#psychometrics — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #psychometrics, aggregated by home.social.
-
I love item response theory.
#psychometrics
#rstats -
The MOSAIC study addresses that the @who.int #HealthyAgeing concept "psychological capacity" lacks clear conceptualisation:
https://science-health.csu.edu.au/research/psychological-capacity-in-older-people/_recache
#IntrinsicCapacity #HRQLThe project has now published the definition and conceptual framework resulting from discussions in the International Working Group, which is now being further refined in a #Delphi study
https://www.sciencedirect.com/science/article/pii/S1279770726002022?via%3Dihub -
Got an early train from Balmossie. It felt a bit like a certain movie.
#BaileMosaidh #SpiritedAwayOff for the day to Glasgow for the workshop
"What’s a difference that matters? Establishing patient-focused “good enough” margins”
organised by Beatriz Goulao.
#Glaschu #Psychometrics #PatientCentered -
Psychology has instruments for meaning, for isolation, for the fear of being finite. They are not interchangeable.
Steger et al. (2006) on meaning. Weems et al. (2004) on Tillich's three domains of existential anxiety. Van Pachterbeke et al. (2012) on existential quest, without the religiosity constraint.
Fifteen papers, each with a verdict.
readmarginalia.com/collections/measuring-the-unmeasurable-psychometric-tools-for-existential-concerns
-
Your AI Doesn’t Have a Personality (But a Crowd of Them Does)
Been doing some research on AI and personality. Check it out.
https://ataary.com/your-ai-doesnt-have-a-personality-but-a-crowd-of-them-does/
-
Our latest study on work addiction has now been published in the journal Assessment. Congratulations to Stephanie Towch and thanks to Dr. Paweł Atroszko for the collaboration!
Full study available from here: https://doi.org/10.1177/10731911261447068
-
RE: https://mastodon.social/@jrboehnke/115258021970867970
Message from jobs.ac.uk
"Hi Jan,
There have been no new jobs matching search your chosen criteria within the last 3 months."Alert criteria
#Psychometric OR
#Psychometrics OR
#PsychologicalAssessment
in #ScotlandI am not sure how many years ago I set the alert up, but this is the only advert I ever received through it.
-
New Jamovi module functionality to determine appropriate model fit cutoffs for confirmatory factor analysis now available in easyRasch2jmv v0.4.0. Install/update from Jamovi Library within the app.
-
I've made a Jamovi module for modern psychometric analysis using Rasch Measurement Theory, "easyRasch2jmv", that is available in Jamovi's library. The module implements simulation-based (dynamic) cutoff values for conditional item fit and residual correlations, amongst other things. #psychometrics
The "easyRasch2jmv" module currently contains only 5 of the functions from my package. I prioritized these functions to enable analysis of the 4 basic psychometric criteria:
- unidimensionality
- local independence of items
- ordered response category thresholds (monotonicity)
- invariance (no DIF)Afaik, simulation-based cutoffs for Rasch model fit metrics is not available in any other software, except my github-only R-package easyRasch. Some more details on the topic: https://pgmj.github.io/rasch_itemfit/ and https://pgmj.github.io/simcutoffs.html
If you are new to Rasch psychometrics, you will find a fair amount of resources and analysis examples here:
https://pgmj.github.io/raschrvignette/RaschRvign.htmlThis module is built using R packages such as eRm, mirt, and iarm.
-
The 2025 Trevor Levere Best Paper Prize goes to the team of the paper "The drop and the metric system: how an unruly unit survived revolutions"
https://www.tandfonline.com/doi/full/10.1080/00033790.2026.2636886This is really great news and is for an excellent paper that I highly recommend reading!
Working myself in an area that has at best non-standard measurement units (at worst, some people would argue, is not measurement at all), I found this very interesting.
-
Join today's free webinar about "moral measurement"! I'm talking #psychometrics and data quality in the era of online experiments and AI. I review two problems, two solutions, and two resources.
Register at https://ssri.psu.edu/news/moral-measures-workshop-be-held-march-23
Thanks to Penn State for hosting!
-
Pluralistic: Daily links from Cory Doctorow – No trackers, no ads. Black type, white background. Privacy policy: we don't collect or retain any data at all ever period. [Unofficial] @[email protected] ·Pluralistic: Love of corporate bullshit is correlated with bad judgment (19 Mar 2026)
https://web.brid.gy/r/https://pluralistic.net/2026/03/19/jargon-watch/
-
This paper suggests that the #HoNOS has limited utility for capturing psychopathology or monitoring progress in forensic outpatient settings
https://www.tandfonline.com/doi/full/10.1080/24732850.2026.2636142
Some items differentiated btw diagnostic groups, but limited evidence for use of 1 (to 3) summary scoresI admit having limited love for the instrument since our work on its use in secondary #MentalHealth care https://link.springer.com/article/10.1007/s10488-019-00958-7
More details, CHE working paper 137, pdf
https://www.york.ac.uk/media/che/documents/papers/researchpapers/CHERP137_mental_health_data_episodic_payment.pdf -
Beaufort’s Wind Scale makes me want to add Likert levels.
Rate your agreement with “…”:
⚪️ slightly agree
⚪️ moderately agree
⚪️ FRESH agree
⚪️ strongly agree
⚪️ GALE FORCE agree
⚪️ VIOLENTLY agree
🔘 HURRICANE Agree -
Just came across this blast from the past (2013):
https://rdcu.be/e7TDY
- daily assessments
- ordinal data multilevel #measurement
- DIF analysisCouched as a preliminary investigation and pilot study, the analytic approach still sets a bar reached rarely by studies with such data.
-
#jobs #stellenangebote #GESISjobs #psychometrics #Doctoralstudent
Pursue your scientific career at GESIS!
https://youtu.be/zMY2zqYFIMgWe offer a job as a Research Associate (Doctoral student) focus on psychometrics
(Salary group 13 TV-L, working time 75 %, limited to 4 years):https://gesis.jobs.personio.de/job/2560025?language=de&display=en
-
RE: https://flipboard.com/@wsj/business-b1985f4jz/-/a-T6_YAnIFSTSuzZdNlac-EA%3Aa%3A248213600-%2F0
“Instead of paying humans to join focus groups and complete surveys, #Auru uses thousands of #AI agents, or bots, to simulate human responses. It feeds #demographic and psychographic information into its models to create human profiles that match clients’ needs, and the results those bots spit out are being used for product #development, #pricing, identifying new customers and political #polling.”
Researchers have warned about the inaccuracies of treating #LLMs as human proxies (https://doi.org/10.1007/s10462-025-11297-5), but I wouldn’t be surprised #languageModels beat #qualitative interpretation of non-representative focus groups.
#marketing #psychometrics #statistics #quantMethods #philSci #metascience #business
-
A #SysReview exploring impacts of community-based interventions for adults with #multimorbidity on clinical and patient-reported outcomes (25 studies):
https://bmjpublichealth.bmj.com/content/4/1/e004156Quick comparison of identified outcomes with the two central #CoreOutcomeSets 👇
-
Having seen many (and done some) of these proof-of-concept studies myself, let's me wonder:
Are there still too few well-developed systems available?
Maybe someone reads this and feels we can get a collection of these together so that others can read up on them?
-
A recent post the @Mental_Elf picks up and explains a study on computerized adaptive testing, which is quite cool!
https://www.nationalelfservice.net/treatment/digital-health/measuring-paranoid-beliefs-can-adaptive-testing-support-routine-clinical-care/Psychometricians, what is your favourite application or study in the field of computerized adaptive testing with health-related constructs?
-
Interesting paper about the impact of missed cases on the accuracy of screening tools, likely of interest beyond autism research and practice communities.
I enjoyed in particular, that "[t]he strengths and benefits of blending epidemiology and psychometric perspectives to identify screening tools that are weaker than expected are discussed."
-
Upcoming event at the Institute for #MedicalHumanities in Durham, UK:
#Measurement Heretics Workshop
Being, Meaning, and Measuring Well
https://www.durham.ac.uk/research/institutes-and-centres/medical-humanities/events/measurement-heretics-workshop-being-meaning-and-measuring-well/
11.-13.03.2026Day 1 #hybrid keynote:
A fluid history of measurement: The drop in the metric revolution
Armel Cornu and Sarah Hijmans
[Day2-3 in-person] -
Quality Assessment of Diagnostic Test Accuracy Studies
QUADAS-3 published:
https://pubmed.ncbi.nlm.nih.gov/41698208/__Key changes from QUADAS-2__
introduction of an 'ideal test accuracy trial'
assessment at the estimate rather than study level
"Flow and Timing" domain replaced with an "Analysis" domain
sections on the rationale for judgments
introduction of a judgment of #RiskOfBias and concerns regarding applicability
-
I have made an R package for test equating using the Leunbach method. Thanks to the gracious sharing of DIGRAM source code by Svend Kreiner and some assistance of Claude Opus 4.5, the package `leunbachR` is now available on GitHub: https://pgmj.github.io/leunbachR/
#rstats #psychometrics -
Great to see @hudsongolino.bsky.social presenting on AI-GENIE at #ISOQOL
Firstly, the community hears and uses the words "the #PrePrint is out" too rarely, and here it is:
https://osf.io/preprints/psyarxiv/fgbj4_v2Second, it is great to see the strong theoretical underpinnings of exploratory graph analysis making their way into promising applications
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0174035 -
Brittany Lapin and I edited* the joint publication of the PRISMA-COSMIN guidelines for Outcome Measurement Instruments 2024 in four journals last year:
https://pubmed.ncbi.nlm.nih.gov/38980635/It is great to see that this is now also accompanied by table templates for communication of results
https://link.springer.com/article/10.1007/s11136-025-04058-y#NightshiftEditor #ReportingGuidelines #AcademicPublishing #SysReview #Psychometrics
* https://osf.io/preprints/osf/ukw93_v1 -
Brittany Lapin and I edited* the joint publication of the PRISMA-COSMIN guidelines for Outcome Measurement Instruments 2024 in four journals last year:
https://pubmed.ncbi.nlm.nih.gov/38980635/It is great to see that this is now also accompanied by table templates for communication of results
https://link.springer.com/article/10.1007/s11136-025-04058-y#NightshiftEditor #ReportingGuidelines #AcademicPublishing #SysReview #Psychometrics
* https://osf.io/preprints/osf/ukw93_v1 -
New #AcademicYear - New #introduction
I am a researcher at #DundeeUni and interested in health-related quality of life
#HRQoL #PsychometricsI teach #ResearchMethodology and #ResearchMethods with a focus on #Quantitative methods.
I worked for 7yrs as a #NightshiftEditor and I am still mulling over roles in and sense of #AcademicPublishing
This is mainly a work account, but I also post #Dundee stuff such as #DunDeCofaidh and occasional #Deutsch #Svenska #Gaidhlig (👉 pure work account at BSky)
-
Roughly 2 weeks left to submit to JPRO's #SpecialIssue
"Patient and Public Involvement and Engagement"
https://www.springeropen.com/collections/PPIE
#PPIEThe aim is to capture the use of Patient and Public Involvement and Engagement (#PPIE) in Patient-Reported Outcome-related research, such as the development of PRO measures and electronic PRO (ePRO) systems, as well as the implementation of PRO measures for healthcare research and clinical practice.
-
I was informally (mis)diagnosed as "probably psychopathic" by my supervisor when I did my Social Psychology postgraduate at the University of Leicester psychiatric teaching hospital back in 1989. Now I realise that I was really diagnosed with adult autism by a psychologist who didn't have the tools to differentiate.
It's interesting because it started me on my path to computerising the psychiatric investigation part of the DSM (well, initially Hare PCL) evaluation for my Master's degree. The psychometric question-and-answer model and demo I came up with had me firmly psychopathic in PCL's diagnostic terms, whereas these days it would be easily diagnosed as autism.
I went on to expand the idea from psychometrics, to behaviour analysis in virtual worlds, which I figured would be a better capture than psychometric questions - Would the person co-operate to attain a goal, would they show altruism, would they be quick to anger - There's a lot you can measure in the virtual world as we know very well now, but didn't in 1991. Sadly, the lack of modern technology and the need to feed myself brought this PhD to an end without a write-up - But it's no wonder I ended up working for OkCupid, I guess :D
The sad thing about that is that although it didn't impact my life at all, other than having an interesting topic to discuss at parties, the PCL is used as a tool by US prisons in their parole calculations. A PCL diagnosis is a heavy weighting against parole, even though Hare himself has said that isn't the way this should be used. I dread to think how many autistic people are stuck in prisons for evermore because of misdiagnosed psychopathy.
The psychopathy test puts a lot more emphasis on masking and social interactions than on kidnapping people and putting them in wells to skin them later, I feel.
I can't be bothered to write a blog post about this, so I will scream into the #Mastodon #Void instead - Except now I have to think of some other #Hashtags which is always the hard part, I get carried away, autism you see!
#Medicine #Psychology #Psychiatry #MentalHealth #Education #Diagnosis #Psychopathy #HarePCL #DSM #Psychometrics #Statistics #Autism #ADHD #RetroComputing #Gaming #Online #Worlds #MUD #Leicester #UniversityofLeicester #Prison #Parole #HannibalLecter #SilenceoftheLambs #OkCupid #Tinder #Hinge #MatchGroup #Algorithms #BigData
-
The development of an interactive platform for applying tree-based IRT models for detection of differential item functioning is summarised in a recent #ISOQOL letter:
https://www.isoqol.org/bridging-the-gap-a-user-friendly-tool-for-evaluating-differential-item-functioning-in-patient-reported-outcome-measures/A related methods paper by the team:
https://link.springer.com/article/10.1007/s11136-023-03560-5 -
Read about the editors' choice papers, most downloaded, and interacted paper in "Quality of Life Research":
https://www.isoqol.org/news-from-quality-of-life-research-112024/The last annual update I will be involved in... 😅👋
#ISOQOL #HRQL #HealthEconomics #Psychometrics
#EQ5D #COSMIN #PROMIS -
#1/
Excellent talk by Kevin Weinfurt in #Plenary1 discussing multiple types of measures (go also to #Plenary4 for that!), increased use of high-intensity longitudinal data, and generative AI for assessments.Start reading his work:
https://rdcu.be/dWXSz
#HRQL #Psychometrics#2/
Not sure this is what the #ISOQOL_NewInvestigators wanted when asking me to talk about advice for manuscript writing, but this is the slide people talked to me about 👇
#NightshiftEditor #ScientificPublishing -
"The EQUATOR executive supports the practice of #DataSharing when reporting all research.
Data sharing is important and should be a checklist item in all reporting guidelines."This is only from the highlights section of [https://www.bmj.com/content/386/bmj-2024-079694], the full text is even better.
-
New #AcademicYear - New #introduction
I am interested in health-related quality of life
#HRQL #PsychometricsI teach #ResearchMethods modules in the #DundeeUni #ProfDoc
#Interdisciplinary #RD62001 #RD62002I convene our School's #ResearchEthics committee
My terms as academic editor of 'Quality of Life Research' come to an end, and I am mulling over roles and sense in #AcademicPublishing
#NightshiftEditorThere may be some occasional #Deutsch #Svenska #Gaidhlig and local stuff in my feed.
-
The #PrismaCosmin #guideline
was published jointly in Quality of Life Research, J of Patient Reported Outcomes, Health and Quality of Life Outcomes & J of Clinical Epidemiology.As lead editors, Brittany Lapin and I offer some thoughts on content, process, and future
https://osf.io/preprints/osf/ukw93#PRISMA #Psychometrics #HRQL #ISOQOL
The four versions of the guidelines are published here:
https://link.springer.com/article/10.1007/s11136-024-03634-yhttps://jpro.springeropen.com/articles/10.1186/s41687-024-00727-7
https://hqlo.biomedcentral.com/articles/10.1186/s12955-024-02256-9
https://www.sciencedirect.com/science/article/pii/S089543562400177X
-
A team investigated to which degree construction methods for anchor-based minimal important difference methods are sensitive to the distribution of the #ChangeScore
https://link.springer.com/article/10.1007/s11136-024-03610-6
(Code in supplement)Terluin et al argue that such simulations need to consider measurement error (& illustrate how)
https://rdcu.be/dNAJz
OSF https://osf.io/m5tuy/The original authors respond with a community call👇
https://rdcu.be/dNAJ9
OSF https://osf.io/hgsu7 -
The reporting guideline for #SysReviews of outcome measurement instruments offers great resources to support the planning and write-up of such reviews
https://link.springer.com/article/10.1007/s11136-024-03634-yWe invited response letters to support the discussion, the first 3 are published here:
3) https://link.springer.com/article/10.1007/s11136-024-03732-x
4) Response by the PRISMA-COSMIN team
https://rdcu.be/dNuz3More letters to come, stay tuned!
-
"The Kaiser-Meyer-Olkin value was 0.94, which means that the sample size is adequate for #FactorAnalysis."
-
Collaborating with the team of [https://link.springer.com/article/10.1007/s11136-023-03574-z] led to the following letter giving more detail about the proprietary nature of NIH #PROMIS parameters and how to use perturbation to facilitate transparency in measure development
https://link.springer.com/article/10.1007/s11136-023-03572-1 -
#psychometrics community: I found a paper that developed a short scale and tested it via #LPA and #kmeans clustering. (Paper here: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0281021). Now for me, this is odd as it uses two clustering techniques to assess scale quality. But then again this is a sociology paper and I know that sociologists and psychologists have a different world view. In case you didn't know: Sociologists tend to look at groups within society or societies at large, whereas psychologists tend to see individuals and groups as aggregates of individuals. Obviously, coming from a sociological perspective, using such clustering methods makes sense. However, I still have mixed feelings about this approach. I still feel a IRT approach would be better since obviously k-means and LPA does NOTHING to evaluate items, for example.
How do you see this? Am I completely wrong here?