If it so happens that I make mistakes and harm the reproducibility of my research, the last thing I want is to hide it.
Eğer araştırmalarımda farkında olmadan bir hata yaptıysam, isteyeceğim son şey onu örtbas etmektir. Bu sayfada elimden geldiğince bütün araştırmalarımın veri setini ve analiz basamaklarını paylaşıyorum.
A Pilot Study for the Development of University Student Mentoring Scale
Manuscript after reviewer comments
Citation
Gök, E , Aydın, B . (2017). Yükseköğretim Öğrenci Mentörlük Ölçeği Geliştirme Yolunda Pilot Bir Çalışma. Kırıkkale Üniversitesi Sosyal Bilimler Dergisi, 7 (1), 107-120. Retrieved from http://dergipark.gov.tr/kusbd/issue/27579/290380
Abstract: This study, as one of the first studies within the context of student affairs administration, designed to translate the “College Student Mentoring Scale” developed by Crisp (2009) into Turkish and ascertain its adaptability for Turkish university students. 390 students from the faculties of education and theology at Recep Tayyip Erdoğan University participated in the study. Of which, 71% are female and 29% are male. Language, construct and face validity results are reported. Scale reliability results reported as Cronbach Alpha 0.87 and alternatively Omega 0.87. In obtaining a Turkish scale (model 3A) through confirmatory factor analysis, the researchers observed a good model-data fit. There are some limitations to consider: convenient sampling technique was used and two items are removed without suggesting alternative items. This study urges new university mentoring scales to be developed.
Keywords: Higher education, university student mentoring scale, student affairs administration
Multilevel Models: The Two Level Model With Continuous Variables and an Empirical Example Using R
Citation
Aydin, B. (2016). "Çok Düzeyli Modeller: Sürekli Değişken ile İki Düzeyli Model Örneği ve R Programı ile Analizi", Ege Eğitim Dergisi, cilt.2, ss.567 -596, 2016
Abstract
This article is crafted to provide basic theory, a definition of important issues and an application of a two-level regression model. It aims to enrich social scientists’ methodological knowledge and equip them with appropriate theories and tools to deduce defensible inferences they draw from statistical analyses. The basic theory with Kuehl (2000), Snijders and Bosker (2012), and Swaminathan and Rogers (2008) were introduced. An illustrative example was included and the R syntax was provided (see supplementary). Keywords: Multilevel regression, Hierarchical Models, R
The Effects of Including Observed Means or Latent Means as Covariates in Multilevel Models for Cluster Randomized Trials
Simulation and analyses code (see APPENDIX B)
Citation
Aydin, B., Leite, W. L., & Algina, J. (2016). The effects of including observed means or latent means as covariates in multilevel models for cluster randomized trials. Educational and Psychological Measurement, 76, 803–823. doi:10.1177/ 0013164415618705
Abstract
We investigated methods of including covariates in two-level models for cluster randomized trials to increase power to detect the treatment effect. We compared multilevel models that included either an observed cluster mean or a latent cluster mean as a covariate, as well as the effect of including Level 1 deviation scores in the model. A Monte Carlo simulation study was performed manipulating effect sizes, cluster sizes,
We investigated methods of including covariates in two-level models for cluster randomized trials to increase power to detect the treatment effect. We compared multilevel models that included either an observed cluster mean or a latent cluster mean as a covariate, as well as the effect of including Level 1 deviation scores in the model. A Monte Carlo simulation study was performed manipulating effect sizes, cluster sizes, number of clusters, intraclass correlation of the outcome, patterns of missing data, and the squared correlations between Level 1 and Level 2 covariates and the outcome. We found no substantial difference between models with observed means or latent means with respect to convergence, Type I error rates, coverage, and bias. However, coverage could fall outside of acceptable limits if a latent mean is included as a covariate when cluster sizes are small. In terms of statistical power, models with observed means performed similarly to models with latent means, but better when cluster sizes were small. A demonstration is provided using data from a study of the Tools for Getting Along intervention.