Grouping Records Before Calculating Averages in Data Exploration
Short answer
D Group records by student identifier so the average score is aggregated within each student before any per-student statistic is reported.
Question
Which of the following exploration techniques should the analyst have considered before calculating the average?
Key Takeaways
The question tests whether you recognize that a per-category statistic (average per student) is only meaningful after grouping records by that category; the trap is picking duplication, redundancy, or binning, which solve unrelated data-quality problems.
In data exploration, computing an average score per student requires first grouping records by the student identifier so the aggregate is calculated within each category. This question establishes that grouping is the appropriate exploration technique, because duplication and redundancy address repeated data and binning discretizes continuous values into ranges.
Common mistake: The most common wrong answers are duplication and redundancy, since learners associate any table that repeats student names with duplicate data — but repeated rows per student are legitimate records (multiple scores), not errors to remove. Binning is also mis-picked, though it converts numeric values into intervals rather than enabling per-student aggregation.
Expert Analysis
Why the Answer Is Correct
Grouping (option D) partitions the table by the student key so that each student's rows are aggregated together, which is the only way an "average score per student" can be computed at all. Exploration techniques such as grouping let the analyst inspect the structure of the data — one row per score, several rows per student — before applying aggregations. As Amelia233 noted, "the analyst needs to calculate the score for each student separately," and grouping by student then averaging produces an accurate individual result. Without grouping, an average over the raw table yields one single overall mean, which is not the requested per-student statistic.
Why the Other Options Are Wrong
Duplication (A) and redundancy (B) are data-quality checks that detect duplicate records or unnecessary overlapping columns; a student appearing on multiple rows with different scores is not duplicate or redundant data, so removing those rows would corrupt the dataset. Binning (C) is an exploration technique that segments continuous values into intervals (for example, score bands of 0–59, 60–79, 80–100) for histogram-style analysis, and it does nothing to aggregate records by student. None of these three techniques establishes the category boundaries required for a per-student average; only grouping does.
Community Comment Notes
The lone community comment argues for option D, explaining that "Grouping should be considered before calculating the average" and explicitly rejecting duplication, redundancy, and binning for the same reasons given above. That reasoning aligns with the exam blueprint's data exploration guidance and with the question's wording that no changes were made to the table before the average was calculated. No dissenting comments appear, so the vote record is not available to cross-check, but the technical justification is sound.
Exam Strategy
On DA-002 aggregation questions, identify the grouping key implied by the phrasing ("per student," "per region") and choose the option that partitions by that key. Read carefully whether an option removes data (duplication, redundancy) or reshapes values (binning) — neither enables a per-category average.
Frequently Asked Questions
Why isn't binning the right exploration technique before calculating an average?
Why is duplication not an issue when a student appears on several rows?
Discussion 2 contributions
Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.
From public community threads 2
-
6b7911d 👍 1 Answered AA is correct. The table has two exact duplicate rows. Student 123 has Chemistry 80 listed twice, and student 234 has Math 96 listed twice. The analyst left the table unchanged, so both duplicates were counted. That drops student 123’s average to 86.67 instead of 90 and raises student 234’s to 94.67 instead of 94. The analyst should have checked for and removed duplicates first. D is wrong. Grouping by Student ID is how the analyst got a per-student average, so it was already done. It also doesn’t fix the problem, because grouping with the duplicates still in place gives the same wrong averages. B is wrong. Redundancy means the same information stored in more than one place, like the TypeID column built from Type and ID. Repeated identical rows are duplication. C is wrong. Binning groups values into ranges, which has nothing to do with this issue.
-
Amelia233 👍 1 Answered DGrouping should be considered before calculating the average because the analyst needs to calculate the score for each student separately. By grouping records by student, the analyst can then calculate an accurate average for each individual. Duplication and redundancy deal with repeated data, while binning divides values into ranges. 👉 Final Answer: D. Grouping ✅
Reader comments & corrections
No reader corrections yet — spotted an error or have a note? Share it below.
Related Analysis
Practice All DA0-002 Questions
Access 100 questions with complete answers and detailed explanations.
View Full DA0-002 Practice Test →