1,178 research outputs found
Test of the hypothesis that the intraclass reliability coefficient is the same for two measurement procedures
No full textAn approximate statistical test is derived for the
hypothesis that the intraclass reliability coefficients
associated with two measurement procedures are
equal. Control of Type 1 error is investigated by
comparing empirical sampling distributions of the
test statistic with its derived theoretical distribution.
A numerical illustration of the procedure is
also presented. Index terms: intraclass reliability,
reliability, sampling theory, Spearman-Brown
extrapolation, statistical test.Alsawalmeh, Yousef M.; Feldt, Leonard S.. (1992). Test of the hypothesis that the intraclass reliability coefficient is the same for two measurement procedures. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/115648
The FELDT-HIGGS Universal Bridge (F-HUB) - Part One: The Birth of Spacetime - An Informational Framework for Mass, Gravity, and Entropy
No full text“And God said, ‘Let there be light,’ and there was light.” — Genesis 1:3 (New International Version)
But before there was light, there had to be mass.
And before there was mass, there had to be structure.
And before there was structure, there had to be information.
For over a century, physics has been governed by two seemingly irreconcilable frameworks: General Relativity, which describes gravity as the curvature of spacetime (Einstein, 1915), and Quantum Mechanics, which governs the probabilistic nature of subatomic interactions (Heisenberg, 1927). While both theories have been experimentally validated with extraordinary precision, they remain fundamentally disconnected—unable to unify into a single coherent model (Witten, 1998).
This paper introduces the Feldt-Higgs Universal Bridge (F-HUB), a framework that proposes mass, gravity, entropy, and spacetime itself are not fundamental properties but emergent phenomena of structured quantum information. Inspired by the Holographic Principle (Susskind, 1995), black hole thermodynamics (Bekenstein, 1973; Hawking, 1974), and quantum information theory (Wheeler, 1989), FHUB establishes a direct link between mass-energy interactions, entropy growth, and the informational structure of spacetime.
At the core of F-HUB lies a mathematically validated and testable equation that predicts:
1. Mass is not an intrinsic property but an emergent effect of quantum information interacting with the Higgs Field (Higgs, 1964).
2. Gravity is not a fundamental force but a secondary effect arising from entropy and mass- energy structuring spacetime (Penrose, 2014).
3. Entropy is not merely disorder—it is the fundamental process that structures spacetime through information flow (Bekenstein, 1973).
4. Spacetime itself is not fundamental but an emergent construct shaped by quantum information interactions (Susskind, 1995; t’Hooft, 1993).
Unlike previous unification attempts—such as String Theory, which introduces speculative extra dimensions (Witten, 1998), or Loop Quantum Gravity, which assumes a discretised spacetime (Rovelli & Smolin, 1995)—F-HUB does not require new dimensions, undiscovered particles, or unverified forces. Instead, it reveals the informational foundation that underlies all known physics.
The F-HUB Master Equation, derived from fundamental principles, is expressed as:
S = (H’ · M · k_B · α) / c³
where:
• S = Entropy (Joules per Kelvin, J/K), representing structured spacetime information
• H’ = Higgs Field Contribution (as an energy density-like term)
• M = Mass (kg), the emergent effect of structured quantum information.
• k_B = Boltzmann’s Constant (J/K), ensuring thermodynamic consistency.
• α = Unified Scaling Factor (dimensionless), encoding entropy, curvature, and quantum information density.
• c³ = Relativistic Scaling Factor (m³/s³), maintaining compatibility with relativity.
This mathematical correction ensures dimensional consistency, strengthening F-HUB’s scientific credibility and reinforcing its thermodynamic foundation.
F-HUB is:
Mathematically rigorous – dimensionally consistent and logically derived.
Experimentally testable – making predictions that can be validated or falsified.
Conceptually fundamental – requiring no arbitrary assumptions beyond known physics.
By examining Higgs boson behaviour, entropy-information relationships, and spacetime fluctuations, F-HUB presents clear empirical avenues for validation. If correct, F-HUB is not merely an extension of modern physics—it represents a fundamental shift in our understanding of spacetime itself
Testing the Equality of Two Related Intraclass Reliability Coefficients
No full textAn approximate statistical test of the equality of two
intraclass reliability coefficients based on the same
sample of people is derived. Such a test is needed when a
researcher wishes to compare the reliability of two measurement
procedures and both procedures can be applied
to the performances or products of the same group of
individuals. A numerical example is presented. Monte
carlo studies indicate that the proposed test effectively
controls Type I error with as few as two or three measurements
on each of 50 people. Index terms: equality
of related intraclass reliability coefficients, intraclass
reliability, sampling theory, Speannan-Brown extrapolation,
statistical test.Alsawaimeh, Yousef M.; Feldt, Leonard S.. (1994). Testing the Equality of Two Related Intraclass Reliability Coefficients. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/120038
Atomdroid: A Computational Chemistry Tool for Mobile Platforms
No full textWe present the implementation of a new molecular mechanics program designed for use in mobile platforms, the first specifically built for these devices. The software is designed to run on Android operating systems and is compatible with several modern tablet-PCs and smartphones available in the market. It includes molecular viewer/builder capabilities with integrated routines for geometry optimizations and Monte Carlo simulations. These functionalities allow it to work as a stand-alone tool. We discuss some particular development aspects, as well as the overall feasibility of using computational chemistry software packages in mobile platforms. Benchmark calculations show that through efficient implementation techniques even hand-held devices can be used to simulate midsized systems using force fields
Ground truth deficiencies in software engineering: when codifying the past can be counterproductive
No full textMany software engineering tools build and evaluate their models based on historical data to support development and process decisions. These models help us answer numerous interesting questions, but have their own caveats. In a real-life setting, the objective function of human decision-makers for a given task might be influenced by a whole host of factors that stem from their cognitive biases, subverting the ideal objective function required for an optimally functioning system. Relying on this data as ground truth may give rise to systems that end up automating software engineering decisions by mimicking past sub-optimal behaviour. We illustrate this phenomenon and suggest mitigation strategies to raise awareness
Thyroglobulin measurement by highly sensitive assays : focus on laboratory challenges
No full textDifferentiated thyroid cancer (DTC) is the most common endocrine cancer and its incidence has increased in recent decades. The initial treatment consists of total thyroidectomy followed by ablation of thyroid remnants by radioiodine in most cases. As thyroid cells are the only source of thyroglobulin (Tg), circulating Tg serves as a biochemical marker of persistent or recurrent disease in the follow-up of DTC. Due to the suboptimal clinical detection rate of older Tg assays endogenous or exogenous thyrotropin (TSH) stimulations are recommended for unmasking occult disease. However, the development of new Tg assays with improved analytical sensitivity and precision at low concentrations now allows detection of very low Tg concentrations, reflecting minimal amounts of thyroid tissue, even without the need for TSH stimulation. Even if the use of these assays still has not found its way in current clinical guidelines, such assays are now increasingly used in clinical practice. As serum Tg measurement is a technically challenging assay and criteria to define a 'highly sensitive' assay may be different, a good knowledge of the technical difficulties and interpretation criteria is of paramount importance for both clinical thyroidologists, laboratory physicians and scientists involved in the care of DTC patients
Test Set Diameter: Quantifying the Diversity of Sets of Test Cases
No full textA common and natural intuition among software testers is that test cases need
to differ if a software system is to be tested properly and its quality
ensured. Consequently, much research has gone into formulating distance
measures for how test cases, their inputs and/or their outputs differ. However,
common to these proposals is that they are data type specific and/or calculate
the diversity only between pairs of test inputs, traces or outputs.
We propose a new metric to measure the diversity of sets of tests: the test
set diameter (TSDm). It extends our earlier, pairwise test diversity metrics
based on recent advances in information theory regarding the calculation of the
normalized compression distance (NCD) for multisets. An advantage is that TSDm
can be applied regardless of data type and on any test-related information, not
only the test inputs. A downside is the increased computational time compared
to competing approaches.
Our experiments on four different systems show that the test set diameter can
help select test sets with higher structural and fault coverage than random
selection even when only applied to test inputs. This can enable early test
design and selection, prior to even having a software system to test, and
complement other types of test automation and analysis. We argue that this
quantification of test set diversity creates a number of opportunities to
better understand software quality and provides practical ways to increase it.Comment: In submissio
Aikapaine ja hyvinvointi ohjelmistotuotannossa : Tutkimusaineistoa ohjelmistojen versionhallintatyökaluista, ESM-menetelmästä ja aikaisemmasta kirjallisuudesta
No full textAbstractPopular and academic sources have indicated that high-pressure work environments are commonplace in the software industry, leading to stress and burnout. One cause of stress is time pressure, not having enough time to complete a task at hand. In addition to effects on well-being, time pressure affects software development processes, productivity, and quality. Synthesising prior evidence and providing real-time data to managers could help to minimize the detrimental effects and optimize productivity.This thesis aims to investigate and give a comprehensive view of the existing body of knowledge on the effects of time pressure in software engineering, including processes, methods, and individual developers. Additionally, we aim to investigate ways to link time pressure and work well-being to software repositories to understand the well-being of software developers better. The research consists of two branches: a review branch and a primary study branch. In the review branch, prior knowledge related to sentiment analysis and time pressure was analyzed with bibliometric studies, making a systematic map and a systematic literature review. Studies were conducted using software repository mining, sentiment analysis, experience sampling, and interviews in the primary study branch.Results from the review branch indicate, among others, increased productivity and decreased quality under time pressure. The causes of time pressure can be divided into technical and social factors, with errors in cost estimation, project management, and company culture being the most common causes. The results from the primary study branch show the limiting effect of individual differences on the prediction of well-being. Other findings include the detection of work rhythms through mining time stamps of code commits and the prediction ability of chat activity over chat sentiment on developer productivity.While the research for this thesis could not find clear links between repository variables and developer well-being that would work at a team level, possibilities to study these links further are established. Future work related to time pressure in software engineering should focus on contextual factors such as company culture and trade-offs between productivity, quality, and well-being within different time scales.Original papersOriginal papers are not included in the electronic version of the dissertation.Kuutila, M., Mäntylä, M. V., Claes, M., & Elovainio, M. (2017). Reviewing literature on time pressure in software engineering and related professions: Computer assisted interdisciplinary literature review. 2017 IEEE/ACM 2nd International Workshop on Emotion Awareness in Software Engineering (SEmotion), 54–59. https://doi.org/10.1109/SEmotion.2017.1Self-archived versionMäntylä, M. V., Graziotin, D., & Kuutila, M. (2018). The evolution of sentiment analysis—A review of research topics, venues, and top cited papers. Computer Science Review, 27, 16–32. https://doi.org/10.1016/j.cosrev.2017.10.002Self-archived versionKuutila, M., Mäntylä, M., Farooq, U., & Claes, M. (2020). Time pressure in software engineering: A systematic review. Information and Software Technology, 121, 106257. https://doi.org/10.1016/j.infsof.2020.106257Self-archived versionKuutila, M., Mäntylä, M. V., Farooq, U., & Claes, M. (2021). What do we know about time pressure in software development? IEEE Software, 38(5), 32–38. https://doi.org/10.1109/MS.2020.3020784Self-archived versionClaes, M., Mäntylä, M. V., Kuutila, M., & Adams, B. (2018). Do programmers work at night or during the weekend? Proceedings of the 40th International Conference on Software Engineering, 705–715. https://doi.org/10.1145/3180155.3180193Self-archived versionKuutila, M., Mäntylä, M. V., & Claes, M. (2020). Chat activity is a better predictor than chat sentiment on software developers productivity. Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops, 553–556. https://doi.org/10.1145/3387940.3392224Self-archived versionKuutila, M., Mäntylä, M. V., Claes, M., & Elovainio, M. (2018). Daily questionnaire to assess self-reported well-being during a software development project. Proceedings of the 3rd International Workshop on Emotion Awareness in Software Engineering, 39–43. https://doi.org/10.1145/3194932.3194942Self-archived versionKuutila, M., Mäntylä, M. V., Claes, M., Elovainio, M., & Adams, B. (2018). Using experience sampling to link software repositories with emotions and work well-being. Proceedings of the 12th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement, 1–10. https://doi.org/10.1145/3239235.3239245Self-archived versionKuutila, M., Mäntylä, M., Claes, M., Elovainio, M., & Adams, B. (2021). Individual differences limit predicting well-being and productivity using software repositories: A longitudinal industrial study. Empirical Software Engineering, 26(5), 88. https://doi.org/10.1007/s10664-021-09977-1Self-archived versionTiivistelmäAmmattilais- ja akateeminen kirjallisuus on viitannut painostavien työympäristöjen olevan yleisiä ohjelmistoalalla, johtaen ylimääräiseen stressiin ja työuupumukseen. Yksi stressin lähde on aikapaine, ts. tehtävän tekemiseen ei ole tarpeeksi aikaa. Heikentyneen työhyvinvoinnin lisäksi aikapaine vaikuttaa tuottavuuteen ja ohjelmistojen laatuun. Aikaisempien tutkimustulosten syntetisointi ja reaaliaikaisen tiedon tuottaminen managereille voisi helpottaa aikapaineen haitallisia vaikutuksia ja parantaa tehokkuutta.Tämä väitöskirja yrittää antaa kokonaisvaltaisemman kuvan olemassa olevasta aikapaineeseen liittyvästä kirjallisuudesta ohjelmistokehityksen kontekstissa, mukaanlukien vaikutuksista prosesseihin, metodeihin ja ohjelmistokehittäjiin. Lisäksi tavoitteena on myös yrittää yhdistää aikapaine ja työhyvinvointi ohjelmistokehityksen työkaluista saatavaan tietoon. Tehty tutkimus koostuu kahdesta osiosta: kirjallisuuskatsaukset ja primääriset tutkimukset. Kirjallisuuskatsauksiin keskittyvässä osiossa käytettiin muunmuassa klusteriointia laajojen aineistojen katselmoimiseen liittyen sentimentti analyysiin ja aikapaineeseen. Lisäksi tehtiin systemaattinen kartta ja -katsaus aikapaineeseen ohjelmistokehityksen kontekstissa. Primääritutkimuksissa käytettiin tutkimusmetodologioina ohjelmistokehitykseen liittyvien tietolähteiden “louhintaa”, sentimentti analyysiä, ESM-menetelmää ja haastatteluja.Kirjallisuuskatsausosion tulokset näyttävät aikapaineen lisäävän tuottavuutta ja huonontavan laatua ohjelmistokehityksessä. Aikapaineen aiheuttajat ovat teknisiä ja sosiaalisia ja ne liittyvät kolmeen kategoriaan: virheet kustannusarvioissa, virheet projektijohtamisessa ja yrityksen kulttuuri. Primääritutkimusosion tulokset näyttävät, kuinka erot ohjelmistokehittäjien välillä vaikeuttavat hyvinvoinnin ennustamista ohjelmistokehitykseen liittyvistä työkaluista saadusta tiedosta. Muita tuloksia ovat se, että kommitoidun ohjelmakoodin määrä seuraa vuorokausirytmiä avoimenlähdekoodin projekteissa, sekä se, että yksittäisessä ohjelmistoprojektissa kommunikaation määrä ennusti kommitoidun lähdekoodin määrää paremmin kuin kommunikaatiossa oleva sentimentti.Vaikka tämä väitöstutkimus ei pystynyt löytämään ohjelmistokehitystyökaluista saatavien muuttujien ja ohjelmistokehittäjien hyvinvoinnin välille selviä linkkejä, jotka toimisivat hyvinä ennustajina ohjelmistokehitystiimin tasolla, osoittaa tutkimus lisää mahdollisuuksia tutkia näitä linkkejä. Tulevan aikapaineeseen liittyvän tutkimuksen ohjelmistokehityksen saralla tulisi keskittyä kontekstisidonnaisiin muuttujiin, kuten yrityskulttuuriin, sekä valintoihin tuottavuuden, laadun ja hyvinvoinnin välillä eri aikajänteillä.OsajulkaisutOsajulkaisut eivät sisälly väitöskirjan elektroniseen versioon.Kuutila, M., Mäntylä, M. V., Claes, M., & Elovainio, M. (2017). Reviewing literature on time pressure in software engineering and related professions: Computer assisted interdisciplinary literature review. 2017 IEEE/ACM 2nd International Workshop on Emotion Awareness in Software Engineering (SEmotion), 54–59. https://doi.org/10.1109/SEmotion.2017.1Rinnakkaistallennettu versioMäntylä, M. V., Graziotin, D., & Kuutila, M. (2018). The evolution of sentiment analysis—A review of research topics, venues, and top cited papers. Computer Science Review, 27, 16–32. https://doi.org/10.1016/j.cosrev.2017.10.002Rinnakkaistallennettu versioKuutila, M., Mäntylä, M., Farooq, U., & Claes, M. (2020). Time pressure in software engineering: A systematic review. Information and Software Technology, 121, 106257. https://doi.org/10.1016/j.infsof.2020.106257Rinnakkaistallennettu versioKuutila, M., Mäntylä, M. V., Farooq, U., & Claes, M. (2021). What do we know about time pressure in software development? IEEE Software, 38(5), 32–38. https://doi.org/10.1109/MS.2020.3020784Rinnakkaistallennettu versioClaes, M., Mäntylä, M. V., Kuutila, M., & Adams, B. (2018). Do programmers work at night or during the weekend? Proceedings of the 40th International Conference on Software Engineering, 705–715. https://doi.org/10.1145/3180155.3180193Rinnakkaistallennettu versioKuutila, M., Mäntylä, M. V., & Claes, M. (2020). Chat activity is a better predictor than chat sentiment on software developers productivity. Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops, 553–556. https://doi.org/10.1145/3387940.3392224Rinnakkaistallennettu versioKuutila, M., Mäntylä, M. V., Claes, M., & Elovainio, M. (2018). Daily questionnaire to assess self-reported well-being during a software development project. Proceedings of the 3rd International Workshop on Emotion Awareness in Software Engineering, 39–43. https://doi.org/10.1145/3194932.3194942Rinnakkaistallennettu versioKuutila, M., Mäntylä, M. V., Claes, M., Elovainio, M., & Adams, B. (2018). Using experience sampling to link software repositories with emotions and work well-being. Proceedings of the 12th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement, 1–10. https://doi.org/10.1145/3239235.3239245Rinnakkaistallennettu versioKuutila, M., Mäntylä, M., Claes, M., Elovainio, M., & Adams, B. (2021). Individual differences limit predicting well-being and productivity using software repositories: A longitudinal industrial study. Empirical Software Engineering, 26(5), 88. https://doi.org/10.1007/s10664-021-09977-1Rinnakkaistallennettu versioAcademic dissertation to be presented with the assent of the Doctoral Training Committee of Information Technology and Electrical Engineering of the University of Oulu for public defence in Martti Ahtisaari auditorium (L2), Linnanmaa, on 3 December 2021, at 12 noonAbstract
Popular and academic sources have indicated that high-pressure work environments are commonplace in the software industry, leading to stress and burnout. One cause of stress is time pressure, not having enough time to complete a task at hand. In addition to effects on well-being, time pressure affects software development processes, productivity, and quality. Synthesising prior evidence and providing real-time data to managers could help to minimize the detrimental effects and optimize productivity.
This thesis aims to investigate and give a comprehensive view of the existing body of knowledge on the effects of time pressure in software engineering, including processes, methods, and individual developers. Additionally, we aim to investigate ways to link time pressure and work well-being to software repositories to understand the well-being of software developers better. The research consists of two branches: a review branch and a primary study branch. In the review branch, prior knowledge related to sentiment analysis and time pressure was analyzed with bibliometric studies, making a systematic map and a systematic literature review. Studies were conducted using software repository mining, sentiment analysis, experience sampling, and interviews in the primary study branch.
Results from the review branch indicate, among others, increased productivity and decreased quality under time pressure. The causes of time pressure can be divided into technical and social factors, with errors in cost estimation, project management, and company culture being the most common causes. The results from the primary study branch show the limiting effect of individual differences on the prediction of well-being. Other findings include the detection of work rhythms through mining time stamps of code commits and the prediction ability of chat activity over chat sentiment on developer productivity.
While the research for this thesis could not find clear links between repository variables and developer well-being that would work at a team level, possibilities to study these links further are established. Future work related to time pressure in software engineering should focus on contextual factors such as company culture and trade-offs between productivity, quality, and well-being within different time scales.Tiivistelmä
Ammattilais- ja akateeminen kirjallisuus on viitannut painostavien työympäristöjen olevan yleisiä ohjelmistoalalla, johtaen ylimääräiseen stressiin ja työuupumukseen. Yksi stressin lähde on aikapaine, ts. tehtävän tekemiseen ei ole tarpeeksi aikaa. Heikentyneen työhyvinvoinnin lisäksi aikapaine vaikuttaa tuottavuuteen ja ohjelmistojen laatuun. Aikaisempien tutkimustulosten syntetisointi ja reaaliaikaisen tiedon tuottaminen managereille voisi helpottaa aikapaineen haitallisia vaikutuksia ja parantaa tehokkuutta.
Tämä väitöskirja yrittää antaa kokonaisvaltaisemman kuvan olemassa olevasta aikapaineeseen liittyvästä kirjallisuudesta ohjelmistokehityksen kontekstissa, mukaanlukien vaikutuksista prosesseihin, metodeihin ja ohjelmistokehittäjiin. Lisäksi tavoitteena on myös yrittää yhdistää aikapaine ja työhyvinvointi ohjelmistokehityksen työkaluista saatavaan tietoon. Tehty tutkimus koostuu kahdesta osiosta: kirjallisuuskatsaukset ja primääriset tutkimukset. Kirjallisuuskatsauksiin keskittyvässä osiossa käytettiin muunmuassa klusteriointia laajojen aineistojen katselmoimiseen liittyen sentimentti analyysiin ja aikapaineeseen. Lisäksi tehtiin systemaattinen kartta ja -katsaus aikapaineeseen ohjelmistokehityksen kontekstissa. Primääritutkimuksissa käytettiin tutkimusmetodologioina ohjelmistokehitykseen liittyvien tietolähteiden “louhintaa”, sentimentti analyysiä, ESM-menetelmää ja haastatteluja.
Kirjallisuuskatsausosion tulokset näyttävät aikapaineen lisäävän tuottavuutta ja huonontavan laatua ohjelmistokehityksessä. Aikapaineen aiheuttajat ovat teknisiä ja sosiaalisia ja ne liittyvät kolmeen kategoriaan: virheet kustannusarvioissa, virheet projektijohtamisessa ja yrityksen kulttuuri. Primääritutkimusosion tulokset näyttävät, kuinka erot ohjelmistokehittäjien välillä vaikeuttavat hyvinvoinnin ennustamista ohjelmistokehitykseen liittyvistä työkaluista saadusta tiedosta. Muita tuloksia ovat se, että kommitoidun ohjelmakoodin määrä seuraa vuorokausirytmiä avoimenlähdekoodin projekteissa, sekä se, että yksittäisessä ohjelmistoprojektissa kommunikaation määrä ennusti kommitoidun lähdekoodin määrää paremmin kuin kommunikaatiossa oleva sentimentti.
Vaikka tämä väitöstutkimus ei pystynyt löytämään ohjelmistokehitystyökaluista saatavien muuttujien ja ohjelmistokehittäjien hyvinvoinnin välille selviä linkkejä, jotka toimisivat hyvinä ennustajina ohjelmistokehitystiimin tasolla, osoittaa tutkimus lisää mahdollisuuksia tutkia näitä linkkejä. Tulevan aikapaineeseen liittyvän tutkimuksen ohjelmistokehityksen saralla tulisi keskittyä kontekstisidonnaisiin muuttujiin, kuten yrityskulttuuriin, sekä valintoihin tuottavuuden, laadun ja hyvinvoinnin välillä eri aikajänteillä
An empirical comparison of univariate and multivariate repeated measures analysis techniques when applied to motor performance data : a Monte Carlo study
No full textTypescript (photocopy).The purpose of this study was to examine, through Monte Carlo methods, the empirical alpha levels and the statistical power obtained when selected data from motor learning research was subjected to univariate and multivariate analyses. Specific purposes of this investigation were to compare results obtained from analysis of the group by trials interaction using five statistical techniques, including four variations of univariate ANOVA and one multivariate method. The univariate procedures utilized in this study were (1) the traditional repeated measures (RM) ANOVA, (2) RM ANOVA with degrees of freedom (df) adjusted with the sample estimate to Box's (1954) correction factor, (3) RM ANOVA with df adjusted with Huynh & Feldt's (1973) correction factor, and (5) the Geisser & Greenhouse (1958) conservative test. The multivariate test used in this study was Wilks' A. The five procedures were compared using four different dependent error measures, absolute error (AE), variable error (VE), constant error (CE), and total variability (E), with fixed sample sizes, n = 10, 20, or 30, and under nine degrees of violation of covariance homogeneity. For each of the nine conditions of type of covariance by sample size by dependent error measure, 5000 data sets were generated and empirical alpha levels were compared for the five statistical tests. The relative statistical power of the five tests was also compared. Results revealed that the multivariate test maintained the nominal alpha level under all conditions while violations of the assumptions inherent to ANOVA appeared to coincide with inflated Type I error levels when using uncorrected RM ANOVA. The Geisser & Greenhouse conservative test was indeed conservative as all empirical alpha levels fell more than two standard errors of a proportion below the nominal alpha levels. The remaining two adjusted univariate tests ranged from the estimate for Box's test being slightly conservative when assumptions were met to the Huynh & Feldt test being slightly liberal when assumptions were not met
- …
