update renv

04-roadmap.Rmd

@@ -94,7 +94,7 @@ variance $\sigma^2$. More generally, a parametric model may be defined as
 \end{equation*}
 which describes a constrained statistical model consisting of all distributions
 $P_{\theta}$ that are indexed by some finite, $d$-dimensional parameter
-$\theta$. 
+$\theta$.
 
 The assumption that $P_0$ has a specific, parametric form is made quite
 commonly. Unfortunately, this is even the case when such assumptions are not
@@ -142,7 +142,7 @@ scientific conventions, accepted hypotheses, and operational assumptions.
 rp: This is vague. What's an example of scientific conventions, example of
 accepted hypotheses, and example of operational assumptions that would be
 incorporated in M?
---> 
+-->
 It is then the data scientist's responsibility to translate the domain knowledge
 into statistical knowledge about $P_0$, and then to define the statistical model
 $\M$ so that it respects what is known about $P_0$ and makes no further
@@ -437,11 +437,11 @@ ggdag(tidy_dag) +
 While DAGs like the above provide a convenient means by which to express the
 causal relations between variables, these same causal relations can be
 equivalently represented by an SCM:
-\begin{align*}
+$$\begin{align*}
   W &= f_W(U_W) \\
   A &= f_A(W, U_A) \\
   Y &= f_Y(W, A, U_Y),
-\end{align*}
+\end{align*}$$
 where the $f$'s are unspecified deterministic functions that generate the
 corresponding random variables as a function of the variable's "parents" (i.e.,
 upstream nodes with arrows into the given random variable) in the DAG, and the
@@ -474,17 +474,17 @@ of the outcome distribution in the population under two distinct interventions:
 These interventions may be thought of as operations that imply changes
 to the structural equations in the system under study. For the case $A = 1$, we
 have
-\begin{align*}
+$$\begin{align*}
   W &= f_W(U_W) \\
   A &= 1 \\
   Y(1) &= f_Y(W, 1, U_Y) \ ,
-\end{align*}
+\end{align*}$$
 while, for the case $A=0$,
-\begin{align*}
+$$\begin{align*}
   W &= f_W(U_W) \\
   A &= 0 \\
   Y(0) &= f_Y(W, 0, U_Y) \ .
-\end{align*}
+\end{align*}$$
 
 In these equations, $A$ is no longer a function of $W$ because the intervention
 on the system set $A$ deterministically
@@ -569,12 +569,12 @@ all four are necessary when working within the potential outcomes framework
 Under these assumptions, the ATE may be re-written as a function of $P_0$, the
 distribution of the observed data:
 
-\begin{align}
+$$\begin{align}
   \psi_{\text{ATE}} &= \E_0[Y(1) - Y(0)] \\ \nonumber
                     &= \E_0 [\E_0[Y \mid A = 1, W] -
                        \E_0[Y \mid A = 0, W]] \ .
   (\#eq:estimand)
-\end{align}
+\end{align}$$
 In words, the ATE is the mean difference in the predicted outcome values for
 each subject, under the contrast of treatment conditions ($A = 0$ versus $A =
 1$), in the population (when averaged over all observations). Thus, a parameter

dependencies.R

@@ -0,0 +1,3 @@
+library(sysfonts)
+library(rmarkdown)
+library(bookdown)

renv.lock

@@ -448,14 +448,15 @@
     },
     "bookdown": {
       "Package": "bookdown",
-      "Version": "0.34.2",
-      "Source": "GitHub",
-      "RemoteType": "github",
-      "RemoteHost": "api.github.com",
-      "RemoteUsername": "rstudio",
-      "RemoteRepo": "bookdown",
-      "RemoteRef": "main",
-      "RemoteSha": "e3cae95282f497c55864057e9e8255e2aed75120",
+      "Version": "0.40",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "RemoteType": "standard",
+      "RemotePkgRef": "bookdown",
+      "RemoteRef": "bookdown",
+      "RemoteRepos": "https://cran.rstudio.com",
+      "RemotePkgPlatform": "aarch64-apple-darwin20",
+      "RemoteSha": "0.40",
       "Requirements": [
         "R",
         "htmltools",
@@ -466,7 +467,7 @@
         "xfun",
         "yaml"
       ],
-      "Hash": "cd70ae66241b6493b5f323aea8bac6b0"
+      "Hash": "896a79478a50c78fb035a37148638f4e"
     },
     "boot": {
       "Package": "boot",
@@ -3519,6 +3520,19 @@
       "Repository": "CRAN",
       "Hash": "b227d13e29222b4574486cfcbde077fa"
     },
+    "sysfonts": {
+      "Package": "sysfonts",
+      "Version": "0.8.9",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "RemoteType": "standard",
+      "RemotePkgRef": "sysfonts",
+      "RemoteRef": "sysfonts",
+      "RemoteRepos": "https://cran.rstudio.com",
+      "RemotePkgPlatform": "aarch64-apple-darwin20",
+      "RemoteSha": "0.8.9",
+      "Hash": "7dfca1e9c5c278300b5ca6a1772072f7"
+    },
     "systemfonts": {
       "Package": "systemfonts",
       "Version": "1.1.0",