Data Analysis Assessment: Sample Questions | Bryq
Beginner
Intermediate
Advanced
These are three sample questions from Bryq’s Data Analysis assessment, a technical test for hiring data analysts, business analysts and research analysts. The full assessment covers three levels: beginner, intermediate and advanced, from data interpretation and exploratory data analysis to hypothesis testing and statistical modeling. Each question is multiple choice, with one correct answer out of four options.
Beginner
Question
In a town, most households earn between $40,000 and $60,000 a year, but a few earn several million. Which measure best represents a typical household income?
Select your answer
The median
The mean
The mode
The range
WHY IS THIS THE CORRECT ANSWER
A few very high incomes pull the mean far above what most households earn, while the median, the middle value, isn’t affected by those extremes. For skewed data such as income, the median gives a more realistic picture of the typical case.
Intermediate
Question
A dataset shows that ice cream sales and drowning incidents rise and fall together over the year. What is the most likely explanation?
Select your answer
Hot weather increases both swimming and ice cream sales.
Eating ice cream increases the risk of drowning.
The correlation is the result of a data entry error.
Drowning incidents cause ice cream sales to rise.
WHY IS THIS THE CORRECT ANSWER
When two variables move together, a third variable may be driving both. Warm weather increases swimming and ice cream sales at the same time, so the correlation reflects a shared cause rather than a direct link between the two.
Advanced
Question
An analyst runs 20 independent A/B tests at a significance level of 0.05, on changes that in reality have no effect. About how many tests would be expected to show a “significant” result by chance?
Select your answer
1
0
5
20
WHY IS THIS THE CORRECT ANSWER
Each test has a 5% chance of a false positive when there is no real effect, so across 20 tests about 20 × 0.05 = 1 is expected to look significant by chance. Corrections such as the Bonferroni method, or controlling the false discovery rate, help avoid acting on false findings like these.
