Сравнение методов
Просматривайте выбранные методы рядом; строки с различиями подсвечены.
| Робастный количественный контент-анализ× | Байесовский количественный контент-анализ× | |
|---|---|---|
| Область | Дизайн исследования | Дизайн исследования |
| Семейство | Process / pipeline | Process / pipeline |
| Год появления≠ | 1980s–2000s (systematic application of robust statistics to content analysis) | 1990s–2000s (convergence of content analysis and Bayesian statistics) |
| Автор метода≠ | Klaus Krippendorff; Kimberly Neuendorf (systematic codification); robust statistics tradition from Peter Huber (1964) | Integration of Krippendorff's content analysis framework with Bayesian statistical inference (Gelman et al.) |
| Тип≠ | Quantitative research design with robust statistical estimation | Quantitative research design |
| Основополагающий источник≠ | Neuendorf, K. A. (2002). The Content Analysis Guidebook. Sage Publications. ISBN: 978-0761919773 | Krippendorff, K. (2018). Content Analysis: An Introduction to Its Methodology (4th ed.). Sage. ISBN: 978-1506395661 |
| Другие названия | robust content analysis, outlier-resistant content analysis, robust QCA, robust text frequency analysis | Bayesian content analysis, Bayesian text analysis, probabilistic content analysis, BQCA |
| Связанные≠ | 4 | 5 |
| Сводка≠ | Robust quantitative content analysis is a systematic method for coding and counting manifest or latent features of communication content — texts, images, or media — while applying statistical estimators that are resistant to outliers, skewed distributions, and coding inconsistencies. By combining the structured coding protocol of classical content analysis with robust statistical measures, it produces frequency and association estimates that are less distorted when data violate normality assumptions or contain extreme values. | Bayesian quantitative content analysis systematically codes and counts features in textual or media content, then quantifies patterns and tests hypotheses using Bayesian statistical inference. Unlike classical frequency-based content analysis, it incorporates prior knowledge or domain expectations into the estimation process, producing posterior probability distributions over content parameters rather than single point estimates with p-values. The approach is particularly valuable when prior research, expert knowledge, or pilot data exist and when uncertainty quantification around content proportions and category frequencies is important. |
| ScholarGateНабор данных ↗ |
|
|