What to study for each PCAD-31-02 domain
Data Acquisition and Pre-Processing
Covers data collection methods, ethics, anonymization, and multi-source aggregation, plus storage in warehouses, lakes, CSV, Excel, and cloud formats. It also covers cleaning and standardization including missingness mechanisms MCAR, MAR, and MNAR, imputation, normalization and scaling, encoding, outliers, validation, integrity, and extraction including web scraping with BeautifulSoup and requests.
Key skills
Collecting and aggregating data from multiple sources, handling missing data and outliers, applying imputation, encoding and scaling, validating data integrity, and extracting data from files and web pages.
Programming and Database Skills
Covers Python syntax, control flow, data structures, functions, module and PIP management, exception handling, and object-oriented programming for data modeling. It also covers SQL queries with SELECT, JOINs, WHERE, GROUP BY, HAVING, ORDER BY and LIMIT, SQL CRUD operations, and Python-database connections using sqlite3 and pymysql.
Key skills
Writing Python for data work, querying and modifying relational data with SQL joins and aggregations, and connecting Python to databases with sqlite3 using parameterized queries.
Statistical Analysis
Covers descriptive statistics including measures of center and spread and the interpretation of distributions and correlation. It also covers inferential statistics including hypothesis testing, p-values, and confidence intervals for drawing conclusions from samples.
Key skills
Summarizing data with descriptive statistics, interpreting correlation and distributions, and applying hypothesis tests and confidence intervals correctly.
Data Analysis and Modeling
Covers analysis with Pandas, NumPy, Matplotlib, and Seaborn, including DataFrame manipulation, grouping, merging, and handling missing values. It also covers foundational machine learning with regression, train/test evaluation, error metrics, and overfitting.
Key skills
Analyzing data with Pandas and NumPy, building and evaluating basic regression models, and assessing performance with metrics such as R-squared and MAE without data leakage.
Data Communication and Visualization
Covers choosing and building effective visualizations for distributions, comparisons, trends, and relationships. It also covers audience-tailored reporting that leads with insights, labels measures and units clearly, and avoids misleading design choices.
Key skills
Selecting appropriate chart types, creating clearly labeled visualizations, and communicating findings and recommendations tailored to the audience.