What kinds of statistical tools are available?

A quick overview of statistical tools Querri can use

Querri knows a lot of statistical tools. Here is just a quick synopsis of the types of things that you can try. Please note that while these tools are sometimes used to build models which then generate future predictions, Querri is currently using them to primarily answer questions about your existing data.

  • Descriptive Statistics — Understand basic properties of a dataset.

    • e.g., "What's the average monthly sales figure for our top products?"
  • T-Test — Determine if two groups are significantly different.

    • e.g., "Is there a significant difference in sales between our two most popular products?"
  • ANOVA (Analysis of Variance) — Check for significant differences among multiple groups.

    • e.g., "Are there regional sales differences among our top-performing branches?"
  • Linear Regression — Understand the impact of one variable on another.

    • e.g., "How does advertising spend influence our monthly sales figures?"
  • Logistic Regression — Estimate the likelihood of an event.

    • e.g., "Based on browsing behavior, how likely is a site visitor to make a purchase?"
  • Decision Trees — Understand decision pathways and influential factors.

    • e.g., "What factors most influence whether a customer renews their subscription or not?"
  • Random Forest — Derive insights from an ensemble of decisions.

    • e.g., "Which features play a significant role in determining if a transaction might be fraudulent?"
  • K-Means Clustering — Identify natural groupings in data.

    • e.g., "How can we group our products based on sales patterns?"
  • Principal Component Analysis (PCA) — Summarize data with many variables.

    • e.g., "Can we get a simplified view of our customer survey responses to see the main patterns?"
  • Time Series Analysis — Forecast and understand temporal patterns.

    • e.g., "What might our sales figures look like for the next six months based on past trends?"
  • Chi-Squared Test — Examine relationships between categorical variables.

    • e.g., "Is there a notable association between product category preference and customer age group?"
  • Cross-Validation — Validate the reliability of insights from models.

    • e.g., "How consistent are our predictions about customer churn across different data sets?"