updates

Author: mca91

.Rprofile

@@ -1070,9 +1070,9 @@ cat('
 <p>
 The sample average $\\overline{Y}$ converges in probability to $\\mu_Y$: $\\overline{Y}$ is *consistent* for $\\mu_Y$ if the probability that $\\overline{Y}$ is in the range $(\\mu_Y - \\epsilon)$ to $(\\mu_Y + \\epsilon)$ becomes arbitrary close to $1$ as $n$ increases for any constant $\\epsilon > 0$. We write this as
 
-$$ \\overline{Y} \\xrightarrow[]{p} \\mu_Y. $$
+$$ P(\\mu_Y-\\epsilon \\leq \\overline{Y} \\leq \\mu_Y + \\epsilon) \\rightarrow 1, \\, \\epsilon > 0 \\text{ as } n\\rightarrow\\infty. $$
 
-Consider the independently and identically distributed random variables $Y_i, i=1,\\dots,n$ with expectation $E(Y_i)=\\mu_Y$ and variance $\\text{Var}(Y_i)=\\sigma^2_Y$. Under the condition that $\\sigma^2_Y< \\infty$, that is, large outliers are unlikely, the law of large numbers states
+Consider the independently and identically distributed random variables $Y_i, i=1,\\dots,n$ with expectation $E(Y_i)=\\mu_Y$ and variance $\\text{Var}(Y_i)=\\sigma^2_Y$. Under the condition that $\\sigma^2_Y< \\infty$, that is, large outliers are unlikely, the law of large numbers thus states that
 
 $$ \\overline{Y} \\xrightarrow[]{p} \\mu_Y. $$
 
@@ -1086,7 +1086,7 @@ The following application simulates a large number of coin tosses (you may set t
 cat('\\begin{keyconcepts}[Convergence in Probability\\comma Consistency and the Law of Large Numbers]{2.6}
 The sample average $\\overline{Y}$ converges in probability to $\\mu_Y$: $\\overline{Y}$ is \\textit{consistent} for $\\mu_Y$ if the probability that $\\overline{Y}$ is in the range $(\\mu_Y - \\epsilon)$ to $(\\mu_Y + \\epsilon)$ becomes arbitrary close to $1$ as $n$ increases for any constant $\\epsilon > 0$. We write this as
 
-$$ \\overline{Y} \\xrightarrow[]{p} \\mu_Y. $$
+$$ P(\\mu_Y-\\epsilon \\leq \\overline{Y} \\leq \\mu_Y + \\epsilon) \\rightarrow 1, \\, \\epsilon > 0 \\text{ as } n\\rightarrow\\infty. $$
 
 Consider the independently and identically distributed random variables $Y_i, i=1,\\dots,n$ with expectation $E(Y_i)=\\mu_Y$ and variance $\\text{Var}(Y_i)=\\sigma^2_Y$. Under the condition that $\\sigma^2_Y< \\infty$, that is, large outliers are unlikely, the law of large numbers states
 

02-ch2.Rmd

@@ -651,4 +651,63 @@ We have not found evidence that severe punishments and increasing the minimum dr
 
 A powerful method that can be used if common panel regression approaches fail is instrumental variables regression. We will return to this concept in Chapter \@ref(ivr).
 
+## Exercises
 
+```{r, echo=FALSE, results='asis'}
+if (my_output=="html"){
+  cat('
+For the course of this section, you will work with <tt>Guns</tt>, a balanced panel containing observations on criminal and demographic variables for all US states and the years 1977-1999. The data set comes with the package <tt>AER</tt> which is already installed for the interactive R exercises below.
+
+<div  class = "DCexercise">
+
+#### 1. The Guns Data Set {-}
+
+**Instructions:**
+
++ Load both the package and the data set. 
+  
++ Get yourself an overview over the data set using the <tt>summary()</tt> function. Use <tt>?Guns</tt> for detailed information on the variables.
+  
++ Verify that <tt>Guns</tt> is a balanced panel. Do so by extracting the number of years and states from the data set and assign them to the predefined variables <tt>years</tt> and <tt>states</tt>, respectively. Afterwards use these variables for a logical comparison: check that the panel is balanced
+
+<iframe src="DCL/ex10_1.html" frameborder="0" scrolling="no" style="width:100%;height:340px"></iframe>
+        
+**Hints:**
+  
+  + Use <tt>library()</tt> and <tt>data()</tt> to attach the package and load the data set, respectively.
+  + Use <tt>summary()</tt> to obtain a comprehensive overview of the dataset.
+  + In order to be a balanced panel the number of entities times the number of years has to be equal to the total number of observations in the dataset. The basic functions <tt>levels()</tt>, <tt>length()</tt> and <tt>nrow()</tt> may be useful here to accomplish this task.
+      
+</div>')
+} else {
+  cat('\\begin{center}\\textit{This interactive part of URFITE is only available in the HTML version.}\\end{center}')
+}
+```
+
+```{r, echo=FALSE, results='asis'}
+if (my_output=="html") {
+  cat('
+<div  class = "DCexercise">
+
+#### 2. Strict or Loose? Gun Laws and the Effect on Crime I {-}
+
+There is a controversial debate on whether and to what extent the right to carry a gun influences crime. Proponents of so-called "Carrying a Concealed Weapon" (CCW) laws argue that the deterrent effect of guns prevents crime, whereas opponents argue that ... In the following exercises you will empirically investigate this topic.
+
+To begin with consider the following estimated model $$\\widehat{{\\log(violent_i)}} = 6.135 - 0.443 \\times law_i$$, where <tt>violent</tt> and <tt>law</tt> denote the violent crime rate (incidents per $100000$ citizens) and a binary variable indicating the implementation of a CCW law (1 = yes, 0 = no), respectively.
+
+The packages <tt>AER</tt> and <tt>plm</tt> have been loaded.
+      
+**Instructions:**
+        
++ Is the proposed model a "good" model? In particular, are there variables that vary across states?
+
++ Print a summary of the model reporting robust standard errors. Analyze thr results.
+
+<iframe src="DCL/ex10_2.html" frameborder="0" scrolling="no" style="width:100%;height:340px"></iframe>
+
+**Hints:**
+
++ As usual you can use <tt>coeftest()</tt> in conjunction with appropriate arguments to obtain a summary output with robust standard errors.
+</div>')
+}
+```

10-ch10.Rmd

@@ -0,0 +1,115 @@
+<!DOCTYPE html>
+         <html>
+         <head>
+<meta charset='utf-8'/>
+<script async='async' src='https://cdn.datacamp.com/dcl-react-dev.js.gz'></script>
+<style>
+.DCexercise .datacamp-exercise {
+     border: 2px solid #3D678D;
+     border-radius: 10px 10px 10px 10px !important;
+     }
+
+     *[class*="lm_"], .ace_gutter, textarea[class*="ace_"], .ace_scroller {
+     background-color: #F0EFF0 !important;
+     }
+
+     div[class*="Editor-module__editor"], div[class*="dcl__Footer"] {
+     background-color: #3D678D !important; 
+     } 
+
+     *[class*="lm_"] {
+     border-radius: 10px 10px 0px 0px !important;
+     }
+
+     div[class*="dcl__Footer"] {
+     border-radius: 0px 0px 10px 10px !important;
+     }
+
+     .lm_content {
+     border-radius: 0px !important;
+     }
+
+     .lm_splitter {
+     background-color: #3D678D !important; 
+     width: 3px !important;
+     }
+
+     .lm_drag_handle {
+     background: transparent !important;
+     }
+
+     div[class*="dcl__index-module"] {
+     outline-color: transparent !important;
+     border-radius: 10px !important;
+     }
+
+     button[class*="secondary-light"] {
+     background-color: #FF0000;
+     }
+</style>
+         </head>
+         <body>
+         
+         <div data-datacamp-exercise data-lang="r">
+        
+  <code data-type="pre-exercise-code">
+  </code>
+  
+  <code data-type="sample-code">
+  # attach the package and load the data set
+  
+  
+  
+  # obtain an overview over the data set
+  
+  
+  # verify that Guns is a balanced panel
+  years  <- 
+  states <- 
+  
+  
+  </code>
+  
+  <code data-type="solution">
+  # attach the package and load the data set
+  library(AER)  
+  data("Guns")  
+    
+  # obtain an overview over the data set
+  summary(Guns)
+  
+  # verify that Guns is a balanced panel
+  years  <- length(levels(Guns$year))
+  states <- length(levels(Guns$state))
+  years*states == nrow(Guns)
+  
+  </code>
+  
+  <code data-type="sct">
+  ex %>% check_library("AER")
+  test_function("data")
+  test_or({
+      ex() %>% check_function("summary") %>% check_result() %>% check_equal()
+    },{
+      f <- ex() %>% override_solution("str(Guns)") 
+      f %>% check_function("str") %>% check_result() %>% check_equal()
+    })
+  ex() %>% check_object("years") %>% check_equal()
+  ex() %>% check_object("states") %>% check_equal()
+  ex() %>% check_function("nrow") %>% check_arg("x") %>% check_equal()
+  test_or({
+      test_student_typed("years*states == nrow(Guns)")
+    },{
+      test_student_typed("states*years == nrow(Guns)")
+    },{
+      test_student_typed("nrow(Guns) == years*states")
+    },{
+      test_student_typed("nrow(Guns) == states*years")
+    })
+  success_msg("Correct! Overall there are 51 states (entities) over 23 years whose product coincides with the number of total observations in the dataset.")
+  </code>
+  
+</div>
+          
+         </body>
+         </html>

DCL/ex10_1.html

@@ -0,0 +1,85 @@
+<!DOCTYPE html>
+         <html>
+         <head>
+<meta charset='utf-8'/>
+<script async='async' src='https://cdn.datacamp.com/dcl-react-dev.js.gz'></script>
+<style>
+.DCexercise .datacamp-exercise {
+     border: 2px solid #3D678D;
+     border-radius: 10px 10px 10px 10px !important;
+     }
+
+     *[class*="lm_"], .ace_gutter, textarea[class*="ace_"], .ace_scroller {
+     background-color: #F0EFF0 !important;
+     }
+
+     div[class*="Editor-module__editor"], div[class*="dcl__Footer"] {
+     background-color: #3D678D !important; 
+     } 
+
+     *[class*="lm_"] {
+     border-radius: 10px 10px 0px 0px !important;
+     }
+
+     div[class*="dcl__Footer"] {
+     border-radius: 0px 0px 10px 10px !important;
+     }
+
+     .lm_content {
+     border-radius: 0px !important;
+     }
+
+     .lm_splitter {
+     background-color: #3D678D !important; 
+     width: 3px !important;
+     }
+
+     .lm_drag_handle {
+     background: transparent !important;
+     }
+
+     div[class*="dcl__index-module"] {
+     outline-color: transparent !important;
+     border-radius: 10px !important;
+     }
+
+     button[class*="secondary-light"] {
+     background-color: #FF0000;
+     }
+</style>
+         </head>
+         <body>
+         
+ 
+<div data-datacamp-exercise data-lang="r">
+  
+  <code data-type="pre-exercise-code">
+  library(AER)
+  </code>
+  
+  <code data-type="sample-code">
+  # estimate a model with fixed state effects
+  model_fe <- 
+  
+  # print a summary using robust standard errors
+  
+  
+  </code>
+  
+  <code data-type="solution">
+  # estimate a model with fixed state effects
+  model_fe <- plm(log(violent) ~ law, data = Guns, index = c("state", "year"), model = "within")
+  
+  # print a summary using robust standard errors
+  coeftest(model_fe, vcov. = vcovHC, type = "HC1")
+  
+  </code>
+  
+  <code data-type="sct">
+  success_msg("Correct! The proposed model has two severe shortcomings: First the model does not account for variables that vary across the entities. The coefficient is surprisingly large in magnitude which is likely due to omitted variable bias.")
+  </code>
+  
+</div>
+          
+         </body>
+         </html>

DCL/ex10_2.html

@@ -25,7 +25,7 @@
 <meta name="author" content="Christoph Hanck, Martin Arnold, Alexander Gerber and Martin Schmelzer">
 
 
-<meta name="date" content="2018-10-12">
+<meta name="date" content="2018-10-30">
 
   <meta name="viewport" content="width=device-width, initial-scale=1">
   <meta name="apple-mobile-web-app-capable" content="yes">
@@ -58,15 +58,9 @@
 
 <link href="https://fonts.googleapis.com/css?family=PT+Sans|Pacifico|Source+Sans+Pro" rel="stylesheet">
 
-<!-- function to adjust height of iframes automatically depending on content loaded -->
-
-<script>
-  function resizeIframe(obj) {
-    obj.style.height = obj.contentWindow.document.body.scrollHeight + 'px';
-  }
-</script>
-
 <script src="js/hideOutput.js"></script>
+
+<!-- Mathjax -->
 <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/config/default.js"></script>
 
  <script type="text/x-mathjax-config">
@@ -277,6 +271,7 @@
 <li class="chapter" data-level="10.4" data-path="10-4-regression-with-time-fixed-effects.html"><a href="10-4-regression-with-time-fixed-effects.html"><i class="fa fa-check"></i><b>10.4</b> Regression with Time Fixed Effects</a></li>
 <li class="chapter" data-level="10.5" data-path="10-5-tferaaseffer.html"><a href="10-5-tferaaseffer.html"><i class="fa fa-check"></i><b>10.5</b> The Fixed Effects Regression Assumptions and Standard Errors for Fixed Effects Regression</a></li>
 <li class="chapter" data-level="10.6" data-path="10-6-drunk-driving-laws-and-traffic-deaths.html"><a href="10-6-drunk-driving-laws-and-traffic-deaths.html"><i class="fa fa-check"></i><b>10.6</b> Drunk Driving Laws and Traffic Deaths</a></li>
+<li class="chapter" data-level="10.7" data-path="10-7-exercises-8.html"><a href="10-7-exercises-8.html"><i class="fa fa-check"></i><b>10.7</b> Exercises</a></li>
 </ul></li>
 <li class="chapter" data-level="11" data-path="11-rwabdv.html"><a href="11-rwabdv.html"><i class="fa fa-check"></i><b>11</b> Regression with a Binary Dependent Variable</a><ul>
 <li class="chapter" data-level="11.1" data-path="11-1-binary-dependent-variables-and-the-linear-probability-model.html"><a href="11-1-binary-dependent-variables-and-the-linear-probability-model.html"><i class="fa fa-check"></i><b>11.1</b> Binary Dependent Variables and the Linear Probability Model</a></li>
@@ -286,15 +281,15 @@
 </ul></li>
 <li class="chapter" data-level="11.3" data-path="11-3-estimation-and-inference-in-the-logit-and-probit-models.html"><a href="11-3-estimation-and-inference-in-the-logit-and-probit-models.html"><i class="fa fa-check"></i><b>11.3</b> Estimation and Inference in the Logit and Probit Models</a></li>
 <li class="chapter" data-level="11.4" data-path="11-4-application-to-the-boston-hmda-data.html"><a href="11-4-application-to-the-boston-hmda-data.html"><i class="fa fa-check"></i><b>11.4</b> Application to the Boston HMDA Data</a></li>
-<li class="chapter" data-level="11.5" data-path="11-5-exercises-8.html"><a href="11-5-exercises-8.html"><i class="fa fa-check"></i><b>11.5</b> Exercises</a></li>
+<li class="chapter" data-level="11.5" data-path="11-5-exercises-9.html"><a href="11-5-exercises-9.html"><i class="fa fa-check"></i><b>11.5</b> Exercises</a></li>
 </ul></li>
 <li class="chapter" data-level="12" data-path="12-ivr.html"><a href="12-ivr.html"><i class="fa fa-check"></i><b>12</b> Instrumental Variables Regression</a><ul>
 <li class="chapter" data-level="12.1" data-path="12-1-TIVEWASRAASI.html"><a href="12-1-TIVEWASRAASI.html"><i class="fa fa-check"></i><b>12.1</b> The IV Estimator with a Single Regressor and a Single Instrument</a></li>
 <li class="chapter" data-level="12.2" data-path="12-2-TGIVRM.html"><a href="12-2-TGIVRM.html"><i class="fa fa-check"></i><b>12.2</b> The General IV Regression Model</a></li>
 <li class="chapter" data-level="12.3" data-path="12-3-civ.html"><a href="12-3-civ.html"><i class="fa fa-check"></i><b>12.3</b> Checking Instrument Validity</a></li>
 <li class="chapter" data-level="12.4" data-path="12-4-attdfc.html"><a href="12-4-attdfc.html"><i class="fa fa-check"></i><b>12.4</b> Application to the Demand for Cigarettes</a></li>
 <li class="chapter" data-level="12.5" data-path="12-5-where-do-valid-instruments-come-from.html"><a href="12-5-where-do-valid-instruments-come-from.html"><i class="fa fa-check"></i><b>12.5</b> Where Do Valid Instruments Come From?</a></li>
-<li class="chapter" data-level="12.6" data-path="12-6-exercises-9.html"><a href="12-6-exercises-9.html"><i class="fa fa-check"></i><b>12.6</b> Exercises</a></li>
+<li class="chapter" data-level="12.6" data-path="12-6-exercises-10.html"><a href="12-6-exercises-10.html"><i class="fa fa-check"></i><b>12.6</b> Exercises</a></li>
 </ul></li>
 <li class="chapter" data-level="13" data-path="13-eaqe.html"><a href="13-eaqe.html"><i class="fa fa-check"></i><b>13</b> Experiments and Quasi-Experiments</a><ul>
 <li class="chapter" data-level="13.1" data-path="13-1-potential-outcomes-causal-effects-and-idealized-experiments.html"><a href="13-1-potential-outcomes-causal-effects-and-idealized-experiments.html"><i class="fa fa-check"></i><b>13.1</b> Potential Outcomes, Causal Effects and Idealized Experiments</a></li>