Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Analysis of Variance”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,495 records · Page 83Linked to original sources
PubMed1998

Base deficit in the elderly: a marker of severe injury and death.

BACKGROUND: Base deficit has been used as a marker of significant injury and to predict resource utilization and mortality. The significance of base deficit in trauma patients 55 years and older has not been specifically evaluated. The purpose of this study was to determine the utility of base deficit in assessing older trauma patients versus a younger cohort. METHODS: Data were obtained from the trauma registry on trauma patients admitted to a Level I trauma center. Arterial blood gases were obtained within 1 hour of arrival, by protocol, in 2,631 patients, and of these, 274 patients were 55 years or older. Data are presented as means+/-SEM. Statistical analysis was done by paired t test, analysis of variance, and chi2 analysis. Significance was attributed to a p value < 0.05. RESULTS: Patients older than 55 years were significantly more likely to have sustained blunt trauma (86 vs. 69%; p < 0.001). Despite similar Injury Severity Scores and base deficit values, older patients had markedly greater mortality and intensive care unit lengths of stay. A base deficit of < or = -6 had positive predictive values for Injury Severity Scores > or = 16 for 76% of patients younger than 55 years and 78 % of patients 55 years and older. The negative predictive value of a normal base deficit for Injury Severity Scores < or = 16 was 60% for the younger cohort and only 40% for patients 55 years and older (p < 0.001; chi2). CONCLUSIONS: A base deficit of < or = -6 is a marker of severe injury and significant mortality in all trauma patients, but it is particularly ominous in patients 55 years and older. Patients older than 55 years may have significant injuries and mortality risk without manifesting a base deficit out of the normal range.

Acidosis↗
PubMed2004

Cross-validation for linear model with unequal variances in genomic analysis.

In recent years, genomic studies are usually conducted to identify genes that may have an impact on clinical outcomes. The identified genes are then used to establish a predictive model for identifying subjects who are most likely to respond to the test treatment in clinical trials. This information is useful in early and later phases of clinical development. The United States Food and Drug Administration (FDA) requires that such a predictive model be validated before it can be used in clinical development. Shao [Shao, J. (1993). Linear model selection by cross-validation. J. Amer. Statist. Assoc. 88(422):486-494] proposed a cross-validation method for linear model with equal variances, which is found useful in genomic studies. In practice, however, genomic data may be obtained from different sources with unequal variances. As a result, Shao's method may not be applied directly. In this paper, we extend Shao's method for cross-validation of a linear model with unequal variances. Along this line, two re-sampling methods were proposed to account for the heterogeneity in variance. Several simulations were performed to evaluate the finite samples performances of the proposed methods. An example concerning a breast cancer research is present to illustrate the use of the proposed methods.

Algorithms↗
PubMed2004

Gamma regression improves Haseman-Elston and variance components linkage analysis for sib-pairs.

Existing standard methods of linkage analysis for quantitative phenotypes rest on the assumptions of either ordinary least squares (Haseman and Elston [1972] Behav. Genet. 2:3-19; Sham and Purcell [2001] Am. J. Hum. Genet. 68:1527-1532) or phenotypic normality (Almasy and Blangero [1998] Am. J. Hum. Genet. 68:1198-1199; Kruglyak and Lander [1995] Am. J. Hum. Genet. 57:439-454). The limitations of both these methods lie in the specification of the error distribution in the respective regression analyses. In ordinary least squares regression, the residual distribution is misspecified as being independent of the mean level. Using variance components and assuming phenotypic normality, the dependency on the mean level is correctly specified, but the remaining residual coefficient of variation is constrained a priori. Here it is shown that these limitations can be addressed (for a sample of unselected sib-pairs) using a generalized linear model based on the gamma distribution, which can be readily implemented in any standard statistical software package. The generalized linear model approach can emulate variance components when phenotypic multivariate normality is assumed (Almasy and Blangero [1998] Am. J. Hum Genet. 68: 1198-1211) and is therefore more powerful than ordinary least squares, but has the added advantage of being robust to deviations from multivariate normality and provides (often overlooked) model-fit diagnostics for linkage analysis.

Analysis of Variance↗
PubMed1988

A multivariate statistical summary of synaptic plasticity measures in rats exposed to complex, social and individual environments.

Multivariate analysis of variance, canonical discriminant analysis, factor analysis, and stepwise multiple regression were applied to 36 variables representing measures of occipital cortical synaptic, cellular, and vascular morphology in rats reared in complex, social, and individual housing environments. The results indicate differential expression of coordinated vascular and cellular metabolic processes across the three environments.

Analysis of Variance↗
PubMed1997

Tropical illness profiles: the psychology of illness perception in Malawi.

Psychological and social investigations of tropical diseases can make a significant contribution to understanding and managing many illnesses. One-hundred and seventy-five Malawian university students rated peopled who suffered from AIDS, malaria, schistosomiasis and the 'common cold', on 11 psycho-social dimensions related to illness. Analysis of variance and factor analysis was used to distinguish distinctive illness profiles reflecting perceptions of (people with) these illnesses. Results suggested that infirmity was associated with AIDS and that the seriousness of malaria was minimized. Within a context of many threats to health the importance of distinguishing between serious illnesses is emphasized for effective health promotion interventions.

Acquired Immunodeficiency Syndrome↗
PubMed1992

Effect of different sealers on thermoplasticized Gutta-percha root canal obturations.

The objective of this study was to test the hypothesis that the apical seal provided by thermoplasticized root canal obturations depends on the film thickness of the sealer used. The root canals of 120 maxillary cuspid teeth were instrumented and divided into six equal groups of 20 teeth. A thermoplasticized gutta-percha root canal obturator was used to make an impression of the lubricated canal and coated with a sealer cement before reseating. Five different sealer cements of known film thickness were studied. They were, in the decreasing order of film thickness, Roth's Type I Cement, Seal-apex, Lee Endofil, AH26, and Ketac-Cem. The control group that received no sealer was prepared as recommended by the manufacturer. The degree of microleakage was based on the depth of dye penetration from the apical end measured by two independent examiners. The data collected were analyzed by analysis of variance and Weibull distribution. Analysis of variance shows that the control group exhibited significantly higher dye penetration depth (p < 0.05) while there were no significant differences among the other five groups. Analysis by Weibull distribution function shows that Lee Endofil and AH26 exhibited a higher percentage of lower linear dye penetration values compared with other groups.

Analysis of Variance↗
PubMed2002

Does lamotrigine influence valproate concentrations?

The aim of this study is to investigate the effect of lamotrigine (LTG) on valproate (VPA) concentrations dependent on LTG dose, LTG concentration, and additional enzyme-inducing antiepileptic drugs (AED) as well. For this purpose the following patient groups were compared: VPA monotherapy, VPA + one enzyme-inducing AED, VPA + LTG, and VPA + LTG + one enzyme-inducing AED. A total of 400 serum concentrations from 372 patients were evaluated. Two or more serum samples from the same patient were considered only if the comedication had been changed. For statistical evaluation, regression analytical methods and an analysis of variance were performed. For the analysis of variance, the VPA serum concentration in relation to VPA dose:body weight (level:dose ratio, LDR) was calculated and compared for different drug combinations. The analysis of variance revealed a significant effect of enzyme-inducing comedication (as expected) and age on the VPA LDR. Patients on LTG had a slightly lower VPA LDR, but this effect was not statistically significant. In addition, nonlinear regression analysis confirmed that patients on enzyme-inducing AED (carbamazepine, phenytoin, phenobarbital, methsuximide) had significantly lower VPA concentrations. Patients on ethosuximide had slightly but not significantly lower VPA concentrations. Patients on LTG also had significantly lower VPA levels, but this effect was only minor (-7%) and most probably not of any clinical relevance. Furthermore, the regression analysis showed that the relationship between the VPA dose per body weight and the serum concentration deviates significantly from linearity. Children less than 6 years old had lower VPA levels than older children and adults on a comparable VPA dose per body weight. Gender had no significant influence on VPA serum concentration. In addition, a subgroup of 40 patients was analyzed to see whether changing the LTG dose influences VPA serum concentrations. It did not. Thus, the authors conclude that the effect of LTG on VPA concentrations is not of clinical relevance.

Adolescent↗
PubMed1997

Reading research critically: results-group data II.

The readers of this journal are frequently confronted with statistical analysis that includes analysis of variance (ANOVA) and multivariate analysis of variance (MANOVA). This article discusses what the authors are really telling you when they use these techniques.

Analysis of Variance↗
PubMed1999

Sensitometric evaluation of four dental X-ray films using five processing solutions.

OBJECTIVES: To compare the sensitometric properties of four dental films: Ektaspeed Plus and Ultra-speed (Kodak Eastman Co, Rochester, USA) and new and previous Dentus M2 (Agfa-Gevaert, Mortsel, Belgium) in five different processing solutions. METHODS: Characteristic curves were constructed for four dental X-ray films using five different processing solutions. All films were processed manually in three sets of chemicals for manual processing: Agfa (Heraeus Kulzer, Dormagen, Germany), Kodak (Kodak-Pathé, Paris, France) and Demat (Viscopac, Athens, Greece) and two sets of chemicals for automatic processing: Dürr XR and Periomat (Dürr Dental, Bietigheim-Bissingen, Germany). Analysis of variance and regression analysis was performed to examine the factors significantly affecting film density. RESULTS: The new Dentus M2 film had comparable gradient, higher speed and lower base-plus-fog than its predecessor. It had comparable speed with Ektaspeed Plus in chemicals for automatic processing. All films had a higher speed and lower gradient when processed in the chemicals for automatic processing. The highest film speed was achieved using Dürr XR chemicals. CONCLUSIONS: The new Agfa Dentus M2 film is an E-speed film and can be considered an alternative to Ektaspeed Plus: both can be recommended for use in dental practice as they contribute to dose reduction.

Absorptiometry, Photon↗
PubMed1993

Adjustment of young adults with mental retardation in community settings: comparison of parametric and nonparametric statistical techniques.

The impact of four different statistical techniques on the interpretive process using data obtained from young adults with mental retardation in applied settings was evaluated. Our hypothesis was that no difference exists across levels of mental retardation for four dependent variables, jointly or separately, using (a) parametric multivariate analysis of variance, (b) nonparametric multivariate analysis of variance, (c) multiple nonparametric analyses of variance, and (d) multinomial logistic regression. The pattern of significance remained the same across the three classical and quasi-classical designs. Substantive differences were found using the fourth technique, multinomial logistic regression. The four techniques were compared using interpretational as well as statistical criteria.

Adult↗
PubMedDate not supplied

Distance education outcomes in clinical laboratory science.

OBJECTIVE: To compare 2 types of delivery methods for clinical laboratory science students-the technology-driven method at distance sites versus the on-site method on campus-in terms of learning outcomes. DESIGN: The independent variable in this quasi-experimental study was the delivery method consisting of interactive videoteleconferencing and on-site classroom methods. The dependent variables were learning outcomes that were determined by 2 methods: the average score on 8 posttests scheduled at periodic intervals and a national certification examination score. SETTING: Clinical laboratory science (CLS) education program at the University of Nebraska Medical Center in Omaha and at 6 clinical sites in other cities across Nebraska. PARTICIPANTS: 40 senior CLS students enrolled in a baccalaureate degree program. Control group participants were assigned to 2 clinical sites in the Omaha area, and the experimental group were assigned to 6 distant clinical sites. MAIN OUTCOME MEASURES: Data analysis consisted of descriptive statistics, 2-way analysis of variance (ANOVA), 2-way analysis of covariance (ANCOVA), repeated measures analysis of variance, and Hotellings T2. RESULTS: Results showed no significant difference between the students' examination scores based on delivery method (p > 0.05), except in the chemistry topic area. There was no significant difference in the pattern of the examination scores over the semester of learners who were instructed by interactive videoteleconferencing methods and learners who were instructed by on-site classroom methods. CONCLUSION: Results of the study generally support the use of interactive videoteleconferencing as an effective, alternative delivery method for CLS students who cannot attend class on campus. Analysis by topic areas suggests that additional studies are needed to validate the variance found in the chemistry subject area.

Adult↗
PubMed2005

[The antimicrobial effects of chitosans on oral pathogenic microbes in vitro].

PURPOSE: To study the antimicrobial activities of chitosans of different molecular weights and concentrations on oral pathogenic microbes under pH 6.5 in vitro. METHODS: The inhibition effects of chitosans of different molecular weights and different concentrations (2.0%, 1.5%, 1.0%, 0.5%) on Staphylococcus aureus, Candida albicans, Helicobacter pylori, Streptococcus mutans and Porphyromonas gingivalis in culture were investigated, and the differences of their antimicrobial activities under high temperature and after filtering were compared. One way analysis of variance, randomized block design analysis of variance and t test were used for statistical analysis. RESULTS: Chitosans of different molecular weights all showed bacteriostatic effects on Staphylococcus aureus, Candida albicans, Helicobacter pylori, Streptococcus mutans and Porphyromonas gingivalis. Low molecular weight chitosans showed the strongest effects, but the high molecular weight ones had strong effects on Streptococcus mutans (P<0.05,0.01). The bacteriostatic effects of chitosans were not affected by high temperatures (P>0.05). CONCLUSION: Chitosans have inhibitory effects on oral pathogenic microbes under pH 6.5.

Anti-Infective Agents↗
PubMedDate not supplied

Submaximal power output in adopted and biological siblings.

Submaximal power output was determined in relative steady state on a bicycle ergometer at a heart rate of 150 beats per minute (PWC150). PWC150 was measured in 880 individuals, 9 to 26 years of age, belonging to 46 sibships of adopted sibs, 66 sibships of unrelated individuals including adoptees, 33 sibships of first-degree cousins, 225 sibships of biological sibs, 56 sibships of DZ twins and 54 sibships of MZ twins. PWC150, PWC150/kg of body weight, PWC150/kg lean body mass, PWC150/cm of height and PWC150/m2 of body surface area were submitted to analysis of variance and correlation analysis after statistical control over age and sex of subjects. Few significant resemblances were found in PWC measurements for adoptive siblings, unrelated sibs and cousins. Sibling resemblance was, however, significant for the sibships of biological sibs, and of DZ and MZ twins. Interclass correlations reached significance only in pairs of biological brothers and sisters, and in pairs of DZ and MZ twins. Estimates of total genetic effect in PWC150/kg in a population of free-living children, adolescents and young adults vary from 0.30 to 0.48. It is concluded that submaximal power output is only moderately affected by the genotype.

Adolescent↗
PubMedDate not supplied

The effects of holding the newborn at delivery on paternal bonding.

Thirty-seven married first-time fathers attending uncomplicated deliveries of normal infants were randomly assigned to two groups, holding or not holding at delivery. At 12 to 36 hours postpartum, bonding behavior frequencies were recorded during ten minutes of father-infant interaction. Two observers measured the behaviors; verbal interaction, smiling, eye contact, fingertip and whole-hand touching. Analysis of the data by multivariate analysis of variance (MANOVA) and univariate analysis of variance (ANOVA) revealed no difference between the groups (p greater than .05). More bonding behaviors were noted with increased levels of education, male infants, breastfed infants, and outlet-forcep or cesarean-section deliveries. Early contact did not appear to enhance bonding, although several other factors seemed to be related, indicating a need for further study on paternal bonding.

Adult↗
PubMed1990

Correlation of ventricular area, perimeter, and conotruncal diameter with ventricular mass and function in the chick embryo from stages 12 to 24.

Ventricular form and function are interrelated during cardiovascular development. The study of muscle mechanics requires the real-time measurement of length, area, or volume. Because volume measures are not currently possible in the embryonic heart, we tested the hypothesis that end-diastolic (ED) and end-systolic (ES) ventricular perimeter, area, and conotruncal diameter correlate with ventricular mass and function in the stage 12 to stage 24 white Leghorn chick embryo. Video images of the contracting heart were recorded at 60 Hz on 1/2" videotape and studied with a custom image-analysis workstation. ED and ES video fields were selected by maximum and minimum ventricular area and were planimetered for epicardial ventricular perimeter, area, and conotruncal diameter. Data are reported as (mean +/- SEM, n greater than or equal to 8) and were tested by analysis of variance and regression analysis. Heart rate calculated from cycle length increased from 78 +/- 6 beats/min at stage 12 to 162 +/- 5 beats/min at stage 24. ED and ES area increased geometrically versus stage (y = 0.53 - 0.08x + 0.004x2, r = 0.96, p less than 0.001; and y = 0.60 - 0.09x + 0.004x2, r = 0.98, p less than 0.001, respectively). ED and ES perimeter and conotruncal diameter increased linearly versus stage (r = 0.95, p less than 0.001; r = 0.96, p less than 0.001; and r = 0.93, p less than 0.001; r = 0.93, p less than 0.001, respectively). Shortening fraction for each measurement increased from stage 12 to 16 or 18 then decreased.(ABSTRACT TRUNCATED AT 250 WORDS)

Analysis of Variance↗
PubMed2005

Continuity of care and health care costs among persons with severe mental illness.

OBJECTIVES: Although the association between continuity of care and health outcomes among persons with severe mental illness is beginning to be elucidated, the association between continuity and costs has remained virtually unexplored. The purpose of this study was to examine the relationship of continuity of care and health care costs in a sample of 437 adults with severe mental illness in three health regions of Alberta, Canada. METHODS: Service use events and costs were tracked through self-reported and administrative data. Associations between continuity and costs were examined by using analysis of variance and regression analysis. RESULTS: Mean+/-SD total, hospital, and community cost over the 17-month study period were $24,070+/-$25,643, $12,505+/-$20,991, and $2,848+/-$4,420, respectively. The difference in means across levels of observer-rated continuity was not statistically significant for total cost, but improved continuity was associated with both lower hospital cost and higher community cost. Total cost was significantly lower for patients with a higher self-rated quality of life as indicated on the EQ-5D visual analogue scale, although associations did not hold up in the regression analysis. Patients with higher functioning as rated by the Multnomah Community Abilities Scale had significantly lower total and community costs. CONCLUSIONS: The study showed a relationship between continuity of care and both hospital and community costs. The data also indicate that a relationship exists between cost and level of patient functioning. It will be necessary to conduct further studies using experimental designs to examine the impact of shifting resources from hospitals to the community, particularly for high-need patients, on continuity of care and subsequent outcomes.

Activities of Daily Living↗
PubMed1985

Analysis of the variance components in a pharmaceutical aerosol product: lodoxamide tromethamine.

The contributions of several components to the variance in lodoxamide delivery from lodoxamide tromethamine metered-dose aerosol containers have been estimated. Two aerosol lots, manufactured with mean diameters of 2.3 and 7.2 micron, exhibited approximately equal variances. The variance was apportioned to the following components: container-to-container, 27%; mouthpiece-to-mouthpiece 18%; valve-to-valve, 11%; assay, 6%. The largest single contribution to the variance (38%) is attributed to unassignable variations which include within-container variations in the dose; quality improvement efforts should concentrate on this area. Little effort should be expended to minimize the assay, valve delivery, or mouthpiece variation as their contribution to lodoxamide dose variation is small. Likewise, the bulk drug particle size did not contribute appreciably to within-lot dose variation.

Aerosols↗
PubMed1999

Effects of chemical disinfectants on surface characteristics and color of three fixed prosthodontic crown materials.

STATEMENT OF PROBLEM: Dental restorations should reproduce similar optical effects as natural tooth structure to achieve a good color match. Mismatch can result in unsatisfactory shade matching. PURPOSE: This study determined whether chemical disinfectants affected the surface texture and color of 3 fixed prosthodontic materials. MATERIAL AND METHODS: Five chemical disinfectants (Clorox, Banicide, Cidex-7, Biocide, and Multicide) in combination with 3 restorative materials (Dicor, Vita VMK ceramometal porcelain, Midas ADA type III noble casting alloy) were evaluated at 4 different times of immersion (10 minutes, 30 minutes, 24 hours, and 7 days). Changes from baseline for surface roughness and color were evaluated. Surface roughness data were recorded with a surface analyzer and color data in CIE L*a*b* color space were measured with a colorimeter. Data were analyzed with repeated measures analysis of variance and single factor analysis of variance. RESULTS: There were no statistical differences in surface roughness among disinfectants and restorative materials. However, there were statistical differences of changes in color, increase in deltaE and decrease in deltaL, among disinfectants and the noble casting alloy. CONCLUSION: Only 2 of the 3 materials evaluated, Dicor and Vita VMK ceramometal porcelain, can be used with all 5 disinfectants up to 7 days of immersion. Three chemical disinfectants (Biocide, Clorox, and Multicide) caused clinically significant color changes with the noble casting alloy after 7 days of immersion.

Analysis of Variance↗