DA0-002 Data Analysis Practice Test 4 — 15 Questions

Question 1

A data analyst is evaluating a linear regression model predicting house prices. The analyst wants to assess whether the model meets key assumptions. Which TWO of the following should the analyst check? (Choose two.)

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Linearity between predictors and the outcome. Linear regression relies on several assumptions for valid inference, including linearity, homoscedasticity, independence of residuals, and normality of residuals. The analyst should verify linearity and homoscedasticity to ensure the model is well-specified and standard errors are reliable. Checking predictor independence or outcome normality are common misconceptions, while outlier presence is not a formal assumption.

Answer

Normal distribution of the outcome variable

Answer

Independence of predictors from each other

Answer

Absence of outliers in the predictors

Question 2

A data analyst is preparing a dataset for a machine learning model and needs to handle missing values in a numerical feature. The analyst wants to use imputation methods that preserve the distribution of the data and avoid introducing bias. Which TWO of the following imputation methods are most appropriate? (Choose two.)

Accepted Answer

Multiple imputation. Median imputation and multiple imputation are both appropriate for numerical data. Median imputation is robust to outliers and skewness, while multiple imputation models missing values to preserve relationships and uncertainty. Mean imputation reduces variance, mode imputation is for categorical data, and listwise deletion discards data, so they are not suitable.

Answer

Listwise deletion

Answer

Mode imputation

Answer

Mean imputation

Question 3

A data analyst at an e-commerce company is examining the relationship between the number of daily website visits and daily sales revenue. After plotting the data, the analyst observes a non-linear, S-shaped pattern that suggests diminishing returns at high visit counts. The analyst decides to fit a logistic regression model, but the outcome variable is continuous revenue, not binary. Which of the following is the most appropriate next step?

Accepted Answer

Fit a generalized additive model (GAM) with a smooth spline for visits to flexibly model the non-linear trend.. The S-shaped pattern with diminishing returns is a non-linear relationship that is not well handled by logistic regression (which requires a binary outcome) or by simple transformations like logarithmic or polynomial terms. A generalized additive model with a spline offers the flexibility to model such complex curves while keeping the outcome continuous. This approach is appropriate for capturing the nuanced relationship between website visits and revenue, providing a better fit and more accurate insights.

Answer

Transform the revenue variable into a binary outcome (e.g., high vs. low revenue) and proceed with logistic regression.

Answer

Apply a logarithmic transformation to the revenue variable and fit a linear regression.

Answer

Use a polynomial regression with a squared term for visits to capture the non-linear relationship.

Question 4

A data analyst is evaluating the performance of a classification model that predicts customer churn. The dataset is highly imbalanced, with only 5% of customers churning. The analyst wants to select appropriate evaluation metrics to assess the model's effectiveness in identifying churners. Which TWO of the following metrics should the analyst prioritize? (Choose two.)

Accepted Answer

Recall. In imbalanced classification, accuracy is misleading because it can be high even when the minority class is poorly predicted. Precision and recall are more informative: precision focuses on the correctness of positive predictions, while recall focuses on capturing actual positives. Together, they help evaluate the model's ability to identify churners without excessive false alarms. AUC-ROC and MSE are less appropriate here because AUC-ROC does not emphasize threshold-specific performance, and MSE is for regression.

Answer

Area Under the ROC Curve (AUC-ROC)

Answer

Accuracy

Answer

Mean Squared Error (MSE)

Question 5

A data analyst is compiling a monthly operations report and must join a table of 1.2 million shipment records to a lookup table of 4,500 carrier codes. After the join, the record count is 1.44 million. The analyst confirms the shipment table has no duplicate shipment IDs and the carrier table has no duplicate carrier codes. Which type of join most likely produced this result?

Accepted Answer

A left outer join, because every shipment row is retained and unmatched carrier codes are populated as nulls. The row count grew by exactly the number of shipment rows whose carrier codes match more than one lookup record, which is the signature of a one-to-many match preserved by an outer join. Because shipment IDs are unique and the analyst believed carrier codes were unique, the unexpected multiplication must come from duplicate carrier codes on the right side of the join, and the outer join that retains all shipments is the operation consistent with that outcome.

Answer

A cross join, because every shipment is paired with every carrier code, producing a Cartesian product

Answer

An inner join, because only matching carrier codes are retained and the row count should stay at 1.2 million

Answer

A full outer join, because unmatched rows from both tables are combined and duplicates removed

Question 6

A data analyst is assessing the quality of a dataset before analysis. The dataset contains customer records with fields such as age, income, and purchase date. The analyst notices that some age values are negative, some income values are missing, and purchase dates are in inconsistent formats. Which TWO of the following data quality dimensions are most directly violated by these issues? (Choose two.)

Accepted Answer

Completeness. Negative age values violate accuracy because they are incorrect representations of reality. Missing income values violate completeness because required data is absent. While inconsistent date formats could relate to consistency or validity, the most direct violations from the described issues are accuracy and completeness.

Answer

Timeliness

Answer

Validity

Answer

Consistency

Question 7

A data analyst needs to identify the most frequently occurring value in a dataset. Which measure of central tendency should they use?

Accepted Answer

Mode. The mode is the measure of central tendency that identifies the most frequently occurring value in a dataset. Unlike the mean or median, the mode directly counts the frequency of each distinct value and returns the value with the highest count, making it the correct choice for this specific requirement.

Answer

Standard deviation

Answer

Median

Answer

Mean

Question 8

A retail company wants to predict future sales based on historical data. Which modeling approach is most appropriate if the data shows a clear seasonal pattern?

Accepted Answer

Time series analysis. Time series analysis is specifically designed to model data points indexed in time order, making it ideal for capturing and forecasting seasonal patterns. Unlike regression models, it accounts for autocorrelation, trends, and seasonality components, which are critical for accurate sales prediction from historical data.

Answer

Linear regression

Answer

K-means clustering

Answer

Logistic regression

Question 9

A data analyst is building a model to predict customer churn. The dataset has 10,000 records with 500 churned customers. The model predicts churn with 95% accuracy, but only identifies 10% of actual churners. Which metric best highlights this issue?

Accepted Answer

Recall. Recall (also known as sensitivity or true positive rate) measures the proportion of actual positives correctly identified. With only 10% of actual churners detected, the model has a recall of 0.1, which directly highlights the failure to capture churners despite high overall accuracy.

Answer

Accuracy

Answer

F1 score

Answer

Precision

Question 10

A data analyst is performing a hypothesis test with a significance level of 0.05. The p-value obtained is 0.03. What should the analyst conclude?

Accepted Answer

Reject the null hypothesis. Since the p-value (0.03) is less than the significance level (0.05), the result is statistically significant. This means the observed data provides sufficient evidence to reject the null hypothesis in favor of the alternative hypothesis. The analyst should conclude that there is a statistically significant effect or difference.

Answer

Fail to reject the null hypothesis

Answer

Accept the null hypothesis

Answer

The result is practically significant

Question 11

A data scientist trains a regression model and observes high variance with low bias. Which technique is most appropriate to reduce variance?

Accepted Answer

Apply Ridge regularization. Ridge regularization (L2) reduces variance by adding a penalty term proportional to the square of the coefficients, which shrinks them toward zero without eliminating them. This directly addresses high variance (overfitting) by constraining the model's complexity, while low bias indicates the model fits the training data well. The regularization parameter λ controls the trade-off between bias and variance.

Answer

Increase polynomial features

Answer

Use a smaller training set

Answer

Remove correlated features

Question 12

A data analyst is cleaning a dataset and finds missing values in a categorical variable representing customer region. Which imputation method is most appropriate?

Accepted Answer

Mode imputation. Mode imputation is the most appropriate method for a categorical variable because it replaces missing values with the most frequently occurring category, preserving the distribution of the data. Unlike mean or median imputation, which are designed for numerical data, mode imputation maintains the categorical nature of the variable and avoids introducing invalid values. This approach is simple and effective when missing data is random and the category is well-represented.

Answer

Drop rows with missing values

Answer

Mean imputation

Answer

Median imputation

Question 13

A company is analyzing customer feedback sentiment. The dataset is highly imbalanced with 95% positive and 5% negative comments. Which technique should the analyst use to address class imbalance before modeling?

Accepted Answer

Use SMOTE. SMOTE (Synthetic Minority Oversampling Technique) is the correct choice because it generates synthetic samples for the minority class (negative comments) by interpolating between existing minority instances, rather than simply duplicating them. This addresses the 95:5 imbalance without the information loss of undersampling or the overfitting risk of naive oversampling.

Answer

Use accuracy as the evaluation metric

Answer

Undersample the majority class

Answer

Oversample the majority class

Question 14

Which THREE of the following are appropriate methods to handle outliers in a dataset?

Accepted Answer

Transforming the data using log transformation. Log transformation (A) is correct because applying a log (or similar power) transform compresses the scale of extreme values, reducing the leverage of right-skewed outliers and making the distribution more symmetric for downstream models. Removing the outlier records (B) is correct when outliers are confirmed to be data-entry errors or otherwise invalid observations, since deleting them prevents distortion of statistics such as the mean and variance. Capping the outlier values at a certain percentile (C), also called winsorizing, is correct because it clips extreme values to a chosen percentile boundary (e.g., the 1st and 99th percentiles), preserving the record while limiting the outlier's influence. Binning continuous variables (D) is not a dedicated outlier-handling method; it discretizes values into bins and merely masks extremes rather than addressing them. Imputing outliers with the mean (E) is inappropriate because the mean itself is distorted by the outliers, so replacing them with it introduces bias and does not resolve the underlying problem.

Answer

Binning continuous variables

Answer

Imputing outliers with the mean

Question 15

Which TWO of the following are examples of supervised learning algorithms?

Accepted Answer

Linear regression. Linear regression (A) is a supervised learning algorithm because it learns a mapping from labeled input-output pairs by fitting a line (or hyperplane) that minimizes a loss such as mean squared error, making it a classic regression technique. Decision trees (D) are also supervised: they are trained on labeled data, recursively splitting features (e.g., via Gini impurity or information gain) to predict a target class or value. In contrast, K-means clustering (B) is unsupervised, as it groups unlabeled data by minimizing within-cluster variance without target labels. Principal component analysis (C) is an unsupervised dimensionality-reduction technique that finds orthogonal components maximizing variance, requiring no labels. The Apriori algorithm (E) is unsupervised association-rule mining that discovers frequent itemsets from unlabeled transactional data, so it is not supervised learning.

Answer

K-means clustering

Answer

Principal component analysis (PCA)

Answer

Apriori algorithm