Abstract:Bu araştırmanın amacı, Eğitim Bilimleri alanında yayınlanmış, lisansüstü tezlerin, ilgili istatistiksel analize dayalı olarak, sahip oldukları varsayımların test edilme durumlarının değerlendirilmesidir. Betimsel araştırma modelinde olan bu çalışmada, Türkiye'de 2015, 2016 ve 2017 (Eylül ayına kadar) yıllarında Eğitim Bilimleri Enstitüleri tarafından yayınlanmış ve Ulusal Tez Merkezi üzerinden erişimine izin verilmiş 95 lisansüstü tez incelenmiştir. Araştırmacılar tarafından hazırlanan tez inceleme formu ile t… Show more
“…This study examined the 275 articles and the findings demonstrated that most of the articles didn't claim about the structure of variables and assumptions they need to check. Başman et al (2018) examined the thesis in educational science and found that graduate students tend to check sample size correctly; however, normality and homogeneity of variances are still problematic. Furthermore, more than half of the graduate theses didn't provide the evidence of assumption checking for normality, homogeneity of variance, multicollinearity, autocorrelation, and linear relation.…”
Section: Discussionmentioning
confidence: 99%
“…For instance, one study showed that researchers applied unpaired t-test to pair groups in experimental design (Jaykaran, 2010). Besides that, assumption checking, and usage of parametric tests can be problematic in educational research (Başman, Uluman & Tunç, 2018;Demir, Saatçioğlu & İmrol, 2016;Evrekli, İnel, Deniş & Balım, 2011;İlhan, 2016;Jaykaran, 2010;Kabaca & Erdoğan, 2007). Specifically, it was identified that some of the researchers preferred parametric tests to non-normal distribution (Evrekli et al, 2011;Jaykaran, 2010), improper statistical methods for categorical data (Erdoğan, 2001), and univariate statistical tests when they had more than one dependent variable (Kabaca & Erdoğan, 2007).…”
There are numerous problems in quantitative research in education literature. The purpose of the study was to identify the tendencies and challenges early carrier educational researchers face in quantitative data analysis. A basic qualitative design was applied. The study was conducted in four different phases and in every phase there are different samples and data collection tools. The research data was obtained from Ph.D. students, lecturers, Ph.D. thesis and Ph.D. programs. The qualitative data were collected through questionnaires, and document analysis to achieve triangulation. The descriptive analysis method was used to analyze the qualitative data for four phases. The study identified the most commonly used statistical techniques which are descriptive statistics, correlation, t-test and analysis of variances. The results of the study also demonstrated issues that novice educational researchers encountered in quantitative data analysis process. Participants had difficulties in defining the conceptual framework, finding the appropriate test and assumption check.
“…This study examined the 275 articles and the findings demonstrated that most of the articles didn't claim about the structure of variables and assumptions they need to check. Başman et al (2018) examined the thesis in educational science and found that graduate students tend to check sample size correctly; however, normality and homogeneity of variances are still problematic. Furthermore, more than half of the graduate theses didn't provide the evidence of assumption checking for normality, homogeneity of variance, multicollinearity, autocorrelation, and linear relation.…”
Section: Discussionmentioning
confidence: 99%
“…For instance, one study showed that researchers applied unpaired t-test to pair groups in experimental design (Jaykaran, 2010). Besides that, assumption checking, and usage of parametric tests can be problematic in educational research (Başman, Uluman & Tunç, 2018;Demir, Saatçioğlu & İmrol, 2016;Evrekli, İnel, Deniş & Balım, 2011;İlhan, 2016;Jaykaran, 2010;Kabaca & Erdoğan, 2007). Specifically, it was identified that some of the researchers preferred parametric tests to non-normal distribution (Evrekli et al, 2011;Jaykaran, 2010), improper statistical methods for categorical data (Erdoğan, 2001), and univariate statistical tests when they had more than one dependent variable (Kabaca & Erdoğan, 2007).…”
There are numerous problems in quantitative research in education literature. The purpose of the study was to identify the tendencies and challenges early carrier educational researchers face in quantitative data analysis. A basic qualitative design was applied. The study was conducted in four different phases and in every phase there are different samples and data collection tools. The research data was obtained from Ph.D. students, lecturers, Ph.D. thesis and Ph.D. programs. The qualitative data were collected through questionnaires, and document analysis to achieve triangulation. The descriptive analysis method was used to analyze the qualitative data for four phases. The study identified the most commonly used statistical techniques which are descriptive statistics, correlation, t-test and analysis of variances. The results of the study also demonstrated issues that novice educational researchers encountered in quantitative data analysis process. Participants had difficulties in defining the conceptual framework, finding the appropriate test and assumption check.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.