A Primer on the Understanding, Use, and Calculation of Confidence Intervals that are Based on Central and Noncentral Distributions

Cumming, Geoff; Finch, Sue

doi:10.1177/0013164401614002

Cited by 416 publications

(262 citation statements)

References 30 publications

Supporting

Mentioning

255

Contrasting

Unclassified

Order By: Relevance

“…Another solution would be to ignore p values altogether and to focus more on effect sizes and confidence intervals (Cumming & Finch, 2001). Although it is impossible to demonstrate that the true effect size is exactly zero, it is possible to estimate true effect sizes with very narrow confidence intervals.…”

Section: Allow Publication Of Nonsignificant Resultsmentioning

confidence: 99%

The ironic effect of significant results on the credibility of multiple-study articles.

Schimmack¹

2012

Psychological Methods

433

416

View full text Add to dashboard Cite

Cohen (1962) pointed out the importance of statistical power for psychology as a science, but statistical power of studies has not increased, while the number of studies in a single article has increased. It has been overlooked that multiple studies with modest power have a high probability of producing nonsignificant results because power decreases as a function of the number of statistical tests that are being conducted (Maxwell, 2004). The discrepancy between the expected number of significant results and the actual number of significant results in multiple-study articles undermines the credibility of the reported results, and it is likely that questionable research practices have contributed to the reporting of too many significant results (Sterling, 1959). The problem of low power in multiple-study articles is illustrated using Bem's (2011) article on extrasensory perception and Gailliot et al.'s (2007) article on glucose and self-regulation. I conclude with several recommendations that can increase the credibility of scientific evidence in psychological journals. One major recommendation is to pay more attention to the power of studies to produce positive results without the help of questionable research practices and to request that authors justify sample sizes with a priori predictions of effect sizes. It is also important to publish replication studies with nonsignificant results if these studies have high power to replicate a published finding.

show abstract

Section: Allow Publication Of Nonsignificant Resultsmentioning

confidence: 99%

The ironic effect of significant results on the credibility of multiple-study articles.

Schimmack¹

2012

Psychological Methods

433

416

View full text Add to dashboard Cite

show abstract

“…This is done by comparing the output of students with dyslexia to that of an age and education matched control group. The results are based on two groups of 100 participants, so that we could reliably detect effect sizes as small as d = .40 (Cumming & Finch, 2001). In clinical practice, effect sizes from d = .50 become practically relevant, because then we start to see a clear difference between the two population distributions.…”

Section: Beyond Spelling: the Writing Skills Of Students With Dysleximentioning

confidence: 99%

Beyond spelling: the writing skills of students with dyslexia in higher education

et al. 2012

View full text Add to dashboard Cite

To have a clearer idea of the problems students with dyslexia may face during their studies, we compared writings of 100 students with dyslexia and 100 age matched control students in higher education. The aim of this study was to compare the writing of young adults with dyslexia and young adults without dyslexia. The study was carried out in Belgium with writers of Dutch. First, we studied the number and type of spelling errors, the quality of the texts produced, the use of words, and the handwriting, both in a précis writing task (writing a summary of an informative text) and in a dictation task (sentence writing). Our results showed medium to large effect sizes for spelling errors: d = .93 for morphosyntactic spelling errors, d= .55 for memory-related spelling errors, and a medium effect size for punctuation and capitalization errors, d = .40. Second, experts who were blind to the aims of the study were asked to judge the quality of the writing of both groups based on transcriptions that were free from spelling errors. The quality of the texts produced was judged lower for students with dyslexia than for the controls, d = .61 for text structure and d = .56 for agreeability, even though the number and types of words used by both groups were very much the same. There was no significant difference in the quality of the handwriting, d = .15. Given that remedial teaching has been shown to be effective for essay-writing skills, educational support along these lines may be helpful for students with dyslexia.Keywords: adult dyslexia -dictation -précis writing -spelling -writingBeyond spelling: The writing skills of students with dyslexia in higher education A non-negligible percentage of students in mainstream higher education have learning difficulties (Hatcher, Snowling, & Griffiths, 2002). Because they are expected to reach the same objectives as their peers, it is important for them to know how they can optimize their performance and for education authorities to have information about which types of support are helpful and justifiable. For instance, students with dyslexia are known to have spelling problems in addition to reading difficulties (Callens, Tops, & Brysbaert, in press;Swanson & Hsieh, 2009). Because written reports form the basis of many student assessments and evaluations (Farmer, Riddick, & Sterling, 2002) and because poor spelling is likely to influence marking, it is reasonable to provide these students with text-processing software that has a built-in spelling checker (Desoete, Brysbaert, Tops, Callens, De Lange, & Van Hees, 2010;Goldberg, Russell, & Cook, 2003). At the same time, it would be good to know whether the quality of spelling-corrected essays and summaries is equivalent for students with dyslexia as for controls, or whether this is another challenge students with dyslexia should take into account. Hayes and Flower (1980) proposed an influential cognitive model of skilled adult writing, analysing different components of the writing process and their interaction. In this model th...

show abstract

“…As Fidler, Thomason, Cumming, Finch, and Leeman (2004) note, this movement started in medicine as early as the 1980s (see Rothman 1975Rothman , 1978aRothman , 1978b. In psychology, in the past 15 years or so, there has been renewed emphasis on reporting ESs because of editorial policies requiring ESs (e.g., Murphy, 1997;Thompson, 1994) Inference, 1999).…”

Section: Introductionmentioning

confidence: 99%

“…An interest in reporting CIs for ESs has accompanied the emphasis on ESs. Cumming and Finch (2001), for example, presented a primer of CIs for ESs. The purpose of this article is to bring to the attention of researchers in medicine and psychology, and other interested researchers, who set CIs around an ES parameter, a better approach than currently adopted methods.…”

Section: Introductionmentioning

confidence: 99%

Robust Confidence Intervals for Effect Size in the Two-Group Case

Keselman

Algina

Fradette

2005

J. Mod. App. Stat. Meth.

View full text Add to dashboard Cite

The probability coverage of intervals involving robust estimates of effect size based on seven procedures was compared for asymmetrically trimming data in an independent two-groups design, and a method that symmetrically trims the data. Four conditions were varied: (a) percentage of trimming, (b) type of nonnormal population distribution, (c) population effect size, and (d) sample size. Results indicated that coverage probabilities were generally well controlled under the conditions of nonnormality. The symmetric trimming method provided excellent probability coverage. Recommendations are provided.

show abstract

A Primer on the Understanding, Use, and Calculation of Confidence Intervals that are Based on Central and Noncentral Distributions

Cited by 416 publications

References 30 publications

The ironic effect of significant results on the credibility of multiple-study articles.

The ironic effect of significant results on the credibility of multiple-study articles.

Beyond spelling: the writing skills of students with dyslexia in higher education

Robust Confidence Intervals for Effect Size in the Two-Group Case

Contact Info

Product

Resources

About