Worked on Lisa's spreadsheet to convert it into a series of scripts to make the analysis job a bit easier to cross-check.
I produced not very many scripts yet, as I am still parsing her work and making a plan.
Also spent a couple of hours on extra-Isaac admin chores.
Opening a 10 MB XLSX file in LibreOffice proved a challenge. I managed to convert it to an ODS and it's a bit more manageable.
After a day of deep diving into Lisa's analysis, I resorted to ask for her help to understand some parts of it. It isn't that I don't understand what she wanted to see, it's just I can't get the same numbers she has, and the formulas in the spreadsheet as so all over the place that it takes a long time to follow the steps, as the spreadsheet is so heavy that sometimes I have to wait a whole minute just to switch tabs. Hopefully we can meet before Easter.
Had a chat with Lisa on her DfE analysis, clarified a number of things that didn't quite sound right in my attempts at replicating her spreadsheet. Discussed possible ways of testing for significance.
Lisa contacted HESA to see if they can provide student-level performance data for AS and A2 so we can look at individual trajectories of students that engaged with IP.
Started having a look at the Masterclass data. If anything, it looks like we might be able to reject out initial hypothesis in at least one group. Yay…?
Worked on TOCHI paper from PhD thesis. It's really hard not to use the word "education" when in fact you need to use it.