DA0-002 Practice Test 18 — 15 Questions

Question 1

A data analyst is comparing the means of two independent groups using a t-test. The sample sizes are small and the data is not normally distributed. Which condition is violated for a valid t-test?

Accepted Answer

Normality. The t-test assumes normality of the data, especially with small samples. Violation of normality can affect the validity.

Answer

Equal variances

Answer

Independence of observations

Answer

Sample size larger than 30

Question 2

An analyst is planning an A/B test to compare two website designs. Which TWO factors should be considered when calculating the required sample size?

Accepted Answer

Desired effect size. Statistical power and desired effect size are key inputs for sample size calculations.

Answer

Data type of the outcome variable

Answer

Color scheme of the designs

Answer

Number of missing values

Question 3

After building a binary classification model, the data analyst obtains the following confusion matrix: True Positives=80, True Negatives=100, False Positives=20, False Negatives=30. What is the F1 score?

Accepted Answer

0.76. The F1 score is the harmonic mean of precision and recall. Precision = TP/(TP+FP) = 80/(80+20) = 0.80. Recall = TP/(TP+FN) = 80/(80+30) ≈ 0.7273. F1 = 2 * (0.80 * 0.7273) / (0.80 + 0.7273) ≈ 0.7619, which rounds to 0.76. Option A is correct.

Answer

0.73

Answer

0.80

Answer

0.69

Question 4

An analyst is comparing the average sales of two different store locations using a t-test. The p-value obtained is 0.03, and the significance level is 0.05. What should the analyst conclude?

Accepted Answer

Reject the null hypothesis; there is a significant difference. Since p-value (0.03) < α (0.05), we reject the null hypothesis, indicating a statistically significant difference in mean sales between the two locations.

Answer

Fail to reject the null hypothesis; no significant difference

Answer

The test is inconclusive because the p-value is too low

Answer

Accept the null hypothesis; the means are equal

Question 5

An analyst is creating a report for both technical and executive audiences. Which two strategies are effective? (Choose TWO.)

Accepted Answer

Use visual summaries for executives and detailed tables for technical. It tailors the data presentation to the audience: visual summaries (e.g., dashboards with KPIs) allow executives to quickly grasp high-level trends, while detailed tables (e.g., pivot tables or raw query results) give technical users the granularity they need for deep analysis. This dual approach ensures both groups can derive actionable insights without being overwhelmed or underwhelmed by the data.

Answer

Include all raw data in the appendix

Answer

Avoid any technical terms

Answer

Provide a single chart for all audiences

Question 6

An analyst is performing a logistic regression to predict customer churn (yes/no). The model outputs a probability of 0.75 for a particular customer. Which of the following best describes the interpretation?

Accepted Answer

There is a 75% chance that the customer will churn. Logistic regression outputs the probability that the event (churn) occurs, given the input features.

Answer

The model predicts that the customer will not churn

Answer

The customer will definitely churn because the probability is above 0.5

Answer

The odds of churning are 0.75 to 1

Question 7

A dashboard shows sales by region using a map with color intensity. Users complain that two regions with very different sales appear nearly the same color. What is the most likely cause?

Accepted Answer

The color scale uses a sequential palette with insufficient contrast. The issue is that the color scale uses a sequential palette with insufficient contrast between adjacent data values. When the color gradient is too narrow or uses similar hues, regions with significantly different sales figures map to nearly identical colors, making the visualization ineffective. This is a common problem in data visualization when the color mapping does not span the full range of the data or uses a perceptually uniform palette poorly.

Answer

The map projection is distorted

Answer

The monitor resolution is too low

Answer

Users are color blind

Question 8

In a multiple regression model, one predictor has a high p-value (0.45). What should the analyst consider doing?

Accepted Answer

Remove the predictor from the model. High p-value indicates the predictor is not statistically significant; it may be removed to simplify the model.

Answer

Transform the predictor

Answer

Keep the predictor regardless

Answer

Increase the sample size

Question 9

A data analyst is cleaning a dataset and finds that the 'age' column has several missing values. Which of the following is a valid method for handling missing numerical data?

Accepted Answer

Impute with the mean. Mean imputation is a common method for handling missing numerical data, though median or mode can also be used.

Answer

Delete the entire column

Answer

Ignore the missing values

Answer

Replace with zeros

Question 10

A university database stores student information in a normalized schema. The 'students' table has a primary key 'student_id'. The 'enrollments' table has a foreign key 'student_id' referencing 'students'. Which two of the following are true about primary and foreign keys? (Select TWO)

Accepted Answer

A foreign key ensures referential integrity between tables. A foreign key enforces referential integrity by ensuring that every value in the foreign key column of the 'enrollments' table matches a valid primary key value in the 'students' table. This prevents orphaned records and maintains consistency across related tables in a normalized relational database.

Answer

A foreign key must have the same name as the primary key it references

Answer

A foreign key can reference a column that is not a primary key

Answer

A table can have multiple primary keys

Question 11

In an A/B test, the null hypothesis states that there is no difference between the control and treatment groups. After running the test, the p-value is 0.04. Assuming α = 0.05, what is the correct conclusion?

Accepted Answer

Reject the null hypothesis. Since p-value (0.04) < α (0.05), we reject the null hypothesis, indicating a statistically significant difference.

Answer

Fail to reject the null hypothesis

Answer

Accept the null hypothesis

Answer

The test is invalid because the p-value is too low

Question 12

A retail company has collected data on monthly advertising spend (in thousands of dollars) and corresponding sales (in thousands of dollars) over the past 12 months. The analyst creates a scatter plot to visualize the relationship between advertising spend and sales. The plot shows a cluster of points with a positive trend, but there is one extreme outlier where spend was $100,000 but sales were only $20,000. Upon investigation, the analyst discovers that the outlier is due to a data entry error: the sales figure should have been $200,000. The analyst wants to present the overall trend accurately in a meeting. Which course of action should the analyst take first?

Accepted Answer

Remove the outlier and recreate the scatter plot.. Since the outlier is due to a data entry error, the appropriate first step is to correct the data (change the sales figure to $200,000) or remove the outlier, then recreate the scatter plot. This ensures the visualization accurately reflects the true relationship. Option A is incorrect: a bar chart with binned averages would still be affected by the erroneous data point and would not show the individual relationship clearly. Option B is incorrect: adding a trend line to the current plot would still be influenced by the erroneous outlier, potentially distorting the trend. Option D is incorrect: a line chart is typically used for time series data, and this is not a time series; moreover, it would still include the outlier.

Answer

Use a bar chart to show average sales per advertising spend bin.

Answer

Add a trend line using linear regression to the current scatter plot.

Answer

Change the chart type to a line chart.

Question 13

A data analyst is cleaning a dataset and finds that some records have duplicate entries based on customer ID. Which data quality dimension is most directly affected by these duplicates?

Accepted Answer

Uniqueness. Duplicates violate the uniqueness dimension, which requires each entity to be represented only once.

Answer

Timeliness

Answer

Consistency

Answer

Accuracy

Question 14

An analyst is preparing data for a clustering algorithm that uses Euclidean distance. Which TWO data preprocessing techniques should be applied to ensure all features contribute equally?

Accepted Answer

Min-max normalization. Min-max normalization and Z-score standardization both scale features to comparable ranges, preventing features with larger scales from dominating distance calculations.

Answer

Log transformation

Answer

Principal component analysis

Answer

One-hot encoding

Question 15

A data scientist builds a logistic regression model to predict customer churn (yes/no). The model outputs a probability of 0.75 for a particular customer. Which of the following best describes this output?

Accepted Answer

There is a 75% chance the customer will churn.. Logistic regression outputs a probability between 0 and 1, interpreted as the likelihood of the positive class (churn = yes).

Answer

The customer will definitely churn.

Answer

The odds of churning are 0.75 to 1.

Answer

The model is 75% accurate.