STUDENTS: REGISTER TO VOTE RIGHT NOW! The law is as follows. 1. You can register at home AND at your term-time address, if that's more convenient for you. 2. You can CHOOSE on the day where to vote. 3. But you can ONLY legally vote in ONE place on the day.

Do you need to apply multilevel modelling in your research? This two week online course introduces you to a range of basic and advanced multilevel techniques using MLwiN or R. Find out more about the course➡️ bit.ly/4bmbx4B #ESS2024

Last call for this training event I'm running (in person in Sheffield) in a couple of weeks: intersectionalhealth.org/an-introductio…

This is amazing by Peter Inglesby, comparing MRP projections for each seat inglesp.github.io/apogee/ HT Sam Freedman

Hello everyone, less than 48 hours until the polls open... This morning I've added a "coefficient of correlation" to the aggregator, to indicate how much the models agree or disagree in each seat:

If I could give epi students one piece of advice, it's to ~*look*~ at your data. Like actually look at individual observations before you dive into coding anything.

Exit poll seats by liklihood: 80%+ Lab 369 80%+ Con 80 80%+ LD 45 80%+ Reform 5 80%+ SNP 4 80%+ PC 3 80%+ Green 2 Too close to call 124 seats

A great paper that reveals a big source of measurement error yet also tells you a key to happiness: When happy interviewers are gathering data on well-being, they accidentally cheer up their subjects leading to higher reported happiness, compared with a less happy interviewer.

It was great being one of the keynotes at the European Society of Health and Medical Sociology conference, talking about intersectionality and MAIHDA. Thanks for inviting me - was a lovely friendly conference!

IV papers are pretty much all mining noise for stars. Delete one observation and 37% become insig. Delete 2 and 57% become insig. Concerns about generalizing to the real world are overblown, most results don't even generalize to their sample. sciencedirect.com/science/articl…

Out now open access at AJPS. 194 potential exclusion-restriction violations for studies using weather as an instrumental variable onlinelibrary.wiley.com/doi/full/10.11…

Keen to hear from anyone out there who has had issues getting a mortgage (or remortgage) using PhD stipend income! Feel free to DM me. Recently been learning more about mortgage providers' bonkers policies 🤯 Keen to build the evidence base on this & #EndTheNerdPenalty ! 🤓

Ever wanted to know how *not* to study effects of the family environment? Read all about it! academic.oup.com/esr/advance-ar…

It took me a second to read the map correctly. Very cool! What’s the range of the world’s tides? Source: buff.ly/3BVylfq

Here is a remarkable demonstration of how much a pollster's choices affect the results. Joshua Clinton took a single poll and depending on the weighting scheme, he could change the Harris-Trump margin by as much as *8 points*. goodauthority.org/news/election-…

George Leckie and I have created a new short MAIHDA tutorial, with videos and practical exercises: ncrm.ac.uk/resources/onli… It's based on our tutorial paper in SSM Pop Health Soc Sci & Medicine, but shorter and more interactive. Hope it's helpful! NCRM