Biostatistics series module 10: Brief overview of multivariate methods

There has been a recent call to improve data reporting in kinesiology journals, including the appropriate use of univariate and multivariate analysis techniques. For example, a multivariate analysis of variance (MANOVA) with univariate post hocs and a Bonferroni correction is frequently used to investigate group differences on multiple dependent variables. However, this univariate approach decreases power, increases the risk for Type 1 error, and contradicts the rationale for conducting multivariate tests in the first place. Purpose: The purpose of this study was to provide a user-friendly primer on conducting descriptive discriminant analysis (DDA), which is a post-hoc strategy to MANOVA that takes into account the complex relationships among multiple dependent variables. Method: A real-world example using the Statistical Package for the Social Sciences syntax and data from 1,095 middle school students on their body composition and body image are provided to explain and interpret the results from DDA. Results: While univariate post hocs increased the risk for Type 1 error to 76%, the DDA identified which dependent variables contributed to group differences and which groups were different from each other. For example, students in the very lean and Healthy Fitness Zone categories for body mass index experienced less pressure to lose weight, more satisfaction with their body, and higher physical self-concept than the Needs Improvement Zone groups. However, perceived pressure to gain weight did not contribute to group differences because it was a suppressor variable. Conclusion: Researchers are encouraged to use DDA when investigating group differences on multiple correlated dependent variables to determine which variables contributed to group differences.

The objectives of this investigation was to determine the effectiveness of Mindfulness Based Stress Reduction (MBSR) intervention for reducing anxiety, enhancing self-control and improving academic performance among adolescent students. The present study consisted of 300 adolescent students in the age group of 15-18 years, selected through random sampling. State-Trait Anxiety Inventory by Spiel berger et al. and Self-control Scale by Tangney et al. were administered to 150 boys and 150 girls and their academic scores were collected from their performance in continuous assessment. Pre-test and post-test with randomized control group design was used for the present study. MBSR was given to the students in the experimental group for a period of 8 weeks while the control group did not receive the intervention, following which a post-test was carried out. Statistical analyses such as Independent sample't' test, Paired t test, Multi variate Analysis of Variance (MANOVA) and Multi variate Analysis of Covariance (MANCOVA) were used for this study. The results indicate that MBSR is effective for reducing anxiety, enhancing self-control and improving academic performance among adolescent students. This intervention ensured that students could use it for their well-being not only at the present, but also in the future circumstances. Therefore, MBSR may be included in the school curriculum in order to help adolescent students who cope with the expectations and challenges of educational demands.

Historically, behavior analytic research and practice have been grounded in the single subject examination of behavior change. Within the behavior analytic community, there remains little doubt that the graphing of behavior is a powerful strategy for demonstrating functional control by the independent variable; however, during the past thirty years, various statistical techniques have become a popular alternative form of evidence for demonstrating a treatment effect. Concurrently, a mounting number of behavior analytic investigators are measuring multiple dependent variables when conducting statistical analyses. Without employing strategies that protect the experimentwise error rate, evaluation of multiple dependent variables within a single experiment is likely to inflate the Type I error rate. In fact, with each additional dependent variable examined in univariate fashion, the probability of “incorrectly” identifying statistical significance increases exponentially as a function of chance. Multivariate analysis of variance (MANOVA) and several other statistical techniques can preclude this common error. We provide an overview of the procedural complications arising from methodologies that might inflate the Type I error rate. Additionally, we provide a sample of reviewer comments and suggestions, and an enrichment section focusing on this somewhat contentious issue, as well as a number of statistical and neural network techniques that enhance power and preclude the inflation of Type I error rates

The primary purpose of this study was to investigate group counselors’ counter transference reactions toward their clients who provoked the counselors’ strong emotions in a counseling group and the related factors as family-of-origin experience and training level in Taiwan. Using the Ratings of Emtional Attitudes to Client by Therapist Scale (REACT) and the Family-of-Origin Scale (FOS), 73 group counselors in Taiwan reported their counter transference and family-of-origin experiences in this study. The factor analysis, Cronbach’s alpha (, and split-half correlation revealed overall acceptable validity and high reliability of the Chinese version of the REACT and FOS. Analysis of variance (ANOVA), multivariate analysis of variance (MANOVA), and multiple regression analysis were applied to the data collection. The major findings were as follows: (a) novice counselors reported significantly stronger counter transference feelings than the experienced counselors; (b)novice counselors perceived early family experiences similarly to experienced counselors, however, on the “acceptance of loss” factor the experienced counselors reported better family experiences than did novice counselors; (c) counselors who perceived better or worse family-of-origin experiences did not have did not have different counter transference experiences in group counseling; and (d) counter transference scores were significantly affected by training level; the four FOS factor and hours of counseling experience did make a contribution to the prediction of the REACT scores, but the contribution was not unique. Factor IV (trust) of the FOS was the only predictor at the significance level of .05 on countertransference reaction. These findings may be useful for counselor educators, counseling researchers, and counselors to emphasize the counter transference phenomenon and family background in counseling. Recommendations were provided fro future studies which would be important in developing instruments for assessing counter transference as well as improving counselor education and supervision programs in Taiwan.

Objective To investigate the statistical.method for analyzing nurse job burnout Data. Methods Hotelling T2 test and multivariate analysis of variance(MANOVA)were used to analyze nurse job burnout datum. Results There was statistical significance between different cities,different ethnieities in the personal achievements,hut from three dimensions of the whole job burnout,there are no statistical sig-nificant differences among different cities, different ethnicities and different ages. Conclusions The use of Hotelling T2 test and multivariate analysis of variance to analyzing nurse job burnout data, not only ob-tain overall conclusion, and further use of single-variable analysis may also gain comparative results of each dimensions. Key words: Job burnout; Hotelling T2 test; Multivariate analysis of variance

Background: Deficiency of sleep among nurses working in shifts, results in sleepiness, fatigue, health, and safety problem, and it also can deteriorate the quality of care provision. The present study aimed to compare sleepiness and fatigue between night-shift nurses who have a 3-h nap and day-shift nurses. Methods: A prospective cohort study was done on 23 night-shift nurses with a 3-h nap and 24 day-shift nurses in Sina Hospital in Tehran (Iran) during 2015–2016. Subjective sleepiness and fatigue before and after their shifts were measured by Stanford Sleepiness Scale (SSS) and Swedish Occupational Fatigue Inventory (SOFI-20), respectively. Statistical analysis including independent t-test, Mann–Whitney test, multivariate analysis of variance, and discriminant analysis were performed to compare the two groups. Results: The difference in means of subjective sleepiness before and after the shifts was significantly greater among night-shift nurses having a 3-h nap (1.43±1.50) than the day-shift nurses (0.37±0.92) (P=0.007). Although after their working shifts, the night-shift nurses (1.40±2.30) were more fatigued than the day-shift ones (0.96±1.46), this was not statistically significant (P=0.81). Moreover, day or night shift working with a 3-h nap was an effective factor (P=0.015) while considering the interrelationship between sleepiness and fatigue in multivariate analysis. Discriminant analysis revealed the dominant role of subjective sleepiness in differentiating the two groups. Conclusions: Despite the 3-h nap, subjective sleepiness was seen more among the night-shift nurses than the day-shift ones; however, the mean difference scores of fatigue did not differ between the two groups. Presumably, getting a 3-h nap during night shift and a heavy work load for day-shift nurses might result in insignificant fatigue between the groups. Furthermore, studies with new strategies for napping among nurses are recommended.

Means comparisons using multivariate analysis of variance (MANOVA) is a useful though somewhat complex statistical approach for comparing independent groups across multiple dependent measures. In the field of applied linguistics, studies using MANOVA remain few, though its application has been seen across many areas including language assessment, acquisition, psycholinguistics, and textual analysis. As with any statistical method of this relative complexity, MANOVA relies upon several empirical assumptions that need to be examined prior to analysis, though the interpretations that it can provide in terms of both statistical significance and effect can offer a unique approach to examining the effects of group differences across a number of separate but related measured variables. To that end, this entry will cover the main considerations necessary for setting up, running, and interpreting MANOVA in practical and theoretical terms.

PART ONE: FROM THEORY TO METHODOLOGY Types of Research Problems and Research Situations A Classification of Classical Techniques of Multivariate Analysis The Analysis Technique as the Mirror of the Research Problem PART TWO: FROM METHODOLOGY TO ANALYSIS The Experimental Design The Effect of Humour on Financial Concession Multiple Regression Analysis The Causes of Childlessness Partial Correlation and Path Analysis The Causal Influence of Christian Beliefs on Anti-Semitism Analysis of Variance and Covariance The Effect of Interaction of Monetary Rewards and Task Interest on Motivation Two-Group Discriminant Analysis Poor and Rich Neighbourhoods Factor Analysis The Investigation of Marital Adjustment Canonical Correlation Analysis The Study of Economic Inequality and Political Instability Techniques with Multiple Dependent Variables

Multivariate regression is known as a multivariate extension of multiple regression, which explain/predict the variations in multiple dependent variables by multiple independent variables. Recently, various procedures for Sparse Multivariate Regression (SMR) have been proposed, in which a sparse regression coefficient matrix (having a number of zero elements) is obtained aiming to facilitate its interpretation. The procedures for SMR can be classified into the following two types; penalized and cardinality-constrained procedures. In them, the resulting number of zeros in the regression coefficient matrix is controlled/constrained by a prespecified penalty parameter or cardinality value. In this research, we propose another approach for SMR, referred to as Layered Multivariate Regression (LMR). In LMR, the regression coefficient matrix is assumed to be a sum of several sparse matrices, which is called layer. Therefore, the sparseness of the resulting coefficient matrix is controlled by how many layers are used. In LMR, k-th layer can be viewed as the coefficient matrix in the regression of a partial residual (i.e., the residual for all but k-th layer) on independent variables, and thus the variance explained by LMR gets closer to that for the unconstrained regression as the number of layers increases. We present an alternating least squares algorithm for LMR and a procedure for determining how many layers should be used. LMR is assessed in a simulation study and illustrated with a real data example. As an application of LMR, procedures for sparse estimation in some multivariate analysis techniques (e.g., principal component analysis) are also presented.

<abstract xmlns="http://www.w3.org/1999/xhtml"> This study aimed to determine the degree to which supplier development initiatives create a favourable environment for promoting sustainable procurement. Sustainable procurement was modelled as a three-factor construct comprising economic, environmental, and social pillars, following the Triple Bottom Line (TBL) framework. Suppliers were evaluated based on three metrics of sustainable performance. A total of 398 suppliers were evaluated in the Bindura district, which is a key tobacco-farming region in Zimbabwe. A positivist research philosophy was adopted with its attendant quantitative research design. The three constructs comprising the TBL were operationalised using measurement scales distilled from the extant literature to ensure content and construct validity. An Exploratory Factor Analysis (EFA) conducted in SPSS (v26) and a Confirmatory Factor Analysis (CFA) and a Multi-Group Confirmatory Factor Analysis (MG-CFA) run on Analysis of Moment Structures (AMOS) data analysis software were used to validate the measurement scales. A Multivariate Analysis of Variance (MANOVA) and related post hoc Analysis of Variance (AVOVA) run on SPSS data analysis software was used for hypothesis testing. The results reveal that supplier development has a statistically significant effect on all three constructs constituting the TBL framework. The study concluded that developed suppliers (contract farmers) performed better than independent farmers in terms of sustainable performance, thereby enabling tobacco merchants to practice sustainable procurement effectively. It is therefore recommended that supplier development initiatives (contract farming) be expanded to enhance sustainable procurement. </abstract>

Schema therapy has been used in the treatment of various disorders, including depression, anxiety, personality disorders, and couples' incompatibility and has suggested promising outcomes. Therefore, the present study aimed to investigate the effects of schema therapy on emotion regulation, happiness, and procrastination among the staff of healthcare centers. This was a quasi-experimental study with a pretest-posttest and a control group design. The experimental groups received eleven 90-minute (once a week) schema therapy sessions, while the control group received no intervention. The statistical population consisted of the staff of comprehensive health centers in the east of Tehran City, Iran. In total, 40 samples were selected through systematic sampling method. The subjects were randomly divided into the test and control groups (20 samples per group). Considering the experimental nature of the study and eliminating the effect of pretest, the study groups were compared using the Analysis of Covariance (ANCOVA). In addition, Multivariate Analysis of Covariance (MANCOVA) and Analysis of Variance (ANOVA) were applied for testing the primary and secondary hypotheses, respectively. The obtained data were analyzed applying statistics like mean and standard deviation, as well as Multivariate Analysis of Variance (MANCOVA) in SPSS. There were significant differences between the two experimental and control groups in terms of emotion regulation (P

Problem. A report of the perceptions of the environment of an institution can be useful inassessing the effectiveness of that institution. This study assessed student and faculty perceptions of the religious environment of Andrews University, a Seventh-day Adventist (SDA) school. Method. An instrument developed for the study was administered to 350 randomly selected subjects in eight subsamples: non-SDA students, faculty, freshmen, sophomores, juniors, seniors, theological seminary students, and other graduate students. The instrument consisted of inventories to measure perceptions of the religious environment and subject religiosity. Approximately 75% of the subjects completed the instrument. Scores were analyzed by analysis of variance, analysis of covariance (with religiosity as a covariate), multivariate analysis of variance, discriminant analysis, correlation, and enumeration. Results. Analysis of the data revealed: (1) that faculty and non-SDA students perceived the religious environment more positively than SDA students did; (2) that differences in the perceptions of the environment by undergraduate and graduate (non-seminary) students, graduate and theological seminary students, and male and female students were not statistically significant; (3) that positiveness of perception of the environment varied directly with degree of subject religiosity; (4) that early home influence on the development of religious experience and ratio of time spent in SDA and public schools before college did not affect perception of the environment; (5) that a majority of the subjects believed that the overall religious emphasis of Andrews University was weaker than they thought it should be; (6) that faculty, graduate students, and theological seminary students scored higher on religiosity than other subjects did; (7) that subjects assessed their religiosity more positively than they assessed the religious environment. Conclusions. The following conclusions emerged from the study: (1) Subjects perceived the religious environment as moderately positive, with perceptions of faculty and non-SDA studentsbeing more positive than those of SDA students. (2) Subjects at higher levels of religiosity perceived the environment more positively than other subjects did. (3) Religiosity of subjects was moderately high, with faculty, seminary students, and graduate students scoring higher than other subjects.

Fatigue Susceptibility of the Lumbar Extensor Muscles among Smokers

This study examined potential predictors of suicidal ideation among a nonclinical, rural adolescent population. A sample of 76 male and female adolescents enrolled in a rural public high school completed a personal information form, a suicide information questionnaire, short forms of the Beck Depression Inventory and the Family Environment Scale, and the Life Events Checklist. A stepwise multiple regression suggested significant predictive relationships between magnitude of suicidal ideation and measures of family social climate (i.e., Organization, Conflict, Expressiveness, and Independence subscales from the Family Environment Scale--Short Form). Multivariate analyses of variance and a discriminant-function analysis revealed no significant sex differences.

Rice straw is a major kind of biomass that can be utilized as lignocellulosic materials and renewable energy. Rapid prediction of the lignocellulose (cellulose, hemicellulose, and lignin) and organic elements (carbon, hydrogen, nitrogen, and sulfur) of rice straw would help to decipher its growth mechanisms and thereby improve its sustainable usages. In this study, 364 rice straw samples featuring different rice subspecies (japonica and indica), growing seasons (early-, middle-, and late-season), and growing environments (irrigated and rainfed) were collected, the differences among which were examined by multivariate analysis of variance. Statistic results showed that the cellulose content exhibited significant differences among different growing seasons at a significant level (p < 0.01), and the contents of cellulose and nitrogen had significant differences between different growing environments (p < 0.01). Near infrared reflectance spectroscopy (NIRS) models for predicting the lignocellulosic and organic elements were developed based on two algorithms including partial least squares (PLS) and competitive adaptive reweighted sampling-partial least squares (CARS-PLS). Modeling results showed that most CARS-PLS models are of higher accuracy than the PLS models, possibly because the CARS-PLS models selected optimal combinations of wavenumbers, which might have enhanced the signal of chemical bonds and thereby improved the predictive efficiency. As a major contributor to the applications of rice straw, the nitrogen content was predicted precisely by the CARS-PLS model. Generally, the CARS-PLS models efficiently quantified the lignocellulose and organic elements of a wide variety of rice straw. The acceptable accuracy of the models allowed their practical applications. Keywords: rice straw, near infrared reflectance spectroscopy models, rapid prediction, competitive adaptive reweighted sampling, partial least-squares, lignocellulose DOI: 10.25165/j.ijabe.20191202.4374 Citation: Diallo A A, Yang Z L, Shen G H, Ge J Y, Li Z C, Han L J. Comparison and rapid prediction of lignocellulose and organic elements of a wide variety of rice straw based on near infrared spectroscopy. Int J Agric & Biol Eng, 2019; 12(2): 166–172.