1}\).
-Assume that \(E(\varepsilon_t\varepsilon_t')=I_2\) and the diagonal elements of \(B_0^{-1}\) are positive.
+where \(\Theta(1)={(I-A_{1}-\cdots-A_{p})}^{-1}B_{0}^{-1} = {A(1)}^{-1}B_{0}^{-1}\).
+Assume that \(E(\varepsilon_{t}\varepsilon_{t}')=I_{2}\) and the diagonal elements of \(B_{0}^{-1}\) are positive.
 
 \item Plot the structural impulse response functions using \texttt{irfPlots.m} for the level of GDP and the unemployment rate.
 Interpret your results in economic terms.
@@ -49,11 +55,11 @@
 
 \paragraph{Readings}
 \begin{itemize}
-	\item \textcite[Ch.~10.1, 10.3, 11.1, 11.2]{Kilian.Lutkepohl_2017_StructuralVectorAutoregressive}
+\item \textcite[Ch.~10.1, 10.3, 11.1, 11.2]{Kilian.Lutkepohl_2017_StructuralVectorAutoregressive}
 \end{itemize}
 
 \begin{solution}\textbf{Solution to \nameref{ex:BlanchardQuahLongRunRestrictions}}
-\ifDisplaySolutions
+\ifDisplaySolutions%
 \input{exercises/svar_longrun_solution.tex}
 \fi
 \newpage
diff --git a/exercises/svar_longrun_solution.tex b/exercises/svar_longrun_solution.tex
index 550415f..a8f9522 100644
--- a/exercises/svar_longrun_solution.tex
+++ b/exercises/svar_longrun_solution.tex
@@ -12,102 +12,110 @@
 This suggests an alternative approach, i.e\ use theoretically-inspired long-run restrictions to identify shocks and impulse responses
   not only for the long-run behavior but also for the short-run behavior of all variables.
 
-\item We have already shown that in a VAR(1) model we get the following structural impulse response function for horizons \(h=0,1,2,\cdots \)
+\item We have already shown that in a VAR{(1)} model we get the following structural impulse response function for horizons \(h=0,1,2,\cdots \)
 \begin{align*}
-    \frac{\partial y_t}{\partial \varepsilon_t'} = B_0^{-1}
-    ,\qquad
-    \frac{\partial y_{t+1}}{\partial \varepsilon_t'} = A_1 B_0^{-1}
-    ,\qquad
-    \frac{\partial y_{t+2}}{\partial \varepsilon_t'} = A^2_1 B_0^{-1}
-    ,\qquad
-    \frac{\partial y_{t+h}}{\partial \varepsilon_t'} = A^h_1 B_0^{-1}
+\frac{\partial y_{t}}{\partial \varepsilon_{t}'} = B_{0}^{-1}
+,\qquad
+\frac{\partial y_{t+1}}{\partial \varepsilon_{t}'} = A_{1} B_{0}^{-1}
+,\qquad
+\frac{\partial y_{t+2}}{\partial \varepsilon_{t}'} = A^{2}_{1} B_{0}^{-1}
+,\qquad
+\frac{\partial y_{t+h}}{\partial \varepsilon_{t}'} = A^{h}_{1} B_{0}^{-1}
 \end{align*}
-The effects of \(\Delta gdp_t\) are given by the first row and the second row contains the effects on \(ur_t\).
-So the effect of the structural shocks on the covariance stationary variables \(ur_t\) and \(\Delta gdp_t\) is given by
+The effects of \(\Delta {gdp}_{t}\) are given by the first row and the second row contains the effects on \({ur}_{t}\).
+So the effect of the structural shocks on the covariance stationary variables \({ur}_{t}\) and \(\Delta {gdp}_{t}\) is given by
 \begin{itemize}
-    \item \(B_0^{-1}\) on impact
-    \item \(A_1 B_0^{-1}\) after one period
-    \item \(A_1^2 B_0^{-1}\) after two periods
-    \item \(A_1^h B_0^{-1}\) after \(h\) periods
+\item \(B_{0}^{-1}\) on impact
+\item \(A_{1} B_{0}^{-1}\) after one period
+\item \(A_{1}^{2} B_{0}^{-1}\) after two periods
+\item \(A_{1}^{h} B_{0}^{-1}\) after \(h\) periods
 \end{itemize}
-Now, because \(ur_t\) and \(\Delta gdp_t\) are covariance stationary,
-  the Eigenvalues of \(A_1\) are inside the unit circle.
-So, in the long-run, \(h\rightarrow \infty \), we have that \(A^h\rightarrow 0\).
-That is, the effect of the structural shocks on the covariance-stationary variables \(ur_t\) and \(\Delta gdp_t\) vanishes over time
-  and they return to their expected mean value.
-On the other hand, given the IRFs of \(\frac{\partial \Delta gdp_{t+h}}{\partial \varepsilon_t'}\)
-  we can derive the IRF of \(gdp_{t+h}\) by the cumulative sum
+Now, because \({ur}_{t}\) and \(\Delta {gdp}_{t}\) are covariance stationary,
+  the Eigenvalues of \(A_{1}\) are inside the unit circle.
+So, in the long-run, \(h\rightarrow \infty \), we have that \(A^{h}\rightarrow 0\).
+That is, the effect of the structural shocks on the covariance-stationary variables \({ur}_{t}\) and \(\Delta {gdp}_{t}\)
+  vanishes over time and they return to their expected mean value.
+On the other hand, given the IRFs of \(\frac{\partial \Delta {gdp}_{t+h}}{\partial \varepsilon_{t}'}\)
+  we can derive the IRF of \({gdp}_{t+h}\) by the cumulative sum
 \begin{align*}
-\frac{\partial gdp_{t+h}}{\partial \varepsilon_t'} = \frac{\partial \Delta gdp_t}{\partial \varepsilon_t'} + \frac{\partial \Delta gdp_{t+1}}{\partial \varepsilon_t'} + \cdots  + \frac{\partial \Delta gdp_{t+h}}{\partial \varepsilon_t'}
+\frac{\partial {gdp}_{t+h}}{\partial \varepsilon_{t}'}
+=
+\frac{\partial \Delta {gdp}_{t}}{\partial \varepsilon_{t}'}
++ \frac{\partial \Delta {gdp}_{t+1}}{\partial \varepsilon_{t}'}
++ \cdots
++ \frac{\partial \Delta {gdp}_{t+h}}{\partial \varepsilon_{t}'}
 \end{align*}
 That is, the effect on the level of GDP to an increase in the structural shocks is equal to the \textbf{first row} in
 \begin{itemize}
-    \item \((I)B_0^{-1}\) on impact
-    \item \((I+A_1) B_0^{-1}\) after one period
-    \item \((I+A_1+A_1^2) B_0^{-1}\) after two periods
-    \item \((I+A_1+A_1^2+A_1^3) B_0^{-1}\) after three periods
-    \item \((I+A_1+A_1^2+\cdots +A_1^h) B_0^{-1}\) after $h$ periods
+\item \((I)B_{0}^{-1}\) on impact
+\item \((I+A_{1}) B_{0}^{-1}\) after one period
+\item \((I+A_{1}+A_{1}^{2}) B_{0}^{-1}\) after two periods
+\item \((I+A_{1}+A_{1}^{2}+A_{1}^{3}) B_{0}^{-1}\) after three periods
+\item \((I+A_{1}+A_{1}^{2}+\cdots +A_{1}^{h}) B_{0}^{-1}\) after \(h\) periods
 \end{itemize}
-In the long-run, \(h\rightarrow\infty \), the effect of the structural shocks on the level of \(gdp_t\) is given by the \textbf{first row} of
+In the long-run, \(h\rightarrow\infty \), the effect of the structural shocks on the level of \({gdp}_{t}\) is given by the \textbf{first row} of
 \begin{align*}
-    (I+A_1+A_1^2+A_1^3+\cdots ) B_0^{-1} = {(I-A)}^{-1} B_0^{-1}
+(I+A_{1}+A_{1}^{2}+A_{1}^{3}+\cdots ) B_{0}^{-1} = {(I-A)}^{-1} B_{0}^{-1}
 \end{align*}
-Again, we make use of the fact that \(ur_t\) and \(\Delta gdp_t\) are covariance-stationary,
-  which implies that the Eigenvalues of \(A_1\) are inside the unit circle and we can make use of the formula for the geometric sum.
+Again, we make use of the fact that \({ur}_{t}\) and \(\Delta {gdp}_{t}\) are covariance-stationary,
+  which implies that the Eigenvalues of \(A_{1}\) are inside the unit circle and we can make use of the formula for the geometric sum.
 
-More generally, for VAR(p) models with variables in first-differences, we get the long-run effect matrix for the corresponding level variables
+More generally, for VAR{(p)} models with variables in first-differences, we get the long-run effect matrix for the corresponding level variables
 \begin{align*}
-    \Theta(1) = {A(1)}^{-1} B_0^{-1}
+\Theta(1) = {A(1)}^{-1} B_{0}^{-1}
 \end{align*}
-where \(A(1)= (I - A_1 - \cdots  - A_p)\) is the lag polynomial evaluated at \(L=1\).
+where \(A(1)= (I - A_{1} - \cdots  - A_{p})\) is the lag polynomial evaluated at \(L=1\).
 
 \item Re-consider the long-run multiplier matrix:
 \begin{align*}
-\Theta(1) = {A(1)}^{-1} B_0^{-1} \equiv \begin{pmatrix} a & \textcolor{red}{c}\\ b & d \end{pmatrix}
+\Theta(1) = {A(1)}^{-1} B_{0}^{-1} \equiv \begin{pmatrix} a & \textcolor{red}{c}\\ b & d \end{pmatrix}
 \end{align*}
-where \(a\) and \(c\) are the long-run effects of \(\varepsilon_t^{AS}\) and \(\varepsilon_t^{AD}\) on the level of \(gdp_t\).
-Economic theory tells us that in the long-run \(gdp_t\) is not affected by an aggregate demand shock and it returns to its initial value.
+where \(a\) and \(c\) are the long-run effects of \(\varepsilon_{t}^{AS}\) and \(\varepsilon_{t}^{AD}\) on the level of \({gdp}_{t}\).
+Economic theory tells us that in the long-run \({gdp}_{t}\) is not affected by an aggregate demand shock and it returns to its initial value.
 In other words, economic theory requires that \(c=0\):
 \begin{align*}
-\Theta(1) = {A(1)}^{-1} B_0^{-1} \equiv \begin{pmatrix} a & \textcolor{red}{0}\\ b & d \end{pmatrix}
+\Theta(1) = {A(1)}^{-1} B_{0}^{-1} \equiv \begin{pmatrix} a & \textcolor{red}{0}\\ b & d \end{pmatrix}
 \end{align*}
-Note that we don't have anything to say about $a$ (the effect of an AS shock on the level of GDP) and leave it unrestricted.
-Similarly, as \(ur_t\) is covariance-stationary and does not enter \(y_t\) as first difference,
+Note that we don't have anything to say about \(a\) (the effect of an AS shock on the level of GDP) and leave it unrestricted.
+Similarly, as \({ur}_{t}\) is covariance-stationary and does not enter \(y_{t}\) as first difference,
   we can't really identify or economically interpret \(b\) and \(d\) and leave it unrestricted as well.
 
-\item There are two ways to infer \(B_0^{-1}\) from the restricted \(\Theta(1) = {A(1)}^{-1} B_0^{-1} \equiv \begin{pmatrix} a & \textcolor{red}{0}\\ b & d \end{pmatrix}\) matrix:
+\item There are two ways to infer \(B_{0}^{-1}\) from the restricted
+\(\Theta(1) = {A(1)}^{-1} B_{0}^{-1} \equiv \begin{pmatrix} a & \textcolor{red}{0}\\ b & d \end{pmatrix}\) matrix:
 \\
 \textbf{1. Method: Cholesky decomposition}
 \\
 Note that \(\Theta(1)\) is lower triangular and looks like a Cholesky factor. Indeed:
 \begin{align*}
-    \Theta(1) \Theta(1)' = {A(1)}^{-1} B_0^{-1} B_0^{-1'} {A(1)}^{-1'} = {A(1)}^{-1} \Sigma_u {A(1)}^{-1'}
+\Theta(1) \Theta(1)' = {A(1)}^{-1} B_{0}^{-1} B_{0}^{-1'} {A(1)}^{-1'} = {A(1)}^{-1} \Sigma_{u} {A(1)}^{-1'}
 \end{align*}
-This right-hand side can be readily computed as both \(A(1)\) as well as \(\Sigma_u\) are given by the reduced-form estimation.
-That is computing the lower triangular Cholesky factor of \({A(1)}^{-1} \Sigma_u {A(1)}^{-1'}\) provides \(\Theta(1)\).
-From \(\Theta(1)\) we can compute \(B_0^{-1}\):
+This right-hand side can be readily computed as both \(A(1)\) as well as \(\Sigma_{u}\) are given by the reduced-form estimation.
+That is computing the lower triangular Cholesky factor of \({A(1)}^{-1} \Sigma_{u} {A(1)}^{-1'}\) provides \(\Theta(1)\).
+From \(\Theta(1)\) we can compute \(B_{0}^{-1}\):
 \begin{align*}
-B_0^{-1} = A(1)\Theta(1)
+B_{0}^{-1} = A(1)\Theta(1)
 \end{align*}
-Once we have \(B_0^{-1}\) we can proceed as usual and compute the impulse response function.
+Once we have \(B_{0}^{-1}\) we can proceed as usual and compute the impulse response function.
 
 \textbf{2. Method: Numerical optimization}
 \\
-Use a numerical optimizer to find a \(B_0^{-1}\) matrix that fulfills the following restrictions:
+Use a numerical optimizer to find a \(B_{0}^{-1}\) matrix subject to the following restrictions:
 \begin{itemize}
-    \item covariance restrictions: \(vech(B_0^{-1} B_0^{-1'}) = vech(\Sigma_u)\)
-    \item long-run restriction: \(\Theta(1)_{1,2} = 0\)
+\item covariance restrictions: \(vech(B_{0}^{-1} B_{0}^{-1'}) = vech(\Sigma_{u})\)
+\item long-run restriction: \(\Theta{(1)}_{1,2} = 0\)
 \end{itemize}
-where \(\Theta(1) = {A(1)}^{-1} B_0^{-1}\).
-Note that both \(\Sigma_u\) as well as \({A(1)}^{-1}\) are fixed parameters and given by the reduced-form estimation.
+where \(\Theta(1) = {A(1)}^{-1} B_{0}^{-1}\).
+Note that both \(\Sigma_{u}\) as well as \({A(1)}^{-1}\) are fixed parameters and given by the reduced-form estimation.
 
 \item The code might look like this:
 \lstinputlisting[style=Matlab-editor,basicstyle=\mlttfamily,title=\lstname]{progs/matlab/BlanchardQuahLR.m}
 Here is the helper function to impose the restrictions:
 \lstinputlisting[style=Matlab-editor,basicstyle=\mlttfamily,title=\lstname]{progs/matlab/BlanchardQuahLR_f.m}
-The supply shock has on impact a positive effect on the log-level of GDP, it then drops for one quarter, but increases again afterwards.
+The supply shock has on impact a positive effect on the log-level of GDP,
+  it then drops for one quarter, but increases again afterwards.
 The long-run effect of a supply shock on the log-level of GDP is positive.
 On the other hand, the demand shock obviously has no long-run effect on the log-level of GDP (due to our identifying restriction),
   whereas in the short-run the effect is negative.
-The effects on the unemployment rate are basically flipped with the exception that in the long-run the effects vanish as \(ur_t\) is covariance-stationary.
+The effects on the unemployment rate are basically flipped
+  with the exception that in the long-run the effects vanish as \({ur}_{t}\) is covariance-stationary.
 \end{enumerate}
\ No newline at end of file
diff --git a/exercises/svar_shortrun.tex b/exercises/svar_shortrun.tex
index 486463e..112d6d3 100644
--- a/exercises/svar_shortrun.tex
+++ b/exercises/svar_shortrun.tex
@@ -1,14 +1,14 @@
 \section[Non-recursively Identified Models By Short-Run Restrictions]{Non-recursively Identified Models By Short-Run Restrictions\label{ex:NonRecursivelyIdentifiedModelsShortRun}}
 Consider a quarterly model of US monetary policy.
 Let \(y_t=(\Delta p_t, \Delta gnp_t, i_t, \Delta m_t)'\),
-where \(p_t\) refers to the log of the GNP deflator,
-\(gnp_t\) to the log of real GNP,
-\(i_t\) to the federal funds rate, averaged by quarter,
-and \(m_t\) to the log of money aggregate M1. 
+  where \(p_t\) refers to the log of the GNP deflator,
+  \(gnp_t\) to the log of real GNP,
+  \(i_t\) to the federal funds rate, averaged by quarter,
+  and \(m_t\) to the log of money aggregate M1.
 The data is given in \texttt{Keating1992.csv}.
 
 The structural shock vector \(\varepsilon_t = (\varepsilon_t^{AS},\varepsilon_t^{IS},\varepsilon_t^{MS},\varepsilon_t^{MD})\)
-includes an aggregate supply shock, an IS shock, a money supply shock, and a money demand shock.
+  includes an aggregate supply shock, an IS shock, a money supply shock, and a money demand shock.
 The structural model can be written as:
 \begin{align*}
 \begin{pmatrix}
@@ -19,27 +19,27 @@
 -b_{21,0}u_t^p - b_{23,0} u_t^i- b_{24,0}u_t^m +\varepsilon_{t}^{IS}\\
 -b_{34,0}u_t^m + \varepsilon_{t}^{MS}\\
 -b_{41,0}(u_t^{gnp}+u_t^p)-b_{43,0}u_t^i +\varepsilon_{t}^{MD}
-\end{pmatrix}        
+\end{pmatrix}
 \end{align*}
-Furthermore, it is assumed that \(E(\varepsilon_t \varepsilon_t')=\Sigma_\varepsilon\) is NOT the identity matrix;
-hence, we will use the normalization rule that the diagonal elements of \(B_0\) equal unity.
+Furthermore, it is assumed that \(E(\varepsilon_t \varepsilon_t')=\Sigma_{\varepsilon}\) is NOT the identity matrix;
+  hence, we will use the normalization rule that the diagonal elements of \(B_{0}\) equal unity.
 
 \begin{enumerate}
 \item Estimate the reduced-form covariance matrix of a VAR model with four lags and an intercept with ordinary least squares.
 
-\item Provide intuition behind the structural model and derive the \(B_0\) matrix.
-Note that we are imposing restrictions on both \(B_0\) and \(\Sigma_\varepsilon \), but not on \(B_0^{-1}\).
+\item Provide intuition behind the structural model and derive the \(B_{0}\) matrix.
+Note that we are imposing restrictions on both \(B_{0}\) and \(\Sigma_{\varepsilon} \), but not on \(B_{0}^{-1}\).
 
-\item Estimate \(B_0\) and \(\Sigma_\varepsilon \) using the nonlinear equation solver \texttt{fsolve}.
+\item Estimate \(B_{0}\) and \(\Sigma_{\varepsilon}\) using the nonlinear equation solver \texttt{fsolve}.
 To this end, first set up a function that computes
 \begin{align*}
-F_{SR}([B_0, diag(\Sigma_\varepsilon)]) = \begin{bmatrix} vech\left(B_0^{-1} \Sigma_\varepsilon B_0^{-1'} - \hat{\Sigma}_u\right)\\\text{restrictions on }B_0\end{bmatrix}=0
+F_{SR}([B_{0}, diag(\Sigma_{\varepsilon})]) = \begin{bmatrix} vech\left(B_{0}^{-1} \Sigma_{\varepsilon} B_{0}^{-1'} - \hat{\Sigma}_u\right)\\\text{restrictions on }B_{0}\end{bmatrix}=0
 \end{align*}
-where \(diag(\Sigma_\varepsilon)\) denotes only the diagonal elements of \(\Sigma_\varepsilon \).
-Note that these diagonal elements as well as \(B_0\) are stacked into a matrix or vector which is then used as the input for the numerical optimizer.
+where \(diag(\Sigma_{\varepsilon})\) denotes only the diagonal elements of \(\Sigma_{\varepsilon}\).
+Note that these diagonal elements as well as \(B_{0}\) are stacked into a matrix or vector which is then used as the input for the numerical optimizer.
 Use feasible options for the optimizer (e.g.\ as in the previous exercises).
 
-\item Use the estimated structural impact matrix \(B_0^{-1}\Sigma_\varepsilon^{1/2}\) to plot the structural impulse response functions using \texttt{irfPlots.m}.
+\item Use the estimated structural impact matrix \(B_{0}^{-1}\Sigma_{\varepsilon}^{1/2}\) to plot the structural impulse response functions using \texttt{irfPlots.m}.
 Interpret the effects of an aggregate supply shock on prices, real GNP, the Federal Funds rate and M1.
 \end{enumerate}
 
@@ -49,7 +49,7 @@
 \end{itemize}
 
 \begin{solution}\textbf{Solution to \nameref{ex:NonRecursivelyIdentifiedModelsShortRun}}
-\ifDisplaySolutions
+\ifDisplaySolutions%
 \input{exercises/svar_shortrun_solution.tex}
 \fi
 \newpage
diff --git a/exercises/svar_shortrun_solution.tex b/exercises/svar_shortrun_solution.tex
index bb7e776..d3371a1 100644
--- a/exercises/svar_shortrun_solution.tex
+++ b/exercises/svar_shortrun_solution.tex
@@ -1,43 +1,71 @@
 \begin{enumerate}
-\item The OLS estimate of the reduced-form covariance matrix \(\Sigma_u\) is
+\item The OLS estimate of the reduced-form covariance matrix \(\Sigma_{u}\) is
 \begin{align*}
-    \widehat{\Sigma}_u = \begin{pmatrix}
-         0.061054  &  -0.015282  &   0.042398  &  0.0037836 \\
-        -0.015282  &    0.52305  &    0.07967  &   0.030602 \\
-         0.042398  &    0.07967  &    0.71689  &    -0.2451 \\
-        0.0037836  &   0.030602  &    -0.2451  &     1.1093 \\
-    \end{pmatrix} 
+\widehat{\Sigma}_u =
+\begin{pmatrix}
+ 0.061054  & -0.015282 &  0.042398 &  0.0037836 \\
+-0.015282  &  0.52305  &  0.07967  &  0.030602 \\
+ 0.042398  &  0.07967  &  0.71689  & -0.2451 \\
+ 0.0037836 &  0.030602 & -0.2451   &  1.1093 \\
+\end{pmatrix} 
 \end{align*}
 
-\item In order to identify the structural shocks from \(\Sigma_u = B_0^{-1} \Sigma_\varepsilon B_0^{-1'}\),
-  we require at least \(4(4-1)/2=6\) additional restrictions on \(B_0\) or \(B_0^{-1}\).
-In this exercise, we'll do this on \(B_0\) and not its inverse; that is, we can rewrite the equations in matrix notation:
+\item In order to identify the structural shocks from \(\Sigma_{u} = B_{0}^{-1} \Sigma_{\varepsilon} B_{0}^{-1'}\),
+  we require at least \(4(4-1)/2=6\) additional restrictions on \(B_{0}\) or \(B_{0}^{-1}\).
+In this exercise, we'll do this on \(B_{0}\) and not its inverse; that is, we can rewrite the equations in matrix notation:
 \begin{align*}
-    \underbrace{\begin{pmatrix} 1 & 0 & 0 & 0 \\ b_{21,0} & 1 & b_{23,0} & b_{24,0} \\ 0 & 0 & 1 & b_{34,0} \\ b_{41,0} & b_{41,0} & b_{43,0} & 1\end{pmatrix}}_{B_0}
-    \underbrace{\begin{pmatrix}u_t^p\\u_t^{gnp}\\u_t^{i}\\u_t^{m} \end{pmatrix}}_{u_t}
-    =
-    \underbrace{\begin{pmatrix}\varepsilon_t^{AS}\\\varepsilon_t^{IS}\\\varepsilon_t^{MS}\\\varepsilon_t^{MD} \end{pmatrix}}_{\varepsilon_t}
+\underbrace{%
+  \begin{pmatrix}
+  1 & 0 & 0 & 0 \\
+  b_{21,0} & 1 & b_{23,0} & b_{24,0} \\
+  0 & 0 & 1 & b_{34,0} \\
+  b_{41,0} & b_{41,0} & b_{43,0} & 1
+  \end{pmatrix}
+}_{B_{0}}
+\underbrace{%
+  \begin{pmatrix}
+  u_t^p \\
+  u_t^{gnp} \\
+  u_t^{i} \\
+  u_t^{m}
+  \end{pmatrix}
+}_{u_t}
+=
+\underbrace{%
+  \begin{pmatrix}
+  \varepsilon_t^{AS} \\
+  \varepsilon_t^{IS} \\
+  \varepsilon_t^{MS} \\
+  \varepsilon_t^{MD}
+  \end{pmatrix}
+}_{\varepsilon_t}
 \end{align*}
-Note that as the diagonal elements of \(B_0\) equal unity, we don't assume that \(E(\varepsilon_t \varepsilon_t')=\Sigma_\varepsilon \) is the identity matrix.
+Note that as the diagonal elements of \(B_{0}\) equal unity, we don't assume that \(E(\varepsilon_t \varepsilon_t')=\Sigma_{\varepsilon} \) is the identity matrix.
 So this is a different normalization rule as before.
 
 Economically, the above restrictions embody to some extent a baseline IS-LM model:
+
 \begin{enumerate}
+
 \item The first equation provides three restrictions by assuming that the price level is predetermined
 except that producers can respond immediately to aggregate supply shocks (e.g.\ an unexpected increase in oil or gas prices).
 This is basically a horizontal aggregate supply (AS) curve; that is why we label the shock with AS\@.
+
 \item The second equation provides no restrictions as it is assumed that real output responds to all other model variables contemporaneously.
 This equation can be interpreted as an aggregate demand curve, or an IS curve, that is why we label the shock IS\@.
+
 \item The third equation provides two restrictions by assuming that the interest rate does not react contemporaneously to aggregate measures of output and prices.
 This represents a simple money supply function, according to which the central bank adjusts the rate of interest in relation to the money stock
 and does not immediately observe aggregate output and aggregate prices.
 Of course, this is in contrast to modern monetary policy theory (and practice).
+
 \item The fourth equation provides one additional restriction by assuming that the first two entries in the last row are identical.
 The underlying idea is that this equation represents a money demand function in which short-run money holdings rise in proportion to NOMINAL GNP\@.
 Moreover, money holdings are allowed to be dependent on the interest rate.
+
 \end{enumerate}
 In sum, we have \(3+0+2+1=6\) restrictions, that is we have an exactly identified SVAR model,
-identified by short-run exclusion restrictions on \(B_0\).
+identified by short-run exclusion restrictions on \(B_{0}\).
 As the structure is not recursive, a Cholesky decomposition is not valid and hence we need to rely on a numerical optimizer (or an algorithm for short-run exclusion restrictions).
 
 \item The code might look like this:
@@ -47,11 +75,11 @@
 
 \item An unexpected upward shift of the aggregate supply curve
 \begin{itemize}
-    \item raises the price deflator
-    \item lowers real GNP
-    \item raises the federal funds rate
-    \item lowers the money supply at first, but ultimately raises M1
+\item raises the price deflator
+\item lowers real GNP
+\item raises the federal funds rate
+\item lowers the money supply at first, but ultimately raises M1
 \end{itemize}
 This response is not really appropriate for the U.S. economy during the considered sample period,
-making the identifying restrictions rather questionable.
+  making the identifying restrictions rather questionable.
 \end{enumerate}
\ No newline at end of file
diff --git a/week_9.tex b/week_9.tex
new file mode 100644
index 0000000..e7b8f08
--- /dev/null
+++ b/week_9.tex
@@ -0,0 +1,34 @@
+% !TEX root = week_9.tex
+\input{exercises/_common_header.tex}
+\Newassociation{solution}{Solution}{week_9_solution}
+\newif\ifDisplaySolutions\DisplaySolutionstrue
+
+\begin{document}
+\title{Quantitative Macroeconomics\\~\\Winter 2023/24\\~\\Week 9}
+\author{Willi Mutschler\\willi@mutschler.eu}
+\date{Version: 1.0\\Latest version available on: \href{https://github.com/wmutschl/Quantitative-Macroeconomics/releases/latest/download/week_9.pdf}{GitHub}}
+\maketitle\thispagestyle{empty}
+
+\newpage
+\Opensolutionfile{week_9_solution}[week_9_solution]
+\tableofcontents\thispagestyle{empty}\newpage
+
+\setcounter{page}{1}
+\input{exercises/svar_shortrun.tex}\newpage
+\input{exercises/svar_longrun.tex}\newpage
+\newpage
+
+\printbibliography
+\appendix
+\section{vech.m}
+\lstinputlisting[label=vech,,title=\lstname,style=Matlab-editor,basicstyle=\mlttfamily,title=\lstname]{progs/matlab/vech.m}
+
+
+\Closesolutionfile{week_9_solution}
+\ifDisplaySolutions%
+\newpage
+\appendix
+\section{Solutions}
+\input{week_9_solution}
+\fi
+\end{document}
\ No newline at end of file