scholarly journals Calculating non-centrality parameter for power analysis under structural equation modelling: An alternative

2021 ◽  
pp. 273-289
Author(s):  
David Adedia ◽  
Atinuke O. Adebanji ◽  
Simon K. Appiah
Keyword(s):  
Sample Size ◽  
Effect Size ◽  
Structural Equation Modelling ◽  
Structural Equation ◽  
Degrees Of Freedom ◽  
Type I Error ◽  
Estimation Methods ◽  
Type I ◽  
Power Of A Test ◽  
Equation Modelling

Identifying the most parsimonious model in structural equation modelling is of utmost importance and the appropriate power estimation methods minimize the probabilities of Type I and Type II errors. The power of a test depends on the sample size, Type I error, degrees of freedom and effect size. In this study, a modified approach of using effect size in calculating the non-centrality parameter for power is proposed. This is compared to the approach in Maccallum et al. (1996) at different degrees of freedom and sample size specifications --- taken from 50 to 2000. As the sample size increased the difference between the power of a test for both methods reduced to zero. The results showed that the values for power of a test are the same for the modified and original approaches for large sample sizes and degrees of freedom. The findings also revealed that the sample discrepancy function ($\hat{F}$) is asymptotically unbiased.

scholarly journals A Multi-faceted Mess: A Review of Statistical Power Analysis in Psychology Journal Articles

2019 ◽  
Author(s):  
Rob Cribbie ◽  
Nataly Beribisky ◽  
Udi Alter
Keyword(s):  
Sample Size ◽  
Effect Size ◽  
Power Analysis ◽  
Statistical Power ◽  
Type I Error ◽  
A Priori ◽  
Type I ◽  
Specific Level ◽  
Maximum Sample Size ◽  
Power Analyses

Many bodies recommend that a sample planning procedure, such as traditional NHST a priori power analysis, is conducted during the planning stages of a study. Power analysis allows the researcher to estimate how many participants are required in order to detect a minimally meaningful effect size at a specific level of power and Type I error rate. However, there are several drawbacks to the procedure that render it “a mess.” Specifically, the identification of the minimally meaningful effect size is often difficult but unavoidable for conducting the procedure properly, the procedure is not precision oriented, and does not guide the researcher to collect as many participants as feasibly possible. In this study, we explore how these three theoretical issues are reflected in applied psychological research in order to better understand whether these issues are concerns in practice. To investigate how power analysis is currently used, this study reviewed the reporting of 443 power analyses in high impact psychology journals in 2016 and 2017. It was found that researchers rarely use the minimally meaningful effect size as a rationale for the chosen effect in a power analysis. Further, precision-based approaches and collecting the maximum sample size feasible are almost never used in tandem with power analyses. In light of these findings, we offer that researchers should focus on tools beyond traditional power analysis when sample planning, such as collecting the maximum sample size feasible.

Refereeing articles including SEM – what should referees look for?

2020 ◽  
Vol 1 (1) ◽  
pp. 47-61 ◽  
Author(s):  
Chris Ryan
Keyword(s):  
Sample Size ◽  
Least Squares ◽  
Structural Equation Modelling ◽  
Structural Equation ◽  
Cross Sectional ◽  
Content Type ◽  
Equation Modelling ◽  
Sectional Analysis ◽  
Scale Creation ◽  
Least Squares Techniques

Purpose After expressing an initial disquiet about the nature of many studies that are published using structural equation modelling (SEM), a rationale for using the technique is provided. Given the advantages provided by the technique, the differences between covariance-based and partial least squares techniques are briefly described. The argument progresses by indicating assumptions behind the techniques and what it is that referees require before being able to properly referee the paper. Some issues are fundamental to survey-based materials and include the requirement to distinguish between importance and discriminatory power, and the over-dependency on cross-sectional analysis when making claims of generalisation. Other issues of scale creation and sample size are touched upon. This paper finishes by suggesting a checklist for referees who are asked to review papers using SEM.

scholarly journals Type I error rates and test power for some variance components estimation methods: one-way random effect model

2012 ◽  
Vol 55 (5) ◽  
pp. 506-518
Author(s):  
M. Mendeş
Keyword(s):  
Sample Size ◽  
Variance Components ◽  
Type I Error ◽  
Random Effect ◽  
Random Effect Model ◽  
Error Rates ◽  
Estimation Methods ◽  
Type I ◽  
Experimental Conditions ◽  
Test Power

Abstract. This study was conducted to compare Type I error and test power of ANOVA, REML and ML methods by Monte Carlo simulation technique under different experimental conditions. Simulation results indicated that the variance ratios, sample size and number of groups were important factors in determining appropriate methods which were used to estimate variance components. The ML method was found slightly superior when compared to ANOVA and REML methods. On the other hand, ANOVA and REML methods generated similar results in general. As a results, regardless of distribution shapes and number of groups and if n<15; ML, REML methods might be preferred to the ANOVA. However, when either number of groups or sample size was increased (n≥15) ANOVA method may also be used along with ML and REML.

scholarly journals Testing Travel Intention Model: An Empirical Study of Borobudur Temple

2020 ◽  
Vol 24 (2) ◽  
pp. 327
Author(s):  
Elvin Alvandi, Dellazenda, Sabrina O. Sihombing
Keyword(s):  
Literature Review ◽  
Empirical Study ◽  
Sample Size ◽  
Structural Equation Modelling ◽  
Structural Equation ◽  
Research Method ◽  
World Heritage ◽  
Equation Modelling ◽  
The Temple

This research aims to test the travel intention model that includes several main variables in predicting travel intention. Specifically, Borobudur temple was used to test the model because the temple was one of world heritage. Respondents were chosen by judgemental sampling and the sample size was 240. This research applied structural equation modelling to test research hypotheses. All research hypotheses were supported by data. This manuscript provide the literature review along with the development of hypotheses, research method, results and discussion, and research limitations and conclusion.

scholarly journals The Existence of Overall Satisfaction in Service Customer Relationships

2006 ◽  
Vol 8 (3) ◽  
pp. 301 ◽  
Author(s):  
Zulganef Zulganef
Keyword(s):  
Sample Size ◽  
Structural Equation Modelling ◽  
Structural Equation ◽  
Customer Behavior ◽  
Customer Relationships ◽  
Service Organizations ◽  
Customer Relationship ◽  
Survey Method ◽  
Unique Role ◽  
Equation Modelling

Garbarino and Johnson (1999) find that there is no correlation between overall satisfaction and loyalty in the field of customer relationship. Their finding indicates that satisfaction is no longer an important issue in managing service organizations. This research investigates the existence of satisfaction in service organizations, which have relationships with customers. Contrary to Garbarino and Johnson’s (1999) finding, this research finds that overall satisfaction, through commitment, has a relationship with loyalty. Hence, customer satisfaction is still a main issue with respect to managing service organizations, especially service organizations that have customer-relationship strategy. Survey method was conducted to test 12 hypotheses, and the sample of this research is customers of credit cardholders and supermarket cardholders. Sample size is 382 consisting of 196 (51.3%) credit cardholders and 186 (48.7%) supermarket cardholders. Data were analyzed using two-step structural equation modelling technique. In addition, this research also shows that investigators and managers should pay attention to affects, because affects have a unique role in relationship customer behavior.

Sample Size Requirements for Comparing Two Alpha Coefficients

2003 ◽  
Vol 27 (1) ◽  
pp. 72-74 ◽  
Author(s):  
Douglas G. Bonett
Keyword(s):  
Hypothesis Testing ◽  
Sample Size ◽  
Effect Size ◽  
Type I Error ◽  
Interval Estimation ◽  
Type I ◽  
Alpha Reliability ◽  
Reliability Coefficients

Graphs and tables are currently available for approximating the sample size needed to test the equality of two alpha reliability coefficients with desired power. These tables and graphs are limited to particular values of Type I error, power, and effect size. General formulas are derived to determine the sample size requirements for hypothesis testing with desired power and interval estimation with desired precision.

scholarly journals Statistical Power Analysis

2017 ◽  
Author(s):  
Chris Aberson
Keyword(s):  
Sample Size ◽  
Effect Size ◽  
Power Analysis ◽  
Statistical Power ◽  
Type I Error ◽  
Type I ◽  
Statistical Power Analysis ◽  
Emerging Trends ◽  
Optimal Probability ◽  
Innovative Work

Preprint of Chapter appearing as: Aberson, C. L. (2015). Statistical power analysis. In R. A. Scott &amp; S. M. Kosslyn (Eds.) Emerging trends in the behavioral and social sciences. Hoboken, NJ: Wiley.Statistical power refers to the probability of rejecting a false null hypothesis (i.e., finding what the researcher wants to find). Power analysis allows researchers to determine adequate sample size for designing studies with an optimal probability for rejecting false null hypotheses. When conducted correctly, power analysis helps researchers make informed decisions about sample size selection. Statistical power analysis most commonly involves specifying statistic test criteria (Type I error rate), desired level of power, and the effect size expected in the population. This article outlines the basic concepts relevant to statistical power, factors that influence power, how to establish the different parameters for power analysis, and determination and interpretation of the effect size estimates for power. I also address innovative work such as the continued development of software resources for power analysis and protocols for designing for precision of confidence intervals (a.k.a., accuracy in parameter estimation). Finally, I outline understudied areas such as power analysis for designs with multiple predictors, reporting and interpreting power analyses in published work, designing for meaningfully sized effects, and power to detect multiple effects in the same study.

scholarly journals KEMISKINAN MULTIDIMENSI DAN PERLINDUNGAN SOSIAL

2017 ◽  
Vol 13 (2) ◽  
Author(s):  
Abdul Khaliq ◽  
Betty Uspri
Keyword(s):  
Structural Equation Modelling ◽  
Latent Variables ◽  
Structural Equation ◽  
Social Protection ◽  
Multidimensional Poverty ◽  
Estimation Methods ◽  
Bootstrap Resampling ◽  
Data Set ◽  
Bootstrap Aggregating ◽  
Equation Modelling

<p>This research examines the important issues of multidimensional poverty and social protection. Utilizing the raw data set of Survei Sosial Ekonomi Nasional (SUSENAS) 2014, the empirical findings are estimated by Structural Equation Modelling Bootstrap Aggregating (SEM BAGGING). The method of Structural Equation Modelling Bootstrap Aggregating (SEM BAGGING) is a statistical technique that estimates the pattern of relationship between latent variables and indicators using bootstrap resampling to get a small bias from an original estimation. The estimation results found a statictically negative significant between education, health and quality of lives and multidimensional poverty. Moreover, empirical evidence shows a statistically positive effect multidimensional poverty on social protection in Indonesia. These results are robust across different estimation methods and different level of bootstrap resampling.<br />Keywords : Multidimensional Poverty, Social Protection, SEM BAGGING</p>

Sign in / Sign up

Export Citation Format

Share Document