ICDL Data Analytics (ICDL) study plan
ICDL Data Analytics · Give each week a clear focus.
8 weeks · About 7 hours per week
Data analytics concepts and fundamentals
Define the four levels of analytics (descriptive, diagnostic, predictive, prescriptive) and match each to a workplace scenario
Classify data by type (qualitative vs quantitative, discrete vs continuous, nominal vs ordinal) using 20 labelled examples
Describe the stages of the data lifecycle from capture to disposal and state the risk at each stage
Explain the difference between a population and a sample, and between a parameter and a statistic
Your checkpoint
A one-page personal glossary of 25 core analytics terms, each with an original example, plus a 20-question self-quiz scored at 80% or higher
Data analytics concepts and fundamentals & Data preparation and management
Distinguish primary from secondary data sources and rate three sources for reliability and recency
Evaluate a dataset against the six data-quality dimensions (accuracy, completeness, consistency, timeliness, validity, uniqueness)
Apply confidentiality and data-protection principles by identifying which fields in a sample dataset require anonymisation
Document metadata for a dataset: field names, data types, permitted values, and ownership
Your checkpoint
A data-quality audit of a 50-row sample dataset that records at least 10 specific quality defects, each with a severity rating and a proposed fix
Data preparation and management
Clean a raw dataset by removing duplicates, trimming whitespace, and standardising date and text formats
Handle missing values by choosing and justifying deletion, imputation, or flagging for each affected field
Convert data types correctly (text to number, text to date) and validate the conversion with spot checks
Apply filters, sorts, and calculated fields to restructure a dataset for analysis
Your checkpoint
A cleaned version of the week-2 dataset accompanied by a transformation log listing at least 15 changes, each with the reason and the before/after value
Data preparation and management & Data analysis and interpretation
Aggregate data using count, sum, mean, median, minimum, maximum, and mode, and state when each is appropriate
Group and summarise data by at least two categorical dimensions
Detect and explain outliers using the interquartile range rule
Reconcile summary totals against source records to confirm no records were lost during transformation
Your checkpoint
A summary report presenting 10 computed statistics on the cleaned dataset, each independently recalculated a second way and confirmed to match
Data analysis and interpretation
Identify trends and seasonality in a time-ordered dataset and describe them in plain language
Distinguish correlation from causation and rewrite three causal-sounding claims as correlation-only statements
Compare two groups using percentage change and per-capita normalisation rather than raw totals
Interpret results against the original business question and note the limits of the conclusion
Your checkpoint
A written analysis answering 5 questions about the dataset, each with the method used, the supporting figures, and an explicit statement of one limitation
Data analysis and interpretation & Data visualisation and reporting
Select an appropriate chart type for eight different analytical questions and justify each choice
Identify misleading visualisation practices such as truncated axes, inconsistent scales, and cherry-picked ranges
Apply the data-to-ink principle by simplifying one cluttered chart into a clear version
Structure a narrative that moves from headline finding to supporting evidence to recommended action
Your checkpoint
A chart-selection matrix mapping 8 question types to chart types with a written justification, plus one before/after chart redraw
Data visualisation and reporting
Build a one-page dashboard with at least five visuals that share consistent colours, labels, and units
Apply accessibility basics: sufficient contrast, readable font sizes, and non-colour-dependent encoding
Write three key findings as action-oriented headlines rather than neutral chart titles
Add source notes, date stamps, and axis labels so the report is self-explanatory without narration
Your checkpoint
A single-page dashboard containing 5 visuals and 3 headline findings, checked against a 10-point design and accessibility checklist
Data analytics concepts and fundamentals & Data preparation and management & Data analysis and interpretation & Data visualisation and reporting
Consolidate the four domains into one end-to-end case: raw data in, cleaned data, analysis, and visual report out
Complete a timed 60-question mock exam under exam conditions
Categorise every incorrect answer by domain and by error type (knowledge gap vs misreading)
Re-study the two weakest sub-topics and re-test them to confirm improvement
Your checkpoint
A full mock exam scored at 80% or higher, plus a gap log listing each error, its domain, and the corrective action taken
Milestones
Week 1: Recite the four analytics levels and correct-classify 18 of 20 data-type examples without notes
Week 2: Produce the quality audit unaided and correctly name the quality dimension for at least 8 of the 10 recorded defects
Week 4: Show a cleaned dataset that passes a duplicate and type check, and summary totals that reconcile exactly to the source record count
Week 6: Justify a chart choice for 7 of 8 question types and identify all three deliberately planted misleading features in a practice chart
Week 8: Score 80% or higher on the timed mock exam with no single domain below 70%