Data Analysis

  1. Introduction to Data Analysis

    A comprehensive guide to the data analysis process, covering key steps from data collection through interpretation. Learn about systematic approaches to examine, clean, transform, and model data for extracting valuable insights and supporting decision-making.

  2. Data Collection

    Data collection for clinical research: sources, formats, sampling and the design choices that determine what your dataset can answer.

  3. Data Formats

    Explore the benefits and limitations of data formats like CSV, JSON, XML, YAML, Excel, SQL Databases, Parquet, and HDF5. Learn how Python, with its powerful libraries, enhances data analysis through efficient data handling and integration.

  4. Data Cleaning

    Data cleaning in Python: handling errors, inconsistencies, duplicates and impossible values before analysing a clinical dataset.

  5. Data quality assessment

    How to assess data quality before analysis: completeness, accuracy, consistency and plausibility checks on clinical datasets in Python.

  6. Missing data

    Missing data explained: MCAR, MAR and MNAR mechanisms, and how deletion or imputation choices change your clinical results.

  7. Duplicate data

    Guide to handling duplicate data: causes, risks (including healthcare), detection and removal with Pandas, plus scalable solutions with Dask and Vaex.

  8. Outliers

    A comprehensive guide to understanding, identifying, and managing outliers in datasets using statistical methods and visualization techniques. Includes practical implementations in Python and SPSS, covering IQR, Z-scores, and various approaches to outlier detection and treatment in data analysis.

  9. Normalization, Standardization and Scalers

    A detailed guide to data transformation techniques including normalization and standardization, with mathematical formulas and practical Python implementations using scikit-learn. Covers various scaling methods, their applications in machine learning, and visual demonstrations using matplotlib.

  10. Organization of Variables

    How to organise variables in a clinical dataset: types, roles, naming and structure, so that the analysis stays reproducible and readable.

  11. Exploratory Data Analysis

    A comprehensive guide to Exploratory Data Analysis (EDA), featuring practical implementation using Python and the Iris dataset. It covers statistical analysis, data visualization techniques, correlation analysis, and hypothesis testing using ANOVA and Tukey's HSD, with detailed code examples and interpretations.