scholarly journals Consistency and overfitting of multi-omics methods on experimental data

2019 ◽  
Vol 21 (4) ◽  
pp. 1277-1284 ◽  
Author(s):  
Sean D McCabe ◽  
Dan-Yu Lin ◽  
Michael I Love
Keyword(s):  
Experimental Data ◽  
Factor Analysis ◽  
Canonical Correlation ◽  
Cross Validation ◽  
Small Sample Size ◽  
R Package ◽  
Small Sample ◽  
Ready Availability ◽  
Variation Explained ◽  
The Relationship

Abstract Knowledge on the relationship between different biological modalities (RNA, chromatin, etc.) can help further our understanding of the processes through which biological components interact. The ready availability of multi-omics datasets has led to the development of numerous methods for identifying sources of common variation across biological modalities. However, evaluation of the performance of these methods, in terms of consistency, has been difficult because most methods are unsupervised. We present a comparison of sparse multiple canonical correlation analysis (Sparse mCCA), angle-based joint and individual variation explained (AJIVE) and multi-omics factor analysis (MOFA) using a cross-validation approach to assess overfitting and consistency. Both large and small-sample datasets were used to evaluate performance, and a permuted null dataset was used to identify overfitting through the application of our framework and approach. In the large-sample setting, we found that all methods demonstrated consistency and lack of overfitting; however, in the small-sample size setting, AJIVE provided the most stable results. We provide an R package so that our framework and approach can be applied to evaluate other methods and datasets.

Improving new product development performance by risk management

2016 ◽  
Vol 31 (3) ◽  
pp. 418-425 ◽  
Author(s):  
Mehran Salavati ◽  
Milad Tuyserkani ◽  
Seyyede Anahita Mousavi ◽  
Nafiseh Falahi ◽  
Farshid Abdi
Keyword(s):  
Risk Management ◽  
Product Development ◽  
New Product Development ◽  
Small Sample Size ◽  
New Product ◽  
Small Sample ◽  
Content Type ◽  
Total Performance ◽  
The Relationship ◽  
Npd Performance

Purpose The principal aim of this study is to investigate the relationship between technological, marketing, organizational and commercialization risk management on new product development (NPD) performance. Design/methodology/approach Based on questionnaire, the data were collected from a sample of general automotive industry in Iran. Based on theoretical considerations, a model was proposed and descriptive statistic and hierarchical regression were used to measure the relationship between risk management factors and NPD performance. Findings Data analysis revealed that if organization can amplify their knowledge and information about risk and main factors that affect NPD process, not only can they do their work better but can also increase their ability to predict future happenings that affect performance. Research limitations/implications First, due to the relatively small sample size, caution should be exercised when interpreting the results. Second, the data were collected from automotive producer in Iran, which may restrict to some extent generalizability of the findings. Practical implications The results suggest that managers should consider more attention to risk management. If managers spread the risk management in all aspects of the NPD project, total performance will be increased and it can develop the probability of NPD success. Also organizations should perform great market research due to best commercialization. Originality/value Past researches have presented complete information about NPD process. But identifying and considering the effect of the risk management parameters that are connected to the NPD process were the main thrusts to perform the study. In this paper, based on past research about risk management of NPD, the extra aspect of process that can improve total performance of NPD has been examined.

CEOs’ accounting-based attributes and earnings management strategies under mandatory IFRS adoption

2018 ◽  
Vol 19 (4) ◽  
pp. 608-625 ◽  
Author(s):  
Amel Kouaib ◽  
Anis Jarboui ◽  
Khaireddine Mouakhar
Keyword(s):  
Earnings Management ◽  
Small Sample Size ◽  
Small Sample ◽  
Moderating Effect ◽  
Audit Committees ◽  
Content Type ◽  
Ifrs Adoption ◽  
Experience Education ◽  
The Impact ◽  
The Relationship

Purpose The purpose of this paper is to focus on the moderating effect of mandatory International Financial Reporting Standards (IFRS) adoption on the relationship between chief executive officer (CEO) experience/education and earnings management in European companies. Design/methodology/approach Data from a sample of 302 European firms listed on Stoxx Europe 600 index and 596 CEOs from 2000 to 2014 are used to test the moderation model using moderation regression analysis. Findings Evidence reveals that CEO’s accounting-based attributes are negatively associated with accruals-based earnings management and positively associated with real earnings management (REM). Further, mandatory IFRS adoption significantly moderates the impact of CEO’s accounting-based traits on earnings-management activities. Research limitations/implications A small number of European firms were studied and, given the long study period, many firms with missing data were eliminated. To avoid a small sample size, countries with few observations were included, which leads to an uneven distribution between observations per country. Practical implications Findings from this paper can help: European firms to consider demographic traits when recruiting or promoting executives; the IASB to improve enforcement mechanisms and make IFRS implementation mandatory; and audit committees to effectively monitor REM. Originality/value This study is unique in providing European evidence for the moderating effect of mandatory IFRS adoption on the relationship between CEOs’ accounting experience/education and earnings management activities. This paper is also relevant as it addresses the effectiveness and efficiency of accounting literates.

The relationship between food heritage and clan culture: is “familiness” the missing link in SMEs?

2020 ◽  
Vol 123 (1) ◽  
pp. 337-354
Author(s):  
Fahimeh Khatami ◽  
Alberto Ferraris ◽  
Paola De Bernardi ◽  
Valter Cantino
Keyword(s):  
Structural Equation ◽  
Small Sample Size ◽  
Methodological Approach ◽  
Strong Relationship ◽  
Small Sample ◽  
Equation Modeling ◽  
Content Type ◽  
Clan Culture ◽  
The Relationship

PurposeThis paper empirically tests the relationship between food heritage, familiness, and clan culture, thus, highlighting the pivotal role of familiness in building robustly competitive food firms based on clan culture and food heritage.Design/methodology/approachThe methodological approach adopted is based on a quantitative analysis with data from one eco-tourist city in Iran (Torqabeh). In this regard, we developed a structured questionnaire surveying 98 small- and medium-sized enterprises (SMEs) operating in the food industry. We then used partial least squares structural equation modeling (PLS-SEM) to carry out the analysis.FindingsThe results indicate the significant positive relationship between food heritage and clan culture, and highlight the role of familiness as a strong mediator, which is also associated with a strong relationship between food heritage and clan culture.Research limitations/implicationsIn the present study, the main limitation was linked to the small sample size and data collection, which took place in only a single city; however, further research could overcome this limitation by investigating SMEs from a heterogeneous geographical context.Originality/valueThe value of this research relates to studies that have examined food heritage as a possible antecedent of familiness. Moreover, the novelty of this research is to study the concept of familiness in improving resource-based views and organizational theories.

scholarly journals A Confirmatory Factor Analysis of Student Engagement at the University of Hail, Saudi Arabia

2020 ◽  
Vol 9 (26) ◽  
pp. 181-190
Author(s):  
Ajay Singh
Keyword(s):  
Factor Analysis ◽  
Saudi Arabia ◽  
Student Engagement ◽  
Confirmatory Factor Analysis ◽  
Convergent Validity ◽  
Discriminant Validity ◽  
Small Sample Size ◽  
Small Sample ◽  
Confirmatory Factor ◽  
The University

The research aims to examine the validity of four factors (course structure, course learning outcomes, Constructiveness of learning environment, and instructors' skills) about student engagement at the University of Hail, Kingdom of Saudi Arabia. The research applied the Confirmatory factor analysis (CFA) technique to confirm and validate the four factors. The data of the small sample size of 380 students of business administration took place for analysis. These four factors consisting of 18 variables, have considered from the existing literature for examination. The research uses a survey questionnaire to collect the students' perception of these factors to validate the four-factor model. The study uses Convergent validity and Discriminant validity to construct validity. The research finding supports the construct of four-factors to confirm the model is adequately fit. The results of the research contribute to existing literature from the perspective of the students of the University of Hail, Saudi Arabia, and other similar institutions of the country and outside world. The research also has created the scope for further improvement by adding some more factors along with variables of equal importance.

scholarly journals phylopath: Easy phylogenetic path analysis in R

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e4718 ◽  
Author(s):  
Wouter van der Bijl
Keyword(s):  
Experimental Data ◽  
Path Analysis ◽  
Observational Data ◽  
Brain Size ◽  
R Package ◽  
Causal Models ◽  
Binary Variables ◽  
The Relationship

Confirmatory path analysis allows researchers to evaluate and compare causal models using observational data. This tool has great value for comparative biologists since they are often unable to gather experimental data on macro-evolutionary hypotheses, but is cumbersome and error-prone to perform. I introducephylopath, an R package that implements phylogenetic path analysis (PPA) as described by von Hardenberg & Gonzalez-Voyer (2013). In addition to the published method, I provide support for the inclusion of binary variables. I illustrate PPA andphylopathby recreating part of a study on the relationship between brain size and vulnerability to extinction. The package aims to make the analysis straight-forward, providing convenience functions, and several plotting methods, which I hope will encourage the spread of the method.

scholarly journals The relationship between chronic stress, emotion regulation and depressive symptoms in healthy older adults

2021 ◽  
Author(s):  
Vivian Huang
Keyword(s):  
Older Adults ◽  
Depressive Symptoms ◽  
Sample Size ◽  
Chronic Stress ◽  
Sex Education ◽  
Allostatic Load ◽  
Small Sample Size ◽  
Small Sample ◽  
Community Dwelling ◽  
The Relationship

The current study examined the association between chronic stress (measured in allostatic load or AL), ER, and depressive symptoms in a group of community-dwelling older adults. It was hypothesized that chronic stress levels would mediate the relationship between ER and depressive symptoms. A total of 70 older adults aged 60 and older participated in the study. There were no significant associations found in the main analyses between the AL index and depressive symptoms, as well as no significant relationship was found between ER strategies and AL index, after controlling for age, sex, education, and perceived SES. However, perceived stress significantly mediated the relationship between maladaptive ER strategies and depressive symptoms, and the relationship between adaptive ER strategies and depressive symptoms. Given the small sample size and the lack of variability of the AL index, the study would benefit from a larger sample size to clarify the present results.

scholarly journals Associations Between Sleep Quality, Household Income and Medication Adherence in Adolescents With Asthma

2021 ◽  
Vol 23 ◽  
Author(s):  
Emily Ruth Bryant ◽  
Andrea Fidler ◽  
David Fedele
Keyword(s):  
Sleep Quality ◽  
Household Income ◽  
Inhaled Corticosteroids ◽  
Rank Order ◽  
Small Sample Size ◽  
Persistent Asthma ◽  
Small Sample ◽  
Poor Sleep ◽  
Limited Power ◽  
The Relationship

Adolescents with asthma are at-risk for poor sleep quality. Little research has examined the relationship between sleep quality and inhaled corticosteroids (ICS) adherence. Individuals from lower-income backgrounds experience disparities that may alsocontribute to sleep quality. This study sought to 1) examine associations between household income and sleep quality and 2) analyze the relationship between sleep quality and ICS adherence among adolescents with asthma.Forty-one adolescents with persistent asthma (Mage = 14.83, SD = 1.28) completed the Adolescent Sleep Wake Scale (ASWS) to measure sleep quality across five subscales. Caregivers provided their estimated household income per year and completed a free response question measuring ICS adherence. Spearman’s rank-order correlations were used to examine associations between sleep quality,household income and ICS adherence. Sleep quality and household income were not significantly related (r = .262, p = .098). Sleep quality was not associated with ICS adherence (r = -.028, p = .867). Sleep quality was not significantly related to household income or ICS adherence in adolescents with asthma. Limitations include limited power given a small sample size and less reliable measures of household income and adherence therefore, future directions should focus on using more precise measures. Additional research with larger sample sizes may help better understand potential relationships between sleep quality, ICS adherence, and household income within youth with asthma.

scholarly journals Complaining Behavior: The effect of different factors on Consumer Complaining Behavior

2013 ◽  
Vol 3 (3) ◽  
pp. 203 ◽  
Author(s):  
Anam Manzoor ◽  
Muhammad Rizwan ◽  
Mehak Nazir ◽  
Nadia Perveen
Keyword(s):  
Sample Size ◽  
Significant Relationship ◽  
Quantitative Research ◽  
Small Sample Size ◽  
Prior Experience ◽  
Small Sample ◽  
Convenience Sample ◽  
Complaining Behavior ◽  
Relationship Of ◽  
The Relationship

Purpose: The aim of this paper is to comprehensively understand the determinants who affect the customer intention to complain to firm through an integrated model and also the effect of those determinants on the complaint intention and the relationship of those intentions with the complaining behavior.Design/Approach/Methodology: A quantitative research method was used based on self administered questionnaire with a sample size of 171 participants collected by using convenience sample and the results were tested through regression analysis.Findings/Results: The results shows that the complaining intention and attitude towards complaint have a significant relationship with complaining behavior while prior experience and controllability to complain have an insignificant relationship with complaining behavior. Attitude towards complaint and perceived possibility of success have a significant relationship with intention to complain. The antecedent prior experience has a significant relationship with perceived possibility of success and an insignificant relationship with attitude towards complaint. The variable controllability to complaint has a significant relationship with both perceived possibility of success and attitude towards complaint while Perceived alienation has a significant relationship with perceived possibility of success but insignificant relationship with attitude towards complaint.Limitations and recommendations: This study is conducted on a small level with small sample size. Due to which there are some insignificant relationships which can be prove as significant relationship if the sample size is large. A limited number of variables are discussed in this article. Other researchers can elaborate other variables affecting complaining behavior e.g. word of mouth, level of dissatisfaction etc.

Modeling of pharmacodynamic (PD) biomarkers (BM) related to CDK4/6 inhibition and exploratory BM-response (progression free survival [PFS]) analyses in patients with advanced breast cancer.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e14528-e14528
Author(s):  
Yanke Yu ◽  
Yuan Liu ◽  
Diane Dan Wang
Keyword(s):  
Breast Cancer ◽  
Advanced Breast Cancer ◽  
Time Course ◽  
Small Sample Size ◽  
Phase 1 ◽  
Small Sample ◽  
Advanced Breast ◽  
Longitudinal Change ◽  
Indirect Response Model ◽  
The Relationship

e14528 Background: Palbociclib (PAL) is an oral inhibitor of cyclin-dependent kinase 4 and 6 (CDK4/6) approved for advanced breast cancer (ABC). In a clinical trial, the expression levels of PD BMs related to PAL effect, including thymidine kinase (TK) in serum and phosphor-Rb (pRb) and Ki67 in skin tissues, were measured at both baseline and post-treatment in patients with ABC treated with PAL plus letrozole (LET). Pharmacokinetic (PK)/PD modeling was conducted previously to characterize the longitudinal change of pRb and Ki67. The PK/PD was further evaluated for TK and exploratory analyses were conducted to evaluate the relationship between PFS and all three BMs. Methods: The present analyses used data from a Phase 1 study evaluating the PK, PD, safety and efficacy of PAL plus LET in 26 Chinese women with ABC. A 2 compartment model was used to describe the PK of PAL. A precursor-dependent indirect response model was developed to describe the TK time course after PAL treatment. PAL effect was modeled as Imax inhibitory model. Cox proportional hazard model was used to assess the correlation of PFS with three BM metrics (baseline BM, simulated lowest BM and maximum BM change in Cycle 1). Results: The BM data included 194 TK observations from 26 patients. The PK/PD models adequately described the longitudinal change of TK, and showed PAL caused TK reduction. The estimated IC50 value was 49.5 ng/mL, similar to those for pRb and Ki67. The BM-response analyses for PFS showed that correlation was found for TK. There was a significant correlation between PFS and baseline TK (BTK) and minimum TK (MTK) in Cycle 1. A longer PFS was associated with lower BTK and lower MTK. A trend for longer PFS with higher maximum TK change in Cycle 1 was observed although the relationship was not statistically significant. Conclusions: PAL exposure had significant correlation with the reduction of all three BMs. Longer PFS was associated with lower BTK and MTK. Due to the small sample size (N = 26), this analyses result need to be confirmed in a larger study.

Sign in / Sign up

Export Citation Format

Share Document