Garuda - Garba Rujukan Digital

Analisis Kolerasi dan Analisis Regresi Andrian, M; Fadilah G S, Mila; Panggabean, Hadi Saputra
AURELIA: Jurnal Penelitian dan Pengabdian Masyarakat Indonesia Vol 4, No 2 (2025): July 2025
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/aurelia.v4i2.6787

This study examines the essential statistical methods of correlation analysisand regression analysis, as highlighted in seminal literature indexed in Scopus. Correlation quantifies the strength and direction of linear relationships between continuous variables, typically expressed via Pearson’s r (ranging from –1 to +1) Regression analysis further extends this relationship into a predictive model through the least squares method, resulting in an equation of the form Y = mX + b, where m is the slope and b is the intercept . We emphasize the importance of verifying data assumptions (e.g., linearity, normality, homoscedasticity) before application . The synergy between correlation and regression offers both relational insight and predictive capability, demonstrating wide utility across fields such as biostatistics, social sciences, economics, and engineering

Ukuran Pemusatan Data Siregar, Siti Aisyah; Zahrach, Eca May; Panggabean, Hadi Saputra
AURELIA: Jurnal Penelitian dan Pengabdian Masyarakat Indonesia Vol 4, No 2 (2025): July 2025
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/aurelia.v4i2.6864

Calculating research results, especially in the social sciences, is not easy. This is because findings in the social sciences do not always show a direct impact on the treatment being studied, unlike other scientific research. For example, in studying the effect of experimental methods on student insight, a qualitative approach is often used to analyze the results. In this article, we provide an example of research that analyzes the mean, median, and mode values. The analysis was carried out manually by relying on the mathematical skills of experts. However, to obtain broader and more valid results in social science research, we recommend the use of computational software such as SPSS and Microsoft Excel. In conclusion, research in the social sciences has a higher level of complexity, and to process and draw conclusions from the data, researchers are advised to utilize various data analysis applications.

Analisis Varians dan Uji Signifikansi F Aghna, Hannah; Ramadhani, Mutia; Hidayah, Naillah; Panggabean, Hadi Saputra
AURELIA: Jurnal Penelitian dan Pengabdian Masyarakat Indonesia Vol 4, No 2 (2025): July 2025
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/aurelia.v4i2.6783

This study discusses the use of Analysis of Variance (ANOVA) and the F-test for significance, which are statistical methods designed to test significant differences between the means of three or more groups. ANOVA works by comparing variability between groups, using the F-test to support the process based on the F-distribution to assess the significance of the observed differences. This article provides a comprehensive discussion of the fundamental concepts of analysis of variance, the steps involved in conducting the F-test, and the statistical interpretation of the test results. The explanation is presented in a systematic and easy-to-understand approach, making it helpful for researchers or students in understanding and applying ANOVA in the context of quantitative research. By understanding analysis of variance and the F-test for significance, researchers can draw valid conclusions based on data and improve the quality of evidence-based decision-making.

Uji Signifikansi Distribusi T Sabiru, Tri; Al ‘Auni, Khofifah; Panggabean, Hadi Saputra
AURELIA: Jurnal Penelitian dan Pengabdian Masyarakat Indonesia Vol 4, No 2 (2025): July 2025
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/aurelia.v4i2.6756

The t-Student distribution is an important tool in statistical analysis, especially for hypothesis testing and determining confidence intervals on small samples. Introduced by William Sealy Gosset, this distribution excels at accommodating greater uncertainty than the normal distribution, making it ideal when the population standard deviation is unknown. This research uses the literature study method to explore the characteristics of the t distribution and its applications in various fields, including psychology, medical, and education. The t-test procedure involves setting the hypothesis, calculating the t value, and determining the critical value, which helps the researcher in making statistical decisions. The t-test results provide significant insights into the differences between groups and relevance in designing more effective teaching strategies. Further research is needed to explore the potential of the t distribution in wider applications and develop more innovative methods of analysis.

Statistika Non- Parametrik Mulyani, Ika Dini; Ismy, Nurul; Panggabean, Hadi Saputra
AURELIA: Jurnal Penelitian dan Pengabdian Masyarakat Indonesia Vol 4, No 2 (2025): July 2025
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/aurelia.v4i2.6752

Non-parametric statistics is an essential tool in data analysis, particularly when the assumption of normal distribution cannot be met. This method offers a flexible approach applicable to various types of data, including ordinal and nominal data. This article explores the fundamental principles, methodologies, and challenges of using non-parametric statistics, highlighting advantages such as more lenient assumptions and ease of calculation. Despite its limitations, especially regarding the testing of parametric assumptions and large sample sizes, non-parametric statistics remain a relevant choice. Guidelines for the use of one-sample, two-sample, and more than two-sample tests are presented, along with practical examples such as the binomial test, chi-square test, and Wilcoxon test. With a deep understanding of this method, researchers and practitioners are expected to make better decisions based on valid and reliable data analyses.

Konsep Statistika Inferensial, Hipotesis dan Pengujian Hipotesis, Taraf Signifikansi Fitriani, Sulia; Manurung, Nazwa Salsabila Br; Anggraini, Dian Sri; Panggabean, Hadi Saputra
AURELIA: Jurnal Penelitian dan Pengabdian Masyarakat Indonesia Vol 4, No 2 (2025): July 2025
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/aurelia.v4i2.6786

Inferential statistics enables drawing conclusions about a population from sample data. Hypothesis testing involves formulating a null hypothesis (H₀) and an alternative hypothesis (H₁). A p-value indicates the probability of obtaining results at least as extreme as those observed, assuming H₀ is true. If the p-value is less than the predetermined significance level (α), commonly set at 0.05, H₀ is rejected in favor of H₁, suggesting statistical significance. Tests can be one-tailed or two-tailed, depending on the research question's directionality. Type I errors (false positives) and Type II errors (false negatives) are risks in hypothesis testing. Controlling these errors involves careful selection of α and consideration of the test's power, which is the probability of correctly rejecting a false null hypothesis. In studies involving multiple comparisons, adjustments such as the Bonferroni correction and the Holm–Bonferroni method are employed to control the family-wise error rate, thereby reducing the likelihood of Type I errors across multiple tests. These techniques adjust the significance thresholds to maintain the overall error rate within acceptable bounds.

Ukuran Letak Puspita, Laila Dwi; Putri, Saskia Amanda; Panggabean, Hadi Saputra
AURELIA: Jurnal Penelitian dan Pengabdian Masyarakat Indonesia Vol 4, No 2 (2025): July 2025
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/aurelia.v4i2.6766

This study aims to examine the concept and application of measures of position in educational statistics. Measures of position include quartiles, deciles, and percentiles, which are used to determine the relative position of a value within a data distribution. The research methodology employed is a literature review by analyzing various relevant sources, including educational statistics textbooks and scientific articles. The results of the discussion indicate that measures of position are essential in analyzing students' academic achievement, as they provide a detailed picture of data distribution. The main issue addressed in this study is the lack of students’ understanding regarding the application of measures of position in educational contexts. The data analyzed were derived from literature studies and examples of how measures of position are applied in analyzing students' exam scores. The conclusion of this study is that understanding measures of position can help educators and researchers assess individual achievements within a group more fairly and accurately.

Uji Signifikansi Distribusi T Sabiru, Tri; Al ‘Auni, Khofifah; Panggabean, Hadi Saputra
AURELIA: Jurnal Penelitian dan Pengabdian Masyarakat Indonesia Vol 4, No 2 (2025): July 2025
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/aurelia.v4i2.6756

The t-Student distribution is an important tool in statistical analysis, especially for hypothesis testing and determining confidence intervals on small samples. Introduced by William Sealy Gosset, this distribution excels at accommodating greater uncertainty than the normal distribution, making it ideal when the population standard deviation is unknown. This research uses the literature study method to explore the characteristics of the t distribution and its applications in various fields, including psychology, medical, and education. The t-test procedure involves setting the hypothesis, calculating the t value, and determining the critical value, which helps the researcher in making statistical decisions. The t-test results provide significant insights into the differences between groups and relevance in designing more effective teaching strategies. Further research is needed to explore the potential of the t distribution in wider applications and develop more innovative methods of analysis.

Statistika Non- Parametrik Mulyani, Ika Dini; Ismy, Nurul; Panggabean, Hadi Saputra
AURELIA: Jurnal Penelitian dan Pengabdian Masyarakat Indonesia Vol 4, No 2 (2025): July 2025
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/aurelia.v4i2.6752

Non-parametric statistics is an essential tool in data analysis, particularly when the assumption of normal distribution cannot be met. This method offers a flexible approach applicable to various types of data, including ordinal and nominal data. This article explores the fundamental principles, methodologies, and challenges of using non-parametric statistics, highlighting advantages such as more lenient assumptions and ease of calculation. Despite its limitations, especially regarding the testing of parametric assumptions and large sample sizes, non-parametric statistics remain a relevant choice. Guidelines for the use of one-sample, two-sample, and more than two-sample tests are presented, along with practical examples such as the binomial test, chi-square test, and Wilcoxon test. With a deep understanding of this method, researchers and practitioners are expected to make better decisions based on valid and reliable data analyses.

Konsep Statistika Inferensial, Hipotesis dan Pengujian Hipotesis, Taraf Signifikansi Fitriani, Sulia; Manurung, Nazwa Salsabila Br; Anggraini, Dian Sri; Panggabean, Hadi Saputra
AURELIA: Jurnal Penelitian dan Pengabdian Masyarakat Indonesia Vol 4, No 2 (2025): July 2025
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/aurelia.v4i2.6786

Inferential statistics enables drawing conclusions about a population from sample data. Hypothesis testing involves formulating a null hypothesis (H₀) and an alternative hypothesis (H₁). A p-value indicates the probability of obtaining results at least as extreme as those observed, assuming H₀ is true. If the p-value is less than the predetermined significance level (α), commonly set at 0.05, H₀ is rejected in favor of H₁, suggesting statistical significance. Tests can be one-tailed or two-tailed, depending on the research question's directionality. Type I errors (false positives) and Type II errors (false negatives) are risks in hypothesis testing. Controlling these errors involves careful selection of α and consideration of the test's power, which is the probability of correctly rejecting a false null hypothesis. In studies involving multiple comparisons, adjustments such as the Bonferroni correction and the Holm–Bonferroni method are employed to control the family-wise error rate, thereby reducing the likelihood of Type I errors across multiple tests. These techniques adjust the significance thresholds to maintain the overall error rate within acceptable bounds.

Title

Found 65 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 65 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 65 Documents
Search