Blog copyedits

content/blog/2020-09-21-forecast-demo.Rmd

@@ -18,11 +18,11 @@ summary: |
   % CLI-in-community indicators from our two surveys can be used to improve 
   the accuracy of short-term forecasts of county-level COVID-19 case rates.
 acknowledgements: |
-  *Delphi's forecasting effort involves many people from our
+  Delphi's forecasting effort involves many people from our
   modeling team, from forecaster design, to implementation, to evaluation. The 
   broader insights on forecasting shared in this post certainly cannot be
   attributable to Ryan's work alone, and are a reflection of the work carried out 
-  by all these team members.*
+  by all these team members.
 related:
   - 2020-09-18-google-survey
   - 2020-08-26-fb-survey
@@ -60,7 +60,7 @@ forecasts](https://www.cdc.gov/coronavirus/2019-ncov/covid-data/mathematical-mod
 
 At the outset, we should state that this post is neither a report on Delphi's
 current COVID-19 forecasters nor an authoritative take on cutting-edge
-COVID-19 forecasting. Instead, our purpose here to study the Facebook and
+COVID-19 forecasting. Instead, our purpose here is to study the Facebook and 
 Google % CLI-in-community signals, and demonstrate their value, when used as
 features, to add predictive power beyond what we can achieve with (fairly
 simple) time series models trained on case rates alone. In a future blog post,
@@ -473,9 +473,7 @@ ggplot(res_dif2 %>%
   theme_bw() + theme(legend.pos = "none")
 ```
 
-## Varying the Number of Days Ahead\*
-
-**[\*Added September 25, 2020]**
+## Varying the Number of Days Ahead
 
 Hypothesis tests (like the sign tests conducted above) tell us
 whether the differences in errors
@@ -638,3 +636,6 @@ We look forward to seeing how you put our data to use!
     even fairly complicated ones. Being statisticians and computer scientists, we
     find these statistical models are easier to build, debug, and most importantly,
     calibrate. More on this in a future blog post.
+
+**Note:** *This post was updated on September 25, 2020 to include the section 
+ [Varying the Number of Days Ahead](#varying-the-number-of-days-ahead).*

content/blog/2020-09-21-forecast-demo.html

@@ -18,11 +18,11 @@
   % CLI-in-community indicators from our two surveys can be used to improve 
   the accuracy of short-term forecasts of county-level COVID-19 case rates.
 acknowledgements: |
-  *Delphi's forecasting effort involves many people from our
+  Delphi's forecasting effort involves many people from our
   modeling team, from forecaster design, to implementation, to evaluation. The 
   broader insights on forecasting shared in this post certainly cannot be
   attributable to Ryan's work alone, and are a reflection of the work carried out 
-  by all these team members.*
+  by all these team members.
 related:
   - 2020-09-18-google-survey
   - 2020-08-26-fb-survey
@@ -44,7 +44,7 @@
 <li><a href="#forecasting-code">Forecasting Code</a></li>
 <li><a href="#results-all-four-models">Results: All Four Models</a></li>
 <li><a href="#results-first-two-models">Results: First Two Models</a></li>
-<li><a href="#varying-the-number-of-days-ahead">Varying the Number of Days Ahead*</a></li>
+<li><a href="#varying-the-number-of-days-ahead">Varying the Number of Days Ahead</a></li>
 <li><a href="#wrap-up">Wrap-Up</a></li>
 </ul>
 </div>
@@ -74,7 +74,7 @@
 forecasts</a>.</p>
 <p>At the outset, we should state that this post is neither a report on Delphi’s
 current COVID-19 forecasters nor an authoritative take on cutting-edge
-COVID-19 forecasting. Instead, our purpose here to study the Facebook and
+COVID-19 forecasting. Instead, our purpose here is to study the Facebook and
 Google % CLI-in-community signals, and demonstrate their value, when used as
 features, to add predictive power beyond what we can achieve with (fairly
 simple) time series models trained on case rates alone. In a future blog post,
@@ -881,8 +881,7 @@ <h2>Results: First Two Models</h2>
 <p><img src="/blog/2020-09-21-forecast-demo_files/figure-html/unnamed-chunk-8-1.svg" width="672" /></p>
 </div>
 <div id="varying-the-number-of-days-ahead" class="section level2">
-<h2>Varying the Number of Days Ahead*</h2>
-<p><strong>[*Added September 25, 2020]</strong></p>
+<h2>Varying the Number of Days Ahead</h2>
 <p>Hypothesis tests (like the sign tests conducted above) tell us
 whether the differences in errors
 (between the forecasters)
@@ -1022,6 +1021,8 @@ <h2>Wrap-Up</h2>
 the Challenge</a>, and
 submissions are due September 29, with finalists eligible for cash prizes.
 We look forward to seeing how you put our data to use!</p>
+<p><strong>Note:</strong> <em>This post was updated on September 25, 2020 to include the section
+<a href="#varying-the-number-of-days-ahead">Varying the Number of Days Ahead</a>.</em></p>
 </div>
 <div class="footnotes">
 <hr />

content/blog/2020-10-14-dv-signal.Rmd

@@ -104,7 +104,7 @@ p1 = plot(df_dv_avg,
           range = c(0, 15), choro_params = list(subtitle = subtitle))
 p2 = plot(df_in_avg,
           title = "Daily new confirmed COVID-19 cases per 100,000 people",
-          range = c(0, 30), choro_params = list(subtitle = subtitle))
+          range = c(0, 25), choro_params = list(subtitle = subtitle))
 grid.arrange(p1, p2, nrow = 1)
 ```
 

content/blog/2020-10-14-dv-signal.html

@@ -103,7 +103,7 @@ <h2>The Doctor Visits Indicator</h2>
           range = c(0, 15), choro_params = list(subtitle = subtitle))
 p2 = plot(df_in_avg,
           title = &quot;Daily new confirmed COVID-19 cases per 100,000 people&quot;,
-          range = c(0, 30), choro_params = list(subtitle = subtitle))
+          range = c(0, 25), choro_params = list(subtitle = subtitle))
 grid.arrange(p1, p2, nrow = 1)</code></pre>
 <p><img src="/blog/2020-10-14-dv-signal_files/figure-html/unnamed-chunk-2-1.svg" width="960" class="wide-figure" /></p>
 </div>

content/blog/2020-12-10-masks-public.Rmd

@@ -12,9 +12,10 @@ heroImage: /blog/images/masks-public-full-size.jpg
 heroImageThumb: /blog/images/masks-public-thumb.jpg
 related:
 - 2020-10-06-survey-wave-4
-acknowledgements: Wichada La Motte-Kerr drafted numerous survey revisions, collected input from experts, and manageed the process of deploying the new survey questions. Sarah LaRocca and Katherine Morris at Facebook gave important input and helped deploy the survey. Kathryn Mazaitis assisted in producing the new aggregate survey data.
 summary: |
   Delphi's symptom surveys reveal rates of mask use across the country. But do they really show that the vast majority of people wear masks?
+acknowledgements: |
+  Wichada La Motte-Kerr drafted numerous survey revisions, collected input from experts, and manageed the process of deploying the new survey questions. Sarah LaRocca and Katherine Morris at Facebook gave important input and helped deploy the survey. Kathryn Mazaitis assisted in producing the new aggregate survey data.
 output:
   blogdown::html_page:
     toc: true

content/blog/2020-12-10-masks-public.html

@@ -12,14 +12,16 @@
 heroImageThumb: /blog/images/masks-public-thumb.jpg
 related:
 - 2020-10-06-survey-wave-4
-acknowledgements: Wichada La Motte-Kerr drafted numerous survey revisions, collected input from experts, and manageed the process of deploying the new survey questions. Sarah LaRocca and Katherine Morris at Facebook gave important input and helped deploy the survey. Kathryn Mazaitis assisted in producing the new aggregate survey data.
 summary: |
   Delphi's symptom surveys reveal rates of mask use across the country. But do they really show that the vast majority of people wear masks?
+acknowledgements: |
+  Wichada La Motte-Kerr drafted numerous survey revisions, collected input from experts, and manageed the process of deploying the new survey questions. Sarah LaRocca and Katherine Morris at Facebook gave important input and helped deploy the survey. Kathryn Mazaitis assisted in producing the new aggregate survey data.
 output:
   blogdown::html_page:
     toc: true
 ---
 
+<script src="/rmarkdown-libs/header-attrs/header-attrs.js"></script>
 <link href="/rmarkdown-libs/anchor-sections/anchor-sections.css" rel="stylesheet" />
 <script src="/rmarkdown-libs/anchor-sections/anchor-sections.js"></script>