نوع مقاله : مقاله پژوهشی
نویسندگان
1 گروه آمار، دانشکده علومپایه، دانشگاه قم، قم، ایران.
2 گروه علم اطلاعات و دانششناسی، دانشکده علوم انسانی، دانشگاه قم، قم، ایران.
چکیده
کلیدواژهها
عنوان مقاله [English]
نویسندگان [English]
Objective: Statistical methods play an important role in achieving results and conducting analyses. The current study aims to analyze the status of statistical methods in articles of knowledge and information science. While reviewing the statistical methods used in articles, it also investigates the frequency of methodological issues.
Methods: The nature of the research is a descriptive survey. The research population comprises articles published in 13 active journals in knowledge and information science in Iran until 2022. Using Cochran’s formula, 141 articles were randomly selected for this study. The research methodology was investigated in three areas: statistical methods, sampling methods, and validity and reliability. Additionally, the variables influencing the characteristics of the articles and their statistical errors were examined. Data analysis was performed using Excel and SPSS 26 software, employing descriptive statistics methods.
Results: The statistical methods have been used a total of 599 times, with the most frequent application being related to descriptive statistics. Among parametric and non-parametric inferential statistical methods, the T-test, chi-square, and the Kolmogorov-Smirnov test are the most commonly employed in parametric and non-parametric inferential statistical methods, respectively. In the section on predictive methods and post hoc tests, the correlation coefficient and Tukey’s test stand out as the most frequent choices. Notably, the research results reveal that the most common statistical error observed in the articles is the use of parametric tests without verifying the normality of the data.
Conclusions: The findings of the research show that although the authors of the articles use descriptive statistics effectively in their work, they pay less attention to inferential statistical methods. An essential consideration when employing parametric methods is ensuring that the underlying assumptions of the tests are met, as violating these assumptions can invalidate research results.
کلیدواژهها [English]
)