diff --git a/summary.md b/README.md
similarity index 100%
rename from summary.md
rename to README.md
diff --git a/index.html b/index.html
new file mode 100644
index 0000000..134aaf6
--- /dev/null
+++ b/index.html
@@ -0,0 +1,1050 @@
+
+
+
+
+
+ Women on Brexit in the British Election Study
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Women on Brexit in the British Election Study
Dr John Lees-Miller 22 Jul 2018
+
+
+
+
+
+
+
+
Summary: Motivation
+
+
+
Eloise identified women aged 30-55 as an important demographic in the 'squishy middle'.
+
We want to reach this demographic. It may help to understand their views and how they differ from those of the nation as a whole.
+
The British Election Study surveyed ~30k people in April-June 2016, before the Brexit vote. It asked questions about peoples' views on Brexit (among other things). (There are also more recent updates with fewer Brexit-related questions.)
+
+
+
+
+
+
+
Summary: Preliminary Results
+
+
Things that mattered most in the referendum:
+
+
+
Stronger interest in family, fairness, protection of rights
+
Weaker interest in Sovereignty / EU bureaucracy
+
+
+
In general, compared to the nation as a whole:
+
+
+
More concerned about impact of immigration on jobs
+
More concerned about security, crime and safety
+
Generally more conservative
+
Less politically engaged / interested
+
+
+
(*) Subject to many caveats…
+
+
+
+
+
+
Distribution of Respondents
+
+
+
There are many in Scotland and Wales.
+
+
+
+
+
+
+
+
+
Validation: Topics of Interest
+
+
We brainstormed some topics we think women 30-55 may more be interested in. Do the data agree?
+
+
+
Family
+
Health
+
Education
+
Jobs
+
Lifestyle, Food
+
Security, Property
+
+
+
+
+
+
+
What matters most to you when deciding how to vote in the EU referendum?
+
+
+
The survey asked this question directly.
+
It was free text, which BES coded into 15 categories.
+
What were the main reasons for the nation as a whole?
+
What reasons were more or less important for women (30-55)?
+
+
+
Run t-tests to find which differences are statistically significant (p=0.05).
+
+
+
+
+
+
+
+
For the nation as a whole
+
+
+
+
+
+
+
+
For Women 30-55 (Target)
+
+
+
+
+
+
+
+
Other Topics
+
+
+
Could not find much data on Health, Education, Lifestyle / Food
+
Did find some on Jobs and Security
+
+
+
+
+
+
+
Jobs (and Economy)
+
+
+
+
+
+
+
+
Security (and Crime)
+
+
+
+
+
+
+
+
Other
+
+
+
+
+
+
+
+
Next Steps
+
+
+
Look at regions — enough data to go to NUTS1 / NUTS2?
+
Have consituencies — enough data to comment on swing constituencies as a whole?