library(knitr)
library(ggplot2)
library(data.table)
+library(icons)
+
f <- function (x) {formatC(x, format="d", big.mark=',')}
theme_set(theme_bw())
<img src="images/nu_logo.png" height="170px" style="padding:21px"/> <img src="images/uw_logo.png" height="170px" style="padding:21px"/> <img src="images/cdsc_logo.png" height="170px" style="padding:21px"/>
-nathan.teblunthuis@northwestern.edu
+`r icons::fontawesome('envelope')` nathan.teblunthuis@northwestern.edu
-[https://teblunthuis.cc](https://teblunthuis.cc)
+`r icons::fontawesome('globe')` [https://teblunthuis.cc](https://teblunthuis.cc)
???
I've run simulations to test these approaches in several scenarios.
+I simulate random data, fit 100 models and plot the average estimate and its variance.
+
The model is not very good: about 70% accurate.
Most plausible scenario:
Link to a messy git repository:[https://code.communitydata.science/ml_measurement_error_public.git](https://code.communitydata.science/ml_measurement_error_public.git)
-<i class="fa fa-envelope" aria-hidden='true'></i> nathan.teblunthuis@northwestern.edu
+`r icons::fontawesome("envelope")` nathan.teblunthuis@northwestern.edu
-<i class="fa fa-twitter" aria-hidden='true'></i> @groceryheist
+`r icons::fontawesome("twitter")` @groceryheist
-<i class="fa fa-globe" aria-hidden='true'></i> [https://communitydata.science](https://communitydata.science)
+`r icons::fontawesome("globe")` [https://communitydata.science](https://communitydata.science)