Talk:Psychometrics
From Wikipedia, the free encyclopedia
 Portal |
This article is within the scope of WikiProject Psychology, which collaborates on Psychology and related subjects on Wikipedia. To participate, help improve this article or visit the project page for details on the project.
|
||||||||
 |
Psychometrics was a good article candidate, but did not meet the good article criteria at the time. Once the objections listed below are addressed, the article can be renominated. You may also seek a review of the decision if you feel there was a mistake.
Date of review: No date specified. Please edit template call function as follows: {{FailedGA|insert date in any format here}} |
Wikipedia:Good_articles/Disputes explicitly says: Do not use the FailedGA template. Holon 06:41, 18 April 2006 (UTC)
I'm afraid I can't resist pointing out the salient irony here. An article on psychometrics is being "graded" using a process that cannot be shown to meet the most basic of psychometric criteria! Dear me. Holon 12:10, 2 September 2006 (UTC)
Contents |
[edit] Failed Good article review
The article focuses solely on individual psychometrics. Social psychometrics need to be addressed. See comments below. Some sections have no inline references or one minor one -- with this level of detail inline references would help. For generality, it would be helpful to discuss the wide range of applications of psychometry, such as in epidemiology, social psychology, public health and in other sociences.
- Psychometrics shares the same root as psychology. Psychology is almost entirely concerned with the mental world of the individual, and is differentiated from sociology. Prominent contributors to the field, including Thurstone, Jensen and Rasch, considered their work very much focused on individuals. Even psychometric instruments used in social psychology are normally used to measure individual perceptions, motivations and so forth which are posited to relate to social factors (e.g. perceptions of social expectations, norms, attributions). In the same way, measurement generally has an almost infinite range of applications, but it is not necessary to mention every single one of these in an article on measurement -- indeed it would detract to do so. There is no problem mentioning applications in such fields, including health, but this would not fundamentally alter the article. Anthropometrics is concerned with the physical measurement of indiduals but can (and has) been applied in a range of fields, including epidemiology. Most articles can be broadened, but the limitation you perceive is minor and a red herring. Holon 05:56, 18 April 2006 (UTC)
[edit] Psychometrics for social phenomena
The various applications of psychometrics are not of crucial importance in a general article, but nevertheless these fields of application (mainly "clinimetrics" which is the application of psychometrics to medical issues) could be mentioned in a separate section. The reasons, according to me, why this is not a good article, are:
(1) Sentences like "An alternative approach involves the application of unfolding measurement models, the most general being the Hyperbolic Cosine Model (Andrich & Luo, 1993)." Several terms (unfolding measurement model, hyperbolic cosine model) are not explained, and so offer very little help for the reader. (2) The structure is unclear, and some important aspects are omitted. (Reaction times, psychometric models of perception etc).
Applications to "social phenomena" (such as those referred to below) are largely irrelevant. For example, the 1984 article on "social support and social network scales" is just an investigation of psychometric properties of a few self-report scales. This is not of general interest and gives no insight to "psychometrics as applied to social phenomena". Lebatsnok 15:33, 24 January 2007 (UTC)
- Just so you are aware, inserting comments here is quite confusing. I couldn't even see the new comments without looking at the history. Perhaps you could suggest or make changes. I can't see much use discussing whether it is a "good article". Like most artciles, it has some good and bad aspects. What should the structure be? I tend to agree it's not good, but you must have something in mind if you think it is unclear. Holon 04:12, 25 January 2007 (UTC)
Psychometrics are applied to measure social phenomena. This article is narrow in its perpsective. The article needs a revised introduction and a new section on using psychometry to study social factors.
Social networks and quality of life for long-term survivors of leukemia and lymphoma. Lim JW, Zebrack B. Support Care Cancer. 2006 Feb;14(2):185-92. Epub 2005 Jul 9. "This study examined the relationship between personal and medical characteristics and quality of life (QOL) for long-term survivors (LTS) of leukemia and lymphoma, and how social networks influence this relationship." PMID: 16007454 [PubMed - in process] [1]
Note the 1984 date on this -- these types of studies have been around awhile: Social support and social network scales: a psychometric review. Rock DL, Green KE, Wise BK, Rock RD. Res Nurs Health. 1984 Dec;7(4):325-32.[2] "Social support and social network scales were reviewed from a psychometric perspective. A sample of 29 behavioral science studies were selected from social support and social network articles published between 1967 and 1982. Each study was classified according to psychometric issues of scaling, reliability, and validity. The review was motivated by the hypothesis that many social support and social network scales are developed without complete utilization of existing measurement technology." [PubMed]
These reviews and studies including social and social psychological factors might or might not help: The scale of ethnic experience: development and psychometric properties. Malcarne VL, Chavira DA, Fernandez S, Liu PJ. Related Articles, Links J Pers Assess. 2006 Apr;86(2):150-61. PMID: 16599789 [PubMed]
Are employees' ratings of coworkers' organizational citizenship behavior influenced by their own perceptions of organizational justice?'. Ascigil SF, Magner NR, Sonmez Y. Psychol Rep. 2005 Aug;97(1):98-100. PMID: 16279309 [PubMed - indexed for MEDLINE]
Epidemiological measurement of children's and adolescents' exposure to community violence: working with the current state of the science. Brandt R, Ward CL, Dawes A, Flisher AJ. Clin Child Fam Psychol Rev. 2005 Dec;8(4):327-42. Review. PMID: 16362258 [PubMed - indexed for MEDLINE] "A number of measures have been used in epidemiological studies of children's exposure to community violence, yet the quality of these instruments is not uniformly good. This paper undertakes a systematic review of the most commonly used (or most promising) self-report or interview-administered instruments, with regard to their conceptual bases and psychometric properties. Based on the review, recommendations are made for working with the current state of the science in order to move the field forward. A key recommendation is for sounder conceptualization of work in the field and greater transparency in the reporting of research, in order to facilitate the comparability of studies."
Trajectories of cognitive decline and social relations. Beland F, Zunzunegui MV, Alvarado B, Otero A, Del Ser T. J Gerontol B Psychol Sci Soc Sci. 2005 Nov;60(6):P320-P330. PMID: 16260706 [PubMed - indexed for MEDLINE] "We assessed conjoint trajectories of cognitive decline and social relations over 7 years on a representative sample of community-dwelling elderly persons. We analyzed data using repeated measurement models. Social integration, family ties, and engagement with family were associated with cognitive function at advanced ages, controlling for education and introducing depressive symptoms, functional limitations, and chronic conditions as intervening variables. Association of social integration, through participation in community activities, with change in cognitive decline was more significant at advanced ages. Having friends was significantly associated with change in cognitive function in women only. Our findings have important implications for clinical medicine and public health because associations of social relations with cognitive function suggests that they may help to maintain cognitive function in old age."
Cultural values underlying psychometric cognitive testing. Ardila A. Neuropsychol Rev. 2005 Dec;15(4):185-95. PMID: 16395623 [PubMed - in process] It is proposed that culture (values, beliefs, styles of behavior) can affect neuropsychological testing.Cognitive testing represents a social situation that-as any social situation, it is one governed by implicit cultural rules. At least eight different culture-dependent values underlie cognitive testing: (1) One-to-one relationship, (2) Background authority, (3) Best performance, (4)Isolated environment (5) Special type of communication, (6) Speed, (7) Internal or subjective issues, and (8) The use of specific testing elements and strategies. In addition, it is proposed that"the distance" (e.g., gender, age, ethnicity) between the examiner and the examinee may potentially impact the testing situation. A special analysis regarding the function of instruction in cognitive tests is also presented emphasizing that test instruction interpretation is also culture-dependent. Some potential avenues of research are finally proposed.
- You said: Psychometrics are applied to measure social phenomena. Psychometrics is used almost invariably as a singular noun, interchangable with psychometry. Are you using the term as a shorthand to refer to psychometric instruments? See my comments above which cover all of these citations. Holon 06:12, 18 April 2006 (UTC)
It would be nice to have some mention of Psychometrics as a branch/application of Statistics. The field can be approached from Psychology as well as Statistics and Education.
Some contemporary issues of Psychometrics would be a nice addition: brief mention of computer adaptive testing, differential item functioning, etc.
I also see no mention of what universities seem to refer to as Psychometrics: (a type of) quantitative psychology.
--StatsJunkie 04:49, 2 September 2006 (UTC)
Some approaches in psychometrics are applications of statistics, but measurement is more fundamental than statistics, in the sense that many statistical techniques require measurement as a starting point. Personally, I wouldn't like to have mention of it in these terms. There's enough confusion about the difference between measurement and statistics as it is.
Holon 12:08, 2 September 2006 (UTC)
[edit] Psychometrics and education
I agree with Holon on how psychometrics refers to the measurement of the individual. However, latent mental variables of the individual are not limited to psychological constructs, and this article needs to reflect this. It is currently written from a psychological slant, but, in my opinion, more of the psychometrics that goes on "out there" is in educational and professional settings. For example, state educational achievement tests, work sample tests, licensure and certification examinations. These are achievement tests, and achievement is not a psychological trait because it is more or less acquired - though the acquisition is often dependent on psychological traits. Many, many psychometricians work on these types of tests.
The initial definition should be the measurement of latent mental variables at the individual level - and while psychology is a primary example of this, it is not the only one. Any thoughts? Iulus Ascanius 03:44, 22 December 2006 (UTC)
- I think you're quite right, and it is actually the area in which I work, even though I started with studies in psych. So let's make some changes to reflect this. They wouldn't need to be dramatic ones, I wouldn't think. Holon 03:20, 23 December 2006 (UTC)
-
- Great - I agree that the changes wouldn't be substantial. I'll sit down one of these days... Iulus Ascanius 03:15, 26 December 2006 (UTC)
[edit] An on-line service of this topic may need to be included
as this is mentioned by
www.hrmguide.com/recruitment/whole-person-tests.htm
[edit] Norming
The practice of adjusting the tests so that male and female test takers will get comparable scores in all areas deserves illumination, plus justification for current practices, balanced by pro and con statements. —The preceding unsigned comment was added by 24.20.140.24 (talk • contribs).
