Andi Fugard
LightNews LightNews
banner
andifugard.info
Andi Fugard
@andifugard.info
1.2K followers 900 following 17 posts
Social policy evaluator. London-based, Belfast-born. They/them. Personal account – views mine. Posts auto delete after a month.

Mastodon: https://sciences.social/@andi
Web: https://andifugard.info/
DM: https://andifugard.info/contact/
Posts Replies Media Videos
andifugard.info
Star Trek II: The Wrath of Khan. Took years to process the mind control earwig scene 😬
sophianyx.bsky.social Sophia_Nyx 🏳️‍⚧️ @sophianyx.bsky.social · 23h
Name 1 movie from your childhood you were way too young to watch.
December 29, 2025 at 12:29 PM
Reposted by Andi Fugard
irisvanrooij.bsky.social
I saw an academic unironically suggest that instead of assessing students’ understanding and competence through their writing of essays, arguments etc., we can assess the “quality” of their prompts, and I feel us slipping further and further into dystopia.
December 28, 2025 at 8:48 PM
Reposted by Andi Fugard
statsepi.bsky.social
‪It has a name now 😜

Many thanks to Ken for agreeing to put his good name to my...artwork. The image is in the public domain (CC 0), but citations to the linked documents are warmly welcomed.

✅ zenodo.org/records/1808...

✅ pubmed.ncbi.nlm.nih.gov/24452418/
Figure 1: The Rothman-Dahly Evidence Pyramid (original version) An equilateral triangle with a small blue section labelled "Thoughtful, well-conducted studies of any design" at the top, with the remaining space colored red and labelled "The other shit"
December 29, 2025 at 11:19 AM
Reposted by Andi Fugard
evalexpl.bsky.social
"Theories of change are theories – of change. They may be illustrated using a diagram, but there needs to be an explanation, usually using prose, describing how the resources, entities (e.g., people, organisations, laws, etc.), & activities carried out lead to outputs and outcomes." #Evaluation #ToC
andifugard.info Andi Fugard @andifugard.info · 8d
Policy #evaluation inherits concepts from multiple disciplines, and somewhere along the way many of them have become muddled. This blog post sketches what I think are seven of the most irritating myths.
andifugard.info/seven-persis...
Seven persistent myths about evaluation – Andi Fugard (∧⇒)
andifugard.info
December 27, 2025 at 10:09 AM
andifugard.info
“[…] the most reckless and treacherous of all theorists is he who professes to let facts and figures speak for themselves, who keeps in the background the part he has played, perhaps unconsciously, in selecting and grouping them […]”

– Alfred Marshall (1885). Reprint: doi.org/10.1017/S174...
‘The present position of economics’ by Alfred Marshall | Journal of Institutional Economics | Cambridge Core
‘The present position of economics’ by Alfred Marshall - Volume 1 Issue 1
doi.org
December 26, 2025 at 12:43 AM
andifugard.info
MERRY CHRISTMAS
Yours truly and partner on a terrifying rollercoaster
December 25, 2025 at 12:23 PM
andifugard.info
Policy #evaluation inherits concepts from multiple disciplines, and somewhere along the way many of them have become muddled. This blog post sketches what I think are seven of the most irritating myths.
andifugard.info/seven-persis...
Seven persistent myths about evaluation – Andi Fugard (∧⇒)
andifugard.info
December 21, 2025 at 10:51 AM
Reposted by Andi Fugard
andrew.heiss.phd
here’s a free version:

neat_research_panel <- data.frame(
id = 1:100,
treatment = sample(c(TRUE, FALSE), 100, replace = TRUE),
outcome = rnorm(100, mean = 50, sd = 5)
)
sabrinanorwood.bsky.social Sabrina Norwood @sabrinanorwood.bsky.social · 13d
Did you know that from tomorrow, Qualtrics is offering synthetic panels (AI-generated participants)?

Follow me down a rabbit hole I'm calling "doing science is tough and I'm so busy, can't we just make up participants?"
Text reads: About synthetic panels Recruiting the right participants for a study can be difficult. You may not get the exact demographics you need, and the shorter the deadline, the less sure you can be that everyone will answer on time. One possible solution can be to use synthetic panels. Synthetic panels are powered by a first party proprietary AI model developed here at Qualtrics. Our synthetic panel is trained on thousands of responses from a variety of demographic backgrounds in order to more accurately predict how certain populations would respond to a survey. Our synthetic panel is based on the United States General Population, and is only available in English. This panel comes with ready-made quotas and target breakouts in order to represent your chosen population and make it easy to launch your survey right away. Text reads: Question-writing best practices To get the most reliable and actionable results from synthetic audiences, consider these question-writing best practices: Ask forward-looking and attitudinal questions. Synthetic panels perform best with perceptions, preferences, and intent-based questions. For example, “How likely are you to try…?” Synthetic panels are less applicable for studies on past behaviors, detailed recall, brand recall, or awareness questions. For example, “When did you last visit…?” Text reads: Discussion The current study aimed to conduct a meta-analysis of the TPB when applied to health behaviours which addressed the limitations of previous reviews by including only prospective tests of behaviour, applying RE meta-analytic procedures, correcting correlations for sampling and measurement error, and hierarchically analysing the effect of behaviour type and sample and methodological moderators. Some 237 tests were identified which examined relations amongst model components. Overall the analysis indicated that the TPB could explain 19.3% of the variance in behaviour and 44.3% of the variance in intention across studies. This level of prediction of behaviour is slightly lower than that of previous meta-analytic reviews which have found between 27% (Armitage & Conner, 2001; Hagger et al., 2002) and 36% (Trafimow et al., 2002) of the variance in behaviour to be explained by intention and PBC.
December 16, 2025 at 6:46 PM
andifugard.info
Completed Day 8 of #AdventOfCode in #RStats ‐ fav so far. Skipped part 2 of Day 7. Let's see if I have time for any more! 'Tis busy season!

github.com/InductiveSte...
GitHub - InductiveStep/aoc2025: Advent of Code 2025
Advent of Code 2025. Contribute to InductiveStep/aoc2025 development by creating an account on GitHub.
github.com
December 10, 2025 at 1:10 PM
Reposted by Andi Fugard
annaalexandrova.bsky.social
The central place of the bogeyman ‘positivism’ in how social scientists caricature each other’s work is nicely captured here by @adrianblau.bsky.social www.cambridge.org/core/journal...
Social Science and Its Critics: An Ideological Analysis | Social Philosophy and Policy | Cambridge Core
Social Science and Its Critics: An Ideological Analysis - Volume 41 Issue 1
www.cambridge.org
December 6, 2025 at 10:29 AM
Reposted by Andi Fugard
annaalexandrova.bsky.social
Whether or not the concerns expressed in this paper are legitimate, the way ‘positivism’ became somehow both meaningless and pejorative is not good.
markrubin.bsky.social Mark Rubin @markrubin.bsky.social · 23d
They do: "A perspective associated with the scientific method which seeks true knowledge about objective reality (Braun & Clarke, 2022a: p.292)."
‘Positivism’ refers broadly to the philosophical approach that emphasises the use of observable, empirical evidence and scientific methods to uncover objective truths about the world that can be refuted (Popper, 2002). Popper’s critique of positivism lay in its concept of true knowledge as that which could be empirically verified, however for our purposes, we define it more broadly as a perspective associated with the scientific method which seeks true knowledge about objective reality (Braun & Clarke, 2022a: p.292).
December 6, 2025 at 8:53 AM
andifugard.info
Day 6 #AdventOfCode was a lot easier #RStats

I'm curious to see whether/how people avoided loops.

github.com/InductiveSte...
GitHub - InductiveStep/aoc2025: Advent of Code 2025
Advent of Code 2025. Contribute to InductiveStep/aoc2025 development by creating an account on GitHub.
github.com
December 6, 2025 at 11:37 AM
andifugard.info
Day 5 #AdventOfCode done in #RStats

Used {gmp} when I probably only wanted options(scipen=999). Ah well 🙃

github.com/InductiveSte...
GitHub - InductiveStep/aoc2025: Advent of Code 2025
Advent of Code 2025. Contribute to InductiveStep/aoc2025 development by creating an account on GitHub.
github.com
December 5, 2025 at 11:50 PM
andifugard.info
Didn't have much time this eve but Day 4 #AdventOfCode is complete, if slow (10 mins to run). I think the trick is to know when brute-ish force is good enough and just move onto the next day. #RStats
github.com/InductiveSte...
GitHub - InductiveStep/aoc2025: Advent of Code 2025
Advent of Code 2025. Contribute to InductiveStep/aoc2025 development by creating an account on GitHub.
github.com
December 5, 2025 at 12:14 AM
andifugard.info
Lunchtime fun: I've completed "Lobby" - Day 3 - Advent of Code 2025 #AdventOfCode in #RStats, with the help of recursion and the {gmp} package for big integers. Good fun 🤓

Answers to date here: github.com/InductiveSte...
GitHub - InductiveStep/aoc2025: Advent of Code 2025
Advent of Code 2025. Contribute to InductiveStep/aoc2025 development by creating an account on GitHub.
github.com
December 3, 2025 at 1:47 PM
Reposted by Andi Fugard
mattansb.msbstats.info
Logistic regression with 5 million observations.

glm() - about 2 hours

glm(start = ) - less than 2 minutes.

Almost feels too good...

#rstats
December 3, 2025 at 8:12 AM
Reposted by Andi Fugard
jdportes.bsky.social
Reminder that when the Times had similar worries about Reform, its response was to give Farage this advice on implementation:

"Removing a city’s worth of people would be an extended exercise. Identity cards would be a must if the population was to be sieved into legitimate and illegitimate camps"
December 2, 2025 at 1:56 PM
andifugard.info
I'm doing #AdventOfCode again - until I run out of time - using #RStats, of course. Aiming for O(finishes by Christmas day) worst case time complexity.

First two solutions (and beyond, if/when I do them) yonder: github.com/InductiveSte...
GitHub - InductiveStep/aoc2025: Advent of Code 2025
Advent of Code 2025. Contribute to InductiveStep/aoc2025 development by creating an account on GitHub.
github.com
December 2, 2025 at 8:14 PM
Reposted by Andi Fugard
tslumley.bsky.social
For the avoidance of doubt: does svyglm() use robust standard errors? Yes!
notstatschat.rbind.io/2025/12/01/d...
Does svyglm use robust standard errors? - Biased and Inefficient
notstatschat.rbind.io
December 1, 2025 at 7:20 AM
Reposted by Andi Fugard
datavisfriendly.bsky.social
#rstats
It is with profound sadness I heard that my long-time friend and colleague, John Fox passed away this week.
He was the author of {car}, {effects}, {Rcmdr}, ... and numerous influential books. I will miss him greatly.
www.john-fox.ca
John Fox: Books and Software
www.john-fox.ca
November 28, 2025 at 3:26 PM
Reposted by Andi Fugard
dingdingpeng.the100.ci
This year explaining regression to the mean took forever but I’m sure next year will be better.
November 28, 2025 at 10:25 AM