Merge pull request #908 from cmu-delphi/ndefries/alert-unweighted-ses

[CTIS] Add note that current SEs are unweighted

Author: krivard

docs/api/covidcast-signals/fb-survey.md

@@ -726,6 +726,13 @@ of zero, and in simulations improves the quality of the standard error
 estimates. See the [Appendix](#appendix) for further motivation for these
 estimators.
 
+<div style="background-color:#FCC; padding: 10px 30px;"><strong>Note:</strong>
+Currently the standard errors are calculated as though all survey weights are
+equal, that is \(w^\text{part}_i = 1\) for all respondents. The result is that
+reported standard errors are artificially narrow for weighted estimates. This
+will be corrected in a future update to the API.
+</div>
+
 The pseudo-observation is not used in $$\hat{p}$$ and $$\hat{q}$$ themselves, to
 avoid potentially large amounts of estimation bias, as $$p$$ and $$q$$ are
 expected to be small.
@@ -750,7 +757,7 @@ knowing someone in their community who is sick. In this subsection we will
 describe how survey weights are used to construct weighted estimates for these
 indicators, using community CLI as an example.
 
-In a given aggregation unit (for example, daily-county), let $$U_i$$ the
+In a given aggregation unit (for example, daily-county), let $$U_i$$ denote the
 indicator that the survey respondent knows someone in their community with CLI,
 including their household, for survey $$i$$, out of $$m$$ surveys collected.
 Also let $$w_i$$ be the weight that accompanies survey $$i$$, normalized to sum

docs/symptom-survey/contingency-tables.md

@@ -173,7 +173,7 @@ for download, and specifies the survey questions on which they are based. See
 the <a href="coding.html">survey instrument codebook</a> for the full text of
 all questions.</div>
 
-The files contain [weighted estimates](../api/covidcast-signals/fb-survey.md#survey-weighting)
+The files contain [weighted estimates](../api/covidcast-signals/fb-survey.md#survey-weighting-and-estimation)
 of the percent of respondents who fulfill one or several criteria. Estimates are
 broken out by state, age, gender, race, ethnicity, occupation, and health
 conditions.