{{Infobox scientist , honorific_prefix = , name = Kelvyn Jones , honorific_suffix = FBA, FLSW,

FAcSS The Fellowship of the Academy of Social Sciences (FAcSS) is an award granted by the Academy of Social Sciences to leading academics, policy-makers, and practitioners of the social sciences. Fellows were previously known as Academicians and used the ...

, native_name = , native_name_lang = , image = Kelvyn Jones photographed in 2016.jpg , image_size = , image_upright = , alt = , caption = Jones in 2021 , birth_date = {{birth date and age, 1953, 10, 31, df=yes , birth_place =

Rhondda Rhondda , or the Rhondda Valley ( cy, Cwm Rhondda ), is a former coal mining, coalmining area in South Wales, historically in the county of Glamorgan. It takes its name from the River Rhondda, and embraces two valleys – the larger Rhondda Fa ...

Wales Wales ( cy, Cymru ) is a country that is part of the United Kingdom. It is bordered by England to the east, the Irish Sea to the north and west, the Celtic Sea to the south west and the Bristol Channel to the south. It had a population in ...

, death_date = , death_place = , death_cause = , resting_place = , resting_place_coordinates = , other_names = , pronounce = , , citizenship = , nationality = , fields = Quantitative social science,

Human Geography Human geography or anthropogeography is the branch of geography that studies spatial relationships between human communities, cultures, economies, and their interactions with the environment. It analyzes spatial interdependencies between social i ...

, workplaces = University of Newcastle,University College Swansea,University of Reading,Portsmouth Polytechnic,University of Portsmouth,Bristol University,University of Leuven , patrons = , education = , alma_mater = BSc, PhD,

University of Southampton , mottoeng = The Heights Yield to Endeavour , type = Public research university , established = 1862 – Hartley Institution1902 – Hartley University College1913 – Southampton University Coll ...

, thesis_title = Geographical Variations in Mortality , thesis_url = https://eprints.soton.ac.uk/374881/1/81038431.pdf , thesis_year = 1980 , doctoral_advisors = Neil Wrigley, David Pinder , academic_advisors = , doctoral_students = , notable_students = , known_for = Contributions to Multilevel Modelling;

Health Geography Health geography is the application of geographical information, perspectives, and methods to the study of health, disease, and health care. Medical geography, a sub-discipline of or sister field of health geography, Oxford Bibliographies entry of ...

, influences = Peter Haggett, Ron Johnston (geographer), Harvey Goldstein, Graham Woosnam(

Socratic Method The Socratic method (also known as method of Elenchus, elenctic method, or Socratic debate) is a form of cooperative argumentative dialogue between individuals, based on asking and answering questions to stimulate critical thinking and to draw ou ...

) , influenced = , awards =

Murchison Award The Murchison Award, also referred to as the Murchison Grant, was first given by the Royal Geographical Society in 1882 for publications judged to have contributed most to geographical science in preceding recent years. Recipients Source (1882–1 ...

, 2013 , author_abbrev_bot = , author_abbrev_zoo = , spouse = , partner = , children = , signature = , signature_alt = , website = , footnotes = Kelvyn Jones, {{Post-nominals, country=GBR, size=100%, sep=,, FBA, FAcSS, FLSW (born {{Birth date, 1953, 10, 31, df=yes) is a British professor (Emeritus) of human

quantitative geography Quantitative geography is a subfield of geography that develops, tests, and uses mathematical and statistical methods to analyze and model geographic phenomena and patterns. It aims to explain and predict the distribution and dynamics of human and ...

at the

University of Bristol , mottoeng = earningpromotes one's innate power (from Horace, ''Ode 4.4'') , established = 1595 – Merchant Venturers School1876 – University College, Bristol1909 – received royal charter , type ...

. He focuses on the quantitative modelling of social science data with complex structure through the application of

multilevel models Multilevel models (also known as hierarchical linear models, linear mixed-effect model, mixed models, nested data models, random coefficient, random-effects models, random parameter models, or split-plot designs) are statistical models of param ...

; especially in relation to change and health outcomes. Uniquely he is an elected Fellow of the British Academy, the Academy of the Social Sciences and the Learned Society of Wales.

Academic controversies

He has been involved in a number of academic controversies, and these debates have been of a methodological and substantive nature. They include: * He has disagreed with the Wilkinson inequality hypothesis that within country differences in health and mortality are driven by invidious comparison; instead arguing that there is a materialist argument based on poverty even in advanced economies.{{cite journal , doi=10.1016/j.socscimed.2008.11.026 , pmid=19095338 , title=Global variations in health: Evaluating Wilkinson's income inequality hypothesis using the World Values Survey , journal=Social Science & Medicine , volume=68 , issue=4 , pages=643–53 , year=2009 , last1=Jen , first1=Min Hua , last2=Jones , first2=Kelvyn , last3=Johnston , first3=Ron The argument is based on critique of Wilkinson's use of aggregate data and supports the ideas of Hugh Gravelle that if there is a non-linear individual relationship between income and ill-health then the aggregate relationship will necessarily involve the 'spread' (standard deviation) of country income that is inequality.{{cite journal , doi=10.1016/j.healthplace.2008.04.005 , pmid=18514014 , title=Compositional and contextual approaches to the study of health behaviour and outcomes: Using multi-level modelling to evaluate Wilkinson's income inequality hypothesis , journal=Health & Place , volume=15 , issue=1 , pages=198–203 , year=2009 , last1=Jen , first1=Min Hua , last2=Jones , first2=Kelvyn , last3=Johnston , first3=Ron * He has argued against

Growth in a Time of Debt ''Growth in a Time of Debt'', also known by its authors' names as Reinhart–Rogoff, is an economics paper by American economists Carmen Reinhart and Kenneth Rogoff published in a non peer-reviewed issue of the ''American Economic Review'' in 2010. ...

thesis and (with Andy Bell) re-analyzed the Reinhart and Rogoff data to show that the evidence for many counties is that the relationship is around the other way - the lack of growth produces debt, and that the relationship between debt and growth varies significantly between countries, meaning that an average "rule", such as that suggested by Reinhart and Rogoff, has little meaning or policy relevance. * With colleagues, he has argued against

Trevor Phillips Sir Mark Trevor Phillips (born 31 December 1953) is a British writer, broadcaster and former politician who served as Chair of the London Assembly from 2000 to 2001 and from 2002 to 2003. He presented '' Trevor Phillips on Sunday'', a Sunda ...

that the UK is 'sleep walking to segregation', finding that ethnic residential segregation in London for example is decreasing.{{cite journal , doi=10.1111/tran.12142 , title=Macro-scale stability with micro-scale diversity: Modelling changing ethnic minority residential segregation - London 2001-2011 , journal=Transactions of the Institute of British Geographers , volume=41 , issue=4 , pages=389–402 , year=2016 , last1=Johnston , first1=Ron , last2=Jones , first2=Kelvyn , last3=Manley , first3=David , last4=Owen , first4=Dewi , url=https://research-information.bristol.ac.uk/en/publications/macroscale-stability-with-microscale-diversity(27fe21c6-5d72-4c9b-81f3-7b0a3d06a96a).html , hdl=1983/27fe21c6-5d72-4c9b-81f3-7b0a3d06a96a , s2cid=147827437 , hdl-access=free They dispute that Muslim ghettoes are developing in British cities, and that Australian suburbs are being 'swamped' by Asians and Muslims. * He has argued that quantitative analysis in the form of

has an important role in emancipatory

human geography Human geography or anthropogeography is the branch of geography that studies spatial relationships between human communities, cultures, economies, and their interactions with the environment. It analyzes spatial interdependencies between social i ...

(see

critical geography Critical geography is theoretically informed geographical scholarship that promotes social justice, liberation, and leftist politics. Critical geography is also used as an umbrella term for Marxist, feminist, postmodern, poststru ...

). He has argued that this involves adopting a realist philosophy of science distinguished as critical realism and not positivism. The arguments are made in "The Practice of Quantitative Methods" and are further developed and exemplified with colleagues in "Mutual misunderstanding and avoidance, misrepresentations and disciplinary politics: spatial science and quantitative analysis in (United Kingdom) geographical curricula" and a subsequent extended reply to critics in "One step forward but two steps back to the proper appreciation of spatial science". One commentator described this as "an extraordinary contribution. This is a panoramic survey of the legacy of half a century of innovation in spatial science—put into a critical, constructive engagement with half a century of innovation in critical social theory". * He (with colleagues) has challenged the 'gold standard' that fixed effects should be the standard approach to the analysis of

Panel data In statistics and econometrics, panel data and longitudinal data are both multi-dimensional data involving measurements over time. Panel data is a subset of longitudinal data where observations are for the same subjects each time. Time series and ...

and that a Hausman test is an appropriate way of choosing between a

Fixed effects model In statistics, a fixed effects model is a statistical model in which the model parameters are fixed or non-random quantities. This is in contrast to random effects models and mixed models in which all or some of the model parameters are random ...

and a

Random effects model In statistics, a random effects model, also called a variance components model, is a statistical model where the model parameters are random variables. It is a kind of hierarchical linear model, which assumes that the data being analysed are dra ...

. Somewhat controversially they argue that a particular form of the random effects model (the within-between model or the similar Mundlak model) offers all that fixed effects can provide and more. They also challenge the Fixed Effects Vector Decomposition (FEVD) model of Plumper and Troeger. One reaction was: "This paper and the instructive controversial over FEVD have shown me that my econometrics training had not - as I once assumed - taught me all that there is to know about fixed effects estimation. In particular, the authors' treatment of 'heterogeneity bias' clarifies the importance of addressing both 'within' and 'between' variation in the data and they make a compelling case for considering both 'individual' and 'ecological' influences". Another was: "Bizarre and often incorrect paper by two political scientists on the virtues of random-effects over fixed-effects". to "You can and should use a well-specified random effects model. Always.". These models shown algebraically in the table for a two-level panel model Two level panel model alternative specifications

Two level panel model alternative specifications

are discussed and illustrated with snippets of R code by Daniel Lüdecke, and there is a R package (panelr) for panel data analysis by Jacob Long that facilitates their implementation. An extensive review of the potential of this approach in economics concluded that it has been "unreasonably ignored" due in part to "disciplinary isolation" of the subject. In the psychological literature, Hamaker and Muthén, (2020) report that “The most elaborate and animated treatment of the connection etween FE versus RE models and centering in multilevel modelscan be found in the recent paper of Bell and Jones (2015). They build a compelling case for multilevel modelling, arguing that, while the problem of endogeneity is very real, the point is that we should simply use the right multilevel model to tackle it (i.e., based on person mean centering the time-varying covariate and/or including these means as a predictor at the between-level)” * He and colleagues argue that group-mean centering in multilevel models can be a useful procedure in random coefficient models, thereby disagreeing that it is a 'dangerous' procedure. Reactions to this critique include "may the Saints & Angels protect us from ever having a paper this thoroughly dismantled" and "Seriously though, if you are interested in multilevel modelling I highly recommend this short, instructive and frankly rather sassy paper." The essence of the argument is that in a two-level model, the slope parameter associated with level-1 variable is a potentially uninterpretable mixture of within and between effects. The solution is to decentre the level-1 variable by subtracting the level 2 cluster mean and including these level 2 means in the model. The argument is made in terms of continuous variables and is extended to multicategory predictors by Yaremych et al (2021). * He contends that even with population data (e.g. a full enumeration of all pupils in all schools in a country), a statistical inference approach is required to deal with stochastic or natural variation. Observed outcomes are seen as a result of a stochastic process which could produce different results under the same circumstances. It is this underlying process that is of interest and the actual observed values give only an imprecise estimate of this.{{cite journal , doi=10.1007/s13524-015-0430-1 , pmid=26487190 , pmc=4644210 , title=Ethnic Residential Segregation: A Multilevel, Multigroup, Multiscale Approach Exemplified by London in 2011 , journal=Demography , volume=52 , issue=6 , pages=1995–2019 , year=2015 , last1=Jones , first1=Kelvyn , last2=Johnston , first2=Ron , last3=Manley , first3=David , last4=Owen , first4=Dewi , last5=Charlton , first5=Chris * Working with Andy Bell, he has argued that the multilevel model (in the form of the hierarchical-age–period–cohort (HAPC) model) is not an automatic solution to the identification problem of the age period cohort model. This third-party site considers some earlier papers in the exchange between Bell and Jones and Yang and Land, while this most recent paper gives in Table 1 the key papers (and arguments made).; the full list of papers that Bell and Jones have written are available for download from Research Gate. A review of the debate is given by Barker, KM et al (2020) Cross-classified multilevel models (CCMM) in health research: A systematic review of published empirical studies and recommendations for best practices, SSM - Population Health, Volume 12.{{Cite journal, url= , doi = 10.1016/j.ssmph.2020.100661, title = Cross-classified multilevel models (CCMM) in health research: A systematic review of published empirical studies and recommendations for best practices, year = 2020, last1 = Barker, first1 = Kathryn M., last2 = Dunn, first2 = Erin C., last3 = Richmond, first3 = Tracy K., last4 = Ahmed, first4 = Sarah, last5 = Hawrilenko, first5 = Matthew, last6 = Evans, first6 = Clare R., journal = SSM - Population Health, volume = 12, page = 100661, pmid = 32964097, pmc = 7490849, s2cid = 221820440 They conclude "Bell and Jones (2018) have done much to explicate the debate, the ‘identification problem,’ and the methodological concerns. Despite this, the vast majority of researchers continue to employ CCMM for APC analysis without reference to the identification problem, the controversy itself, or any of the latest recommendations for best practices. Those that do refer to the identification problem often note this only within the limitations section of the manuscript. In light of the ongoing debate surrounding these methods, however, we urge substantial caution when conducting APC analysis and recommend a more meaningful engagement with the logic underlying the controversy. "

Academic work and projects

He researches in three main areas: * Geography of health: particularly geographical inequalities in mortality in advanced economies; * Research design: especially to develop evidence-based research in non-experimental, observational studies; * Realistically complex modelling: this research work focuses on the quantitative analysis of social-science data with complex structure, particularly when there are many levels of analysis such as panels, spatial series, and space-time series. His substantive and methodological work is wide-ranging and includes the following bodies of work: Substantive research * Geography of health * Macro determinants of health; * Multilevel modelling of health-related behaviors and outcomes * Multilevel modelling of mental health outcomes * Multilevel modelling of social capital, trust and volunteering * Multilevel modelling of voting behaviors and electoral outcomes * Forecasting geographical variations in the EU referendum * Multilevel modelling of socio-demographic variation in China * Modelling segregation: applying the new methodologies * Multilevel modelling of property(house) prices * Multilevel modelling of sporting outcomes Methodological research * Quantitative geography * Statistical data analysis in the social sciences * Multilevel modelling: scope, models and issues * Multilevel analysis, software, manuals and data * Fixed and Random effects analysis * Modelling nationally predicting locally (multilevel regression with post stratification) * Modelling segregation: methodological developments; this includes work on the

modifiable areal unit problem __NOTOC__ The modifiable areal unit problem (MAUP) is a source of statistical bias that can significantly impact the results of statistical hypothesis tests. MAUP affects results when point-based measures of spatial phenomena are aggregated into ...

; * Modelling interactions: analysis of large tables of counts using a Poisson random effects model * Age period cohort analysis A recent review Cross-classified multilevel models (CCMM) in health research: A systematic review of published empirical studies and recommendations for best practices, the article says "Bell and Jones (2018) have done much to explicate the debate, the ‘identification problem,’ and the methodological concerns. Despite this, the vast majority of researchers continue to employ CCMM for APC analysis without reference to the identification problem, the controversy itself, or any of the latest recommendations for best practices. "

Access to publications and citations

* A Google Scholar profile gives up-to-date citation of his work; in 2022 his H-index score was 64. * He makes available much of his academic output on Research Gate, where he frequently answers questions on statistical (especially multilevel) modeling.; he has also explained his reasons for doing so in answer to a question on the site As of February 2022, he has over 1.2 million 'reads' on Research Gate and this is accruing at a rate of around 3,000 per week. * There are also a

ResearcherID ResearcherID is an identifying system for scientific authors. The system was introduced in January 2008 by Thomson Reuters Corporation. This unique identifier aims at solving the problem of author identification and correct attribution of work ...

site;{{cite web, url=http://www.researcherid.com/rid/A-3939-2011, title=Kelvyn Jones A-3939-2011 - ResearcherID.com, website=Researcherid.com, accessdate=8 September 2017 an

ORCID The ORCID (; Open Researcher and Contributor ID) is a nonproprietary alphanumeric code to uniquely identify authors and contributors of scholarly communication as well as ORCID's website and services to look up authors and their bibliographic ...

site; and a database of publications at the University of Bristol.

Posts held

University of Newcastle, 1978-1979, Lecturer in Geography,;According to entry in

Who's Who (UK) ''Who's Who'' is a reference work. It is a book, and also a CD-ROM and a website, giving information on influential people from around the world. Published annually as a book since 1849, it lists people who influence British life, according to i ...

University College Swansea, 1979-1980, Lecturer in Geography; University of Reading, 1980-1981 SSRC Postdoctoral Fellow; Portsmouth Polytechnic (post 1992, University of Portsmouth) 1981- 1994, Lecturer, Principal Lecturer, Reader; Portsmouth University, 1994-2000, Professor of Geography (Personal Chair), Head of School (1997-2000); Catholic University of Brussels, 1992-2011, Professor of Social Science Methodology; University of Bristol, 2001-2018 Professor of Geography, (Personal Chair) (Head of School, 2005-2009 ); University of Bristol, 2018- Emeritus Professor of Geography; University of Leuven, 2011-2018 Professor at Leuven Statistics Research Centre (LStat). His and other reflections on his time at Portsmouth (Polytechnic and University) were produced on his election to the British Academy Voluntary positions include: RAE Panel Member for Geography 2001; RAE Panel Member for Geography and Environmental Studies 2008; Board Member of Bristol University Press, 2018-; Member of Understanding Society Scientific Advisory Committee, 2018-; Scrutiny Committee for Fellowship of the Learned Society of Wales (Economic and Social Sciences, Education and Law), 2016-.

Recognition and awards

The election to a Fellowship of the British Academy was in 2016 and he was elected both to Sociology, Demography and Social Statistics (Section 4) and to Anthropology and Geography (Section 3)). The citation on election reads ‘Kelvyn Jones is an internationally leading quantitative social scientist. He has made major contributions to the analysis and interpretation of large and complex data sets in a broad field of quantitative social sciences, including geography, and is extremely active in promoting training in quantitative analysis in the social sciences.” He is also a Fellow of the Learned Society of Wales, having been elected in 2013, and an Academician of the Social Sciences, elected in 2008. He was awarded the

of the Royal Geographical Society in 2013 for his contribution to quantitative geography; an account of the ceremony was published in ''

The Geographical Journal ''The Geographical Journal'' is a quarterly peer-reviewed academic journal of the Royal Geographical Society (with the Institute of British Geographers). It publishes papers covering research on all aspects of geography. It also publishes shorter ...

''. 2019 Market Research Society Silver Medal: he was part of the team (Ron Johnston, David Rossiter, Todd Hartman, Charles Pattie, David Manley and Kelvyn Jones) that won this award for best research paper, "Exploring constituency-level estimates for the 2017 British general election", which discusses the implications of constituency-level opinion polls as their predictive ability is improved. {{As of, 2009, he was listed in the top 20 most cited human geographers of the last half century. and since then his

h-index The ''h''-index is an author-level metric that measures both the productivity and citation impact of the publications, initially used for an individual scientist or scholar. The ''h''-index correlates with obvious success indicators such as ...

as measured by Web of Science Researcher ID (Publons) has increased from 20 to 43 in 2022; comparable figures for different social sciences can be found in the LSE impact blog. His Rgate Score as of May 2022 is over 400, and that compares to the outlying high scores of over 100 identified by E. Oduna-Malea et al., 2017 reflecting his willingness to answer questions.

Postgraduate teaching and supervision

He has taught a course on multilevel modeling annually at the Essex Summer School in Social Science Data analysis since 1992 and is a long term contributor to the Masters in Statistics and the Masters in Quantitative Social Science at the Leuven Statistics Research Centre. He also two led two five-day workshops (2009 and 2011) in Pennsylvania State University and UC Santa Barbara under the aegis of GISpopsci.org. He has supervised a number of students for their PhD; they include: * Andrew Clegg * Craig Duncan * Nina Bullen * SV Subramanian * Sarah Johns * Katherine French * Min-Hua Jen * Beatriz Caicedo Velasquez * Caroline Wright- Commendations for PhD thesis and viva in the academic year 2014-15 * Zhixin 'Frank' Feng -winner of the 2013 Faculty Research Prize * Andrew Bell * Dewi Owen * Yingyu Feng * Gwilym Owen- Winner of the Faculty prize for Best Doctoral Research Thesis 2016/17 * Gareth Griffith, * Lucy Prior

Major publications

Book length publications include: * Jones, Kelvyn and Moon, Graham (1987). Health, disease and society: a critical medical geography, Routledge & Kegan Paul Ltd, London. * Jones Kelvyn (1991). Multi-level Models for Geographical Research, Environmental Publications, Norwich. * Moon, Graham; Gould, Myles; Jones, Kelvyn et al. (2000). Epidemiology, Open University Press, Buckingham. * Mohan, John; Barnard, Steve; Jones, Kelvyn and Twigg, Lizbeth (2004). Social capital, place and health: creating, validating and applying small-area indicators in the modelling of health outcomes, Health Development Agency. * Jones, Kelvyn and Subramanian, SV (2014). Developing multilevel models for analysing contextuality, heterogeneity and change using MLwiN, Volume 1, Centre for Multilevel Modelling, University of Bristol, United Kingdom. * Jones, Kelvyn and Subramanian, SV (2013). Developing multilevel models for analysing contextuality, heterogeneity and change using MLwiN, Volume 2, Centre for Multilevel Modelling, University of Bristol, United Kingdom.Developing multilevel models for analysing contextuality, heterogeneity and change: Complete Volume 2 https://www.researchgate.net/publication/260772180 {{Webarchive, url=https://web.archive.org/web/20170915203749/https://www.researchgate.net/publication/260772180 , date=2017-09-15

Personal life

He married Christina Thrush in 1979; Tina died of Breast Cancer in 2020. His hobbies are listening to classical music, especially opera and song; gardening and 'allotmenteering', cooking, wine tasting and watching Bristol Rugby. They have a son, Alex, born in 1987 who is a Fellow of the Royal College of Anaesthetists.{{Cite web, url=https://research-information.bris.ac.uk/en/persons/kelvyn-jones, title=Kelvyn Jones, website=University of Bristol, access-date=2021-01-31, archive-date=2020-10-31, archive-url=https://web.archive.org/web/20201031171843/https://research-information.bris.ac.uk/en/persons/kelvyn-jones, url-status=live

References

{{Reflist {{Authority control {{DEFAULTSORT:Jones, Kelvyn Living people Academics of the University of Bristol British geographers Welsh geographers Fellows of the British Academy Alumni of the University of Southampton Academics of the University of Portsmouth Fellows of the Learned Society of Wales Fellows of the Academy of Social Sciences Human geographers Social geographers Year of birth missing (living people)