The robustness of the two—sample<i>t</i>—test over the Pearson system

Posten, Harry O.

doi:10.1080/00949657808810197

Cited by 51 publications

(17 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Because of the sample size in this study the reporting of results of the parametric tests, such as t -tests, is appropriate as they are robust to violation of normality as the sample size increases. 27–29 To adjust for relevant demographic and clinical variables we used multiple regression analyses. We fit seven multiple regression models.…”

Section: Methodsmentioning

confidence: 99%

Health-Related Profiles of People With Lower Limb Loss

Amtmann

Morgan

Kim

et al. 2015

Archives of Physical Medicine and Rehabilitation

107

View full text Add to dashboard Cite

Objective To construct profiles of self-reported health indicators to examine differences and similarities between people with lower limb loss (LLL) and a normative sample (hereafter called the norm), and to compare health indicators between subgroups based on level and etiology of limb loss. Design Survey Setting General community Participants Adults with unilateral lower limb loss (n=1091) participated in this study. Eligibility criteria included LLL resulting from trauma or dysvascular complications and regular use of a prosthesis. Interventions Not applicable Main Outcome Measures Patient-Reported Outcomes Measurement Information System 29-item profile (PROMIS-29) version 1.0 measures physical function, pain interference, fatigue, sleep disturbance, anxiety, depression and satisfaction with participation in social roles. The norms are based on 5,239 individuals representative of the U.S. general population in gender, age, race, ethnicity and education. Results People with LLL reported statistically significantly worse physical function, pain interference and satisfaction with participation in social roles and significantly less fatigue than the norm. People with transfemoral (i.e., above-knee) amputation significantly differed from people with transtibial (i.e., below-knee) amputation on physical function. Similarly, people with amputation due to trauma and dysvascular etiology significantly differed on physical function and satisfaction with social roles after adjusting for relevant clinical characteristics. Conclusions People with LLL generally report worse physical function, pain interference and satisfaction with social roles when compared to norm. People with dysvascular amputation reported worse physical function and satisfaction with social roles than people with traumatic amputation. Health indicator profiles are an efficient way of providing clinically meaningful information about numerous aspects of self-reported health in people with LLL.

show abstract

Section: Methodsmentioning

confidence: 99%

Health-Related Profiles of People With Lower Limb Loss

Amtmann

Morgan

Kim

et al. 2015

Archives of Physical Medicine and Rehabilitation

107

View full text Add to dashboard Cite

show abstract

“…For small sample sizes, there are a few analytical studies (Efron 1969, Tan 1982) providing evidence of the t test's robustness to non-Normality, but the main evidence comes from simulations, e.g., Yuen and Dixon (1973), Yuen (1974), Murphy (1976), Posten (1978Posten ( , 1979, Tiku(1980), Gans(1981), TikuandSingh(1982. Several others are reviewed by Glass et al (1972).…”

Section: Parametric T Testsmentioning

confidence: 99%

Assessing Effects of Unreplicated Perturbations: No Simple Solutions

Stewart‐Oaten¹,

Bence²,

Osenberg³

1992

Ecology

235

153

View full text Add to dashboard Cite

We address the task of determining the effects, on mean population density or other parameters, of an unreplicated perturbation, such as arises in environmental assessments and some ecosystem—level experiments. Our context is the Before—After—Control—Impact—Pairs design (BACIP): on several dates Before and After the perturbation, samples are collected simultaneously at both the Impact site and a nearby "Control." One approach is to test whether the mean of the Impact—Control difference has changed from Before to After the perturbation. If a conventional test is used, checks of its assumptions are an important and messy part of the analysis, since BACIP data do not necessarily satisfy them. It has been suggested that these checks are not needed for randomization tests, because they are insensitive to some of these assumptions and can be adjusted to allow for others. A major aim of this paper is to refute this suggestion: there is no panacea for the difficult and messy technical problems in the analysis of data from assessments or unreplicated experiments. We compare the randomization t test with the standard t test and the modified (Welch—Satterthwaite—Aspin) t test, which allows for unequal variances. We conclude that the randomization t test is less likely to yield valid inferences than is the Welch t test, because it requires identical distributions for small sample sizes and either equal variances or equal sample sizes for larger ones. The formal requirement of Normality is not crucial to the Welch t test. Both parametric and randomization tests require that time and location effects be additive and the Impact—Control differences on different dates be independent. These assumptions should be tested; if they are seriously wrong, alternative analyses are needed. This will often require a long time series of data. Finally, for assessing the importance of a perturbation, the P value of a hypothesis test is rarely as useful as an estimate of the size of the effect. Especially if effect size varies with time and conditions, flexible estimation methods with approximate answers are preferable to formally exact P values.

show abstract

“…Para checar os efeitos da escolaridade, a ANOVA foi utilizada para comparação entre as médias dos subgrupos superior incompleto, superior completo e pós-graduação. Ressalta-se que a escolha de testes paramétricos deu-se, apesar do efeito-teto nas respostas dos subtestes (que poderia ocasionar violação dos parâmetros de normalidade), pois sabe-se que, ainda assim, são robustos e produzem resultados fi dedignos (Boneau, 1960;Posten, 1978;Rasch & Guiard, 2004). Dado o caráter preliminar do estudo, uma análise de componentes principais também foi realizada, a fi m de identifi car os fatores latentes associados aos subtestes.…”

Section: Análise Estatística Dos Dadosunclassified

O reconhecimento de expressões faciais e prosódia emocional: investigação preliminar em uma amostra brasileira jovem

Costa-Vieira

Souza

2014

Estud. psicol. (Natal)

View full text Add to dashboard Cite

ResumoSinais não verbais de comunicação emocional são frequentes em diferentes culturas. Esta pesquisa buscou traduzir e adaptar uma bateria (Florida Aff ect Battery) de avaliação de expressões faciais e prosódia emocional, bem como avaliar o desempenho de uma amostra populacional brasileira em seus subtestes, incluindo uma comparação entre participantes do sexo feminino e masculino e por escolaridade. Os resultados da amostra brasileira foram avaliados e, posteriormente, comparados aos da amostra estadunidense, fornecidos no manual da bateria. Não foram encontradas diferenças estatisticamente signifi cantes entre o desempenho da amostra brasileira e da amostra estadunidense, bem como entre homens e mulheres, com altas taxas de acerto para todos os grupos avaliados, evidenciando um bom reconhecimento de expressões faciais e prosódia emocional.Palavras-chave: expressões faciais; percepção da face; percepção da fala; disprosodia emocional; Florida aff ect battery. Abstract Recognition of emotional facial expressions and of emotional prosody: A preliminary investigation in a young brazilian sample.Nonverbal signs of emotional communication are common in diff erent cultures. Th is study aimed to translate and adapt a battery (Florida Aff ect Battery) of evaluation of facial expressions and emotional prosody, as well as evaluate the performance of a Brazilian sample in their subtests, including a comparison of men and women and of education level. Th e results of the Brazilian sample were compared to the results of United States sample provided in battery's manual. Th ere were no signifi cant diff erences between the performance of Brazilian sample and the United States sample as well as between men and women, with high success rates for all groups evaluated.Keywords: facial expressions; face perception; speech perception, emotional disprosody; Florida aff ect battery. ResumenEl reconocimiento de las expresiones faciales y la prosodia emocional: Investigación preliminar en una muestra brasileña joven. Señales no verbales de comunicación emocional son comunes em diferentes culturas. Este estudio tuvo como objetivo traducir y adaptar una batería (Florida Aff ect Battery) de evaluación de expresiones faciales y prosodia emocional, así como evaluar el desempeño de una muestra de la población brasileña en sus subpruebas, incluyendo uma comparación entre participantes hombres y mujeres e entre los diferentes níveles de educación. Los resultados de la muestra brasileña fueron evaluados, y posteriormente, se compararon con los resultados de la muestra estadounidense, proporcionados en el manual de la batería. No hubo diferencias signifi cativas entre el desempeño de la muestra brasileña y la muestra estadunidense, así como entre hombres y mujeres, con altas tasas de acierto para todos los grupos evaluados, evidenciando un buen reconocimiento de expresiones faciales y prosodia emocional.Palabras clave: expresiones faciales; percepción facial; percepción del habla; disprosodia emocional, Florida aff ect battery.

show abstract

The robustness of the two—samplet—test over the Pearson system

Cited by 51 publications

References 2 publications

Health-Related Profiles of People With Lower Limb Loss

Health-Related Profiles of People With Lower Limb Loss

Assessing Effects of Unreplicated Perturbations: No Simple Solutions

O reconhecimento de expressões faciais e prosódia emocional: investigação preliminar em uma amostra brasileira jovem

Contact Info

Product

Resources

About