Interactive statistics

An interactive statistics worksheet in Dataiku DSS provides a dedicated interface for performing exploratory data analysis (EDA) on datasets. Using this feature, you can:

• Summarize or describe data samples, e.g. using univariate analysis, bivariate analysis, distribution & curve fitting, and correlation matrices. This falls under the area of descriptive statistics.

• Draw conclusions from a sample dataset about an underlying population, e.g. using hypothesis testing. This falls under the area of inferential statistics.

• Visualize the structure of the dataset in a reduced number of dimensions, using principal component analysis. This falls under the area of dimensionality reduction.

This section of the reference documentation covers the DSS Worksheet and performing EDA tasks in DSS.

• The Worksheet Interface
  • Elements of a worksheet
  • Elements of a card
    • Types of cards
• Univariate Analysis
  • Card options
    • Histogram
      • Numerical histogram
      • Categorical histogram
    • Box Plot
    • Summary Stats
    • Quantile Table
    • Frequency Table
    • Cumulative Distribution Function
• Bivariate Analysis
  • Card options
    • Histogram
    • Box Plot
    • Mosaic Plot
    • Scatter Plot
    • Summary Stats
    • Frequency Table
• Fit curves and distributions
  • Fit Distribution
  • 2D Fit Distribution
  • Fit curve
• Statistical Tests
  • One-sample tests
    • Student t-test (one-sample)
    • Sign test (one-sample)
    • Shapiro-Wilk test
  • Two-sample tests
    • Student t-test (two-sample)
    • Median mood test (two-sample)
    • Kolmogrov-Smirnov test (two-sample)
  • N-sample tests
    • One-way ANOVA
    • Median mood test (N-samples)
    • Pairwise student t-test
    • Pairwise median mood test
  • Categorical test
    • Chi-square independence test
• Multivariate Analysis
  • Principal Component Analysis (PCA)
  • Correlation matrix
  • Scatter plot 3D
  • Parallel Coordinates Plot
• Time Series Analysis
  • Stationarity and unit root tests
    • Augmented Dickey-Fuller (ADF) test
    • Zivot-Andrews test
    • Kwiatkowski-Phillips-Schmidt-Shin (KPSS) test
  • Trend
    • STL decomposition plot
    • Mann-Kendall trend test
  • Auto-correlation
    • Auto-correlation function plot
    • Partial auto-correlation function plot
    • Durbin-Watson statistic
• Assisted Data Exploration