Excel for Data Analytics · Lesson 8
Explore sales data before reporting. Use sorting, filtering and evidence-based questions to discover patterns, top performers and unusual records.
Complete both the activity and MCQ for each concept, then explicitly complete the lesson.
EXPLORATORY ANALYSIS · CONCEPT 1 OF 8
Before creating a dashboard, an analyst should understand what is actually happening inside the dataset. Sorting and filtering are simple Excel tools, but they are powerful ways to discover patterns and ask better business questions.
Step 1 of 2 · Analyst thinking
What should an analyst do before building a dashboard from a new sales dataset?
Analyst Workflow
Sort and filter the complete dataset, compare groups, investigate unusual records, and separate what the data shows from assumptions about why a pattern occurred.
Understand the dataset
Find high and low values
Focus the question
Find patterns
Separate evidence from assumptions
Final Analyst Challenge
Management needs to know which regions and products deserve further investigation. Explore the raw data, sort and filter complete records, compare high and low values, and validate unusual results before drawing conclusions.
01
What needs investigation?
02
Sort and filter records
03
Compare groups and extremes
04
Check evidence and unusual values
Explore → Sort → Filter → Compare → Investigate
Sorting and filtering are important Excel skills for data analytics. They help analysts explore datasets, identify high and low values, investigate specific groups and discover patterns before creating reports and dashboards.
Sorting revenue from largest to smallest can help identify high-value transactions. Sort the entire table so each row remains attached to its related fields.
Excel filters allow analysts to focus on selected regions, products, salespeople or multiple conditions to answer specific business questions.
Exploratory Data Analysis (EDA) examines data structure, patterns, unusual values and relationships before conclusions are made. Analysts should investigate outliers rather than automatically deleting them.
Analysts should separate what the data directly shows from assumptions about why a pattern occurred. Additional evidence is needed to explain causes.