Linked from

The 24 pages that link to Exploratory data analysis, each with the reason it gives.

• Data visualizationRelated: Visualization can serve discovery before a specific statistical claim is tested.

• Statistical inferenceCompared with: Exploration can generate hypotheses, while confirmatory inference evaluates specified claims.

• Principal component analysisRelated: PCA plots can expose broad patterns and outliers in many-variable datasets.

• Multiple comparisons problemRelated: Searching many patterns can yield chance findings that need independent confirmation.

• CorrelationNarrower topic: Pairwise correlations are a common first summary of relationships among measured variables.

• Data journalismRelated: Exploration helps journalists find leads before deciding what the data can establish.

• Descriptive statisticsRelated: It overlaps with descriptive summaries but emphasizes open-ended investigation.

• Scientific visualizationCompared with: Visualization supports exploration, but exploratory analysis also includes nonvisual statistical techniques.

• Pearson correlation coefficientRelated: Correlation matrices quickly screen pairwise linear associations among measured variables.

• Scatter plotNarrower topic: Scatter plots reveal unexpected structure before assumptions are chosen.

• Histogram (statistics)Narrower topic: Histograms are a standard tool for inspecting a variable’s distribution before modeling.

• Data miningCompared with: It overlaps with mining but emphasizes open-ended examination and human-guided summaries.

• Interquartile rangeNarrower topic: The IQR quickly describes central spread during initial data inspection.

• Data scienceRelated: It reveals patterns, anomalies, and assumptions worth testing.

• Data analysisRelated: It reveals structure, anomalies, and candidate explanations early in analysis.

• Statistical graphicsRelated: Plots help expose unexpected patterns before formal modeling begins.

• QuartileRelated: Quartiles reveal distribution spread and potential outliers during initial data inspection.

• Statistical hypothesis testCompared with: Exploration generates patterns and questions, while formal testing evaluates prespecified claims.

• Correlation coefficientRelated: Pairwise coefficients offer compact summaries before a model is chosen.

• Statistical analysisCompared with: It explores patterns without beginning from a narrowly specified confirmatory test.

• Stem-and-leaf displayNarrower topic: A stem-and-leaf display offers a compact first look at a small numerical dataset.

• Violin plotNarrower topic: Violin plots help reveal distribution features before formal modeling.

• Data and Information VisualizationRelated: Visual displays help expose unexpected structure and generate hypotheses.

• Eyeball theoremNarrower topic: Eyeballing is most defensible as an exploratory step that generates questions.