A novel method for evaluating an interaction effect of correlated continuous covariates in a linear model

Interaction effect is an important scientific interest for many areas of research. Common approach for investigating the interaction effect of two continuous covariates on a response variable is through a cross-product term in multiple linear regression. In epidemiological studies, the two-way analysis of variance (ANOVA) type of method has also been utilized to examine the interaction effect by replacing the continuous covariates with their discretized levels. However, the implications of model assumptions of either approach have not been examined and the statistical validation has only focused on the general method, not specifically for the interaction effect.^ In this dissertation, we investigated the validity of both approaches based on the mathematical assumptions for non-skewed data. We showed that linear regression may not be an appropriate model when the interaction effect exists because it implies a highly skewed distribution for the response variable. We also showed that the normality and constant variance assumptions required by ANOVA are not satisfied in the model where the continuous covariates are replaced with their discretized levels. Therefore, naïve application of ANOVA method may lead to an incorrect conclusion. ^ Given the problems identified above, we proposed a novel method modifying from the traditional ANOVA approach to rigorously evaluate the interaction effect. The analytical expression of the interaction effect was derived based on the conditional distribution of the response variable given the discretized continuous covariates. A testing procedure that combines the p-values from each level of the discretized covariates was developed to test the overall significance of the interaction effect. According to the simulation study, the proposed method is more powerful then the least squares regression and the ANOVA method in detecting the interaction effect when data comes from a trivariate normal distribution. The proposed method was applied to a dataset from the National Institute of Neurological Disorders and Stroke (NINDS) tissue plasminogen activator (t-PA) stroke trial, and baseline age-by-weight interaction effect was found significant in predicting the change from baseline in NIHSS at Month-3 among patients received t-PA therapy.^

Computer interaction : its effect on attitude and performance in older adults

This study examined the interaction of age, attitude, and performance within the context of an interactive computer testing experience. Subjects were 13 males and 47 females between the ages of 55 and 82, with a minimum of a high school education. Initial attitudes toward computers, as measured by the Cybernetics Attitude Scale (CAS), demonstrated overall equivalence between these older subjects and previously tested younger subjects. Post-intervention scores on the CAS indicated that attitudes toward computers were unaffected by either a "fun" or a "challenging" computer interaction experience. The differential effects of a computerized vs. a paperand- pencil presentation format of a 20-item, multiple choice vocabulary test were examined. Results indicated no significant differences in the performance of subjects in the two conditions, and no interaction effect between attitude and performance. These findings suggest that the attitudes of older adults towards computers do not affect their computerized testing performance, at least for short term testing of verbal abilities. A further implication is that, under the conditions presented here, older subjects appear to be unaffected by mode of testing. The impact of recent advanced in technology on older adults is discussed.

Correcting Measurement Error Bias in Interaction Models with Small Samples

Several methods have been suggested to estimate non-linear models with interaction terms in the presence of measurement error. Structural equation models eliminate measurement error bias, but require large samples. Ordinary least squares regression on summated scales, regression on factor scores and partial least squares are appropriate for small samples but do not correct measurement error bias. Two stage least squares regression does correct measurement error bias but the results strongly depend on the instrumental variable choice. This article discusses the old disattenuated regression method as an alternative for correcting measurement error in small samples. The method is extended to the case of interaction terms and is illustrated on a model that examines the interaction effect of innovation and style of use of budgets on business performance. Alternative reliability estimates that can be used to disattenuate the estimates are discussed. A comparison is made with the alternative methods. Methods that do not correct for measurement error bias perform very similarly and considerably worse than disattenuated regression

Moderating effects of management control systems and innovation on performance. Simple methods for correcting the effects of measurement error for interaction effects in small samples

In the accounting literature, interaction or moderating effects are usually assessed by means of OLS regression and summated rating scales are constructed to reduce measurement error bias. Structural equation models and two-stage least squares regression could be used to completely eliminate this bias, but large samples are needed. Partial Least Squares are appropriate for small samples but do not correct measurement error bias. In this article, disattenuated regression is discussed as a small sample alternative and is illustrated on data of Bisbe and Otley (in press) that examine the interaction effect of innovation and style of use of budgets on performance. Sizeable differences emerge between OLS and disattenuated regression

Effect of addition of different hydrocolloids on pasting, thermal, and rheological properties of cassava starch

Starches and gums are hydrocolloids frequently used in food systems to provide proper texture, moisture, and water mobility. Starch-gum interaction in food systems can change the starch granule swelling and its gelatinization and rheological properties. In this study, the effect of the addition of xanthan gum (XG), sodium carboxymethyl cellulose (SCMC), and carrageenan (CAR) at the concentrations of the 0.15, 0.25, 0.35 and 0.45% (w/v) on the pasting, thermal, and rheological properties of cassava starch was studied. The swelling power (SP) and the scanning electron microscopy (SEM) of the starch gels were also evaluated. The results obtained showed that xanthan gum (XG) had a strong interaction with the cassava starch penetrating between starch granules causing increase in pasting viscosities, SP, storage and loss (G', and G", respectively) modulus and reduction in the setback of the starch; sodium carboxymethyl cellulose (SCMC) greatly increased the pasting viscosities, the SP, and the storage and loss (G', and G", respectively) modulus of the starch-mixtures, mainly due to its greater capacity to hold water and not due to the interaction with cassava starch. Carrageenan (CAR) did not change any of the starch properties since there was no interaction between this gum and cassava starch at the concentrations used.

Moderating effects of management control systems and innovation on performance. Simple methods for correcting the effects of measurement error for interaction effects in small samples

In the accounting literature, interaction or moderating effects are usually assessed by means of OLS regression and summated rating scales are constructed to reduce measurement error bias. Structural equation models and two-stage least squares regression could be used to completely eliminate this bias, but large samples are needed. Partial Least Squares are appropriate for small samples but do not correct measurement error bias. In this article, disattenuated regression is discussed as a small sample alternative and is illustrated on data of Bisbe and Otley (in press) that examine the interaction effect of innovation and style of use of budgets on performance. Sizeable differences emerge between OLS and disattenuated regression

Correcting Measurement Error Bias in Interaction Models with Small Samples

Several methods have been suggested to estimate non-linear models with interaction terms in the presence of measurement error. Structural equation models eliminate measurement error bias, but require large samples. Ordinary least squares regression on summated scales, regression on factor scores and partial least squares are appropriate for small samples but do not correct measurement error bias. Two stage least squares regression does correct measurement error bias but the results strongly depend on the instrumental variable choice. This article discusses the old disattenuated regression method as an alternative for correcting measurement error in small samples. The method is extended to the case of interaction terms and is illustrated on a model that examines the interaction effect of innovation and style of use of budgets on business performance. Alternative reliability estimates that can be used to disattenuate the estimates are discussed. A comparison is made with the alternative methods. Methods that do not correct for measurement error bias perform very similarly and considerably worse than disattenuated regression

Involvement in environmental causes, does the joint effect between subjective income and the performance of the country matter?

Previous research has shown that richer people are more likely to engage in an environmentalcause. We extend it by considering the joint effect between subjective income and a set of macroeconomicvariables. For doing so, we employ the fifth wave of the World Values Survey (WVS).This study provides clear evidence that even when both factors matter, people´s attitudes cruciallydepend on the interaction effect. Hence, those measures that affect the characteristics of thecountry would also change the disposition to be involved.

Effect of monensin on performance in growing ruminants reared under different environmental temperatures

To evaluate the effect of monensin on the performance of growing cattle under different environmental temperatures, 24 male calves (81.9 +/- 7.7 kg mean weight and 100 days old) were distributed in a 2 x 2 factorial arrangement, contrasting 0 or 85 mg monensin/animal per day at 24.3 or 33.2 degrees C (environmental temperatures). Monensin supplementation increased weight gain (P=0.036), improved feed efficiency (P=0.040), increased ruminal concentrations of volatile fatty acids (VFA; P=0.003) and decreased the molar proportion of butyrate (P=0.034); all effects irrespective of environmental temperatures. A temperature-dependent monensin effect was detected on nitrogen retention (P=0.018) and N retained:N absorbed ratio (P=0.012). Animals fed monensin retained higher N amounts than those of the non-supplemented ones when the environmental temperature was 33.2 degrees C. Environmental temperature and monensin supplementation showed an interaction effect on urine N concentration (P=0.003). Temperature did not affect N excretion in monensin-fed animals, but increased N excretion in the non-supplemented ones. Monensin increased the crude protein (CP) digestibility (P=0.094) for

Effects of sex and age on genotype x environment interaction for beef cattle body weight studied using reaction norm models

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Effect of orthognathic surgery for class III correction on quality of life as measured by SF-36

The purpose of this work was to evaluate the quality of life of patients with Angle's class III malocclusion submitted to orthognathic surgery. Twenty-nine patients of both sexes, ranging in age from 17 to 46 years, with Angle's class III malocclusion and indication for surgical treatment, were evaluated about 30 days before surgery and 6 months postoperatively. Surgery consisted of maxillary advancement or mandibular retrusion, or both. The generic SF-36 questionnaire was used to evaluate the following eight domains: functional capacity, physical aspects, pain, general health status, mental health, emotional aspects, social aspects and vitality. Descriptive and inferential statistical analyses were used to determine possible interactions between timing of evaluation, gender and type of surgery. With respect to physical and social aspects, a significant difference in outcomes was observed, with mean scores being higher after surgery regardless of gender or type of surgery. Regarding emotional aspects, an interaction effect was observed for timing and gender, with higher mean scores only being obtained for females after Surgery. Orthognathic Surgery had a positive impact on the quality of life of both male and female patients, improving physical and social aspects, and on that of female patients, improving emotional aspects.

Effect of the levels of calcium and particle size of limestone on laying hens

O experimento foi realizado para avaliar o efeito dos níveis de cálcio (Ca) e da granulometria do calcário (GC) para poedeiras comerciais. Foram utilizadas 216 poedeiras da linhagem Dekalb White de 25 a 49 semanas de idade em um delineamento inteiramente casualizado, em esquema fatorial 3 × 2, composto de três níveis de cálcio (3,92; 4,02 e 4,12%) e duas granulometrias do calcário (fina - 0,60 mm; e grossa - 1,00 mm), que resultaram em seis tratamentos, com seis repetições de seis aves. Não houve efeito significativo dos níveis de cálcio e da granulometria do calcário nem da interação nível de cálcio × granulometria do calcário para o consumo de ração, o peso dos ovos, a gravidade específica, a espessura da casca, a porcentagem de casca, a unidade Haugh, a digestibilidade de cálcio e fósforo e a porcentagem do trato digestório. A produção, massa, conversão por massa e conversão por dúzia de ovos tiveram seus melhores resultados com 4,12% de cálcio na dieta. A porcentagem de moela e o consumo de ração observado às 15 h melhoraram com o aumento na granulometria do calcário de 0,60 para 1,00 mm. Houve efeito da interação entre nível de cálcio e granulometria do calcário para a resistência à quebra da tíbia, a densidade óssea, o comprimento do intestino delgado e o consumo de ração às 6, 9, 12, 18 e 21 h, respectivamente. Recomenda-se a adição de 4,12% de cálcio e calcário na granulometria grossa (1,00 mm) para melhor desempenho de poedeiras comerciais. Mais estudos são necessários para elucidar os mecanismos envolvidos na alteração do comportamento alimentar das poedeiras em resposta às mudanças nos níveis de cálcio e na granulometria do calcário das rações.

Effect of surface conditioning methods on the microtensile bond strength of resin composite to composite after aging conditions

Objectives. This study evaluated the effect of two different surface conditioning methods on the repair bond strength of a bis-GMA-adduct/bis-EMA/TEGDMA based resin composite after three aging conditions.Methods. Thirty-six composite resin blocks (Esthet X, Dentsply) were prepared (5 mm x 6 mm x 6 mm) and randomly assigned into three groups for aging process: (a) immersion in citric acid (pH 3.0 at 37 degrees C, 1 week) (CA); (b) boiling in water for 8h (BW) and (c) thermocycling (x5000, 5-55 degrees C, dwell time: 30s) (TC). After aging, the blocks were assigned to one of the following surface conditioning methods: (1) silica coating (30 mu m SiOx) (CoJet, 3M ESPE) + silane (ESPE-Sil) (CJ), (2) phosphoric acid + adhesive resin (Single Bond, 3M ESPE) (PA). Resin composite (Esthet.X (R)) was bonded to the conditioned substrates incrementally and light polymerized. The experimental groups formed were as follows: Gr1:CA + PA; Gr2:CA + CJ Gr3:BW + PA; Gr4: BW + CJ; Gr5:TC + PA; Gr6: TC + CJ. The specimens were sectioned in two axes (x and y) with a diamond disc under coolant irrigation in order to obtain non-trimmed bar specimens (sticks, 10 mm x 1 mm x 1 mm) with 1 mm(2) of bonding area. The microtensile test was accomplished in a universal testing machine (crosshead speed: 0.5 mm min(-1)).Results. The means and standard deviations of bond strength (MPa +/- S.D.) per group were as follows: Gr1: 25.5 +/- 10.3; Gr2: 46.3 +/- 10.1; Gr3: 21.7 +/- 7.1; Gr4: 52.3 +/- 15.1; GrS: 16.1 +/- 5.1; Gr6, 49.6 +/- 13.5. The silica coated groups showed significantly higher mean bond values after all three aging conditions (p < 0.0001) (two-way ANOVA and Tukey tests, alpha = 0.05). The interaction effect revealed significant influence of TC aging on both silica coated and acid etched groups compared to the other aging methods (p < 0.032). Citric acid was the least aggressive aging medium.Significance. Chairside silica coating and silanization provided higher resin-resin bond strength values compared to acid etching with phosphoric acid followed by adhesive resin applications. Thermocycling the composite substrates resulted in the lowest repair bond strength compared to citric acid challenge or boiling in water. (C) 2006 Academy of Dental Materials. Published by Elsevier Ltd. All rights reserved.

Strategies in identifying individuals in a segregant population of common bean and implications of genotype x environment interaction in the success of selection

The objective of this study was to compare the BLUP selection method with different selection strategies in F-2:4 and assess the efficiency of this method on the early choice of the best common bean (Phaseolus vulgaris) lines. Fifty-one F-2:4 progenies were produced from a cross between the CVIII8511 x RP-26 lines. A randomized block design was used with 20 replications and one-plant field plots. Character data on plant architecture and grain yield were obtained and then the sum of the standardized variables was estimated for simultaneous selection of both traits. Analysis was carried out by mixed models (BLUP) and the least squares method to compare different selection strategies, like mass selection, stratified mass selection and between and within progeny selection. The progenies selected by BLUP were assessed in advanced generations, always selecting the greatest and smallest sum of the standardized variables. Analyses by the least squares method and BLUP procedure ranked the progenies in the same way. The coincidence of the individuals identified by BLUP and between and within progeny selection was high and of the greatest magnitude when BLUP was compared with mass selection. Although BLUP is the best estimator of genotypic value, its efficiency in the response to long term selection is not different from any of the other methods, because it is also unable to predict the future effect of the progenies x environments interaction. It was inferred that selection success will always depend on the most accurate possible progeny assessment and using alternatives to reduce the progenies x environments interaction effect.