diff --git a/paper/sl.tex b/paper/sl.tex index 933ee6fdd4730c419643091e76f19805e73de222..d785027e5462266655131af490ee7be76ffae5f0 100755 --- a/paper/sl.tex +++ b/paper/sl.tex @@ -210,18 +210,18 @@ Every judge's leniency rate $\leniency$ was sampled uniformly from a half-open i Private features $\features$ were defined as i.i.d standard Gaussian random variables. Next, probabilities for negative results $\outcome = 0$ were calculated as \[ -\prob{\outcome = 0| \features = \featuresValue} = \dfrac{1}{1+\exp\{-\featuresValue\}} +\prob{\outcome = 0| \features = \featuresValue} = \dfrac{1}{1+\exp\{-\featuresValue\}} = p_{y_0} \] -and consequently $\outcome \sim \text{Bernoulli}(1 - \prob{\outcome = 0| \features = \featuresValue})$. -The decision variable $\decision$ was set to 0 if the value $\prob{\outcome = 0| \features = \featuresValue}$ resided in the top $(1-\leniencyValue)\cdot 100 \%$ of the subjects appointed for that judge. +and consequently $\outcome \sim \text{Bernoulli}(1 - p_{y_0})$. +The decision variable $\decision$ was set to 0 if the value $p_{y_0}$ resided in the top $(1-\leniencyValue)\cdot 100 \%$ of the subjects appointed for that judge. Results for estimating the causal quantity $\prob{\outcome = 0 | \doop{\leniency = \leniencyValue}}$ with various levels of leniency $\leniencyValue$ are presented in Figure \ref{fig:without_unobservables}. \begin{figure} \begin{center} \includegraphics[width=\columnwidth]{img/without_unobservables.png} \end{center} -\caption{$\prob{\outcome = 0 | \doop{\leniency = \leniencyValue}}$ with varying levels of acceptance rate. Error bars denote standard error of the mean across simulations.} +\caption{$\prob{\outcome = 0 | \doop{\leniency = \leniencyValue}}$ with varying levels of acceptance rate. Error bars denote standard error of the mean.} \label{fig:without_unobservables} \end{figure}