DA0-002 Data Analysis Practice Test 15 — 15 Questions

Question 1

A data analyst is preparing features for a machine learning model that uses distance-based algorithms (e.g., K-means, KNN). The dataset contains numerical features with different scales: age (0-100), income (20,000-200,000), and credit score (300-850). Which data transformation technique is most appropriate to ensure all features contribute equally to the distance calculations?

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

Accepted Answer

Min-max normalization. Min-max normalization rescales features to a fixed range (e.g., 0 to 1), making distances computed equally weighted. Standardization is better for algorithms assuming Gaussian distributions.

Answer

Z-score standardization

Answer

One-hot encoding

Answer

Log transformation

Question 2

A logistic regression model is used to predict the probability of customer churn. The model's coefficient for the feature 'customer support calls' is 0.8 with a p-value of 0.001. Which interpretation is correct?

Accepted Answer

For each additional support call, the log-odds of churn increase by 0.8, and this effect is statistically significant.. In logistic regression, a positive coefficient indicates that as the predictor increases, the log-odds of the outcome increase. The p-value being less than 0.05 indicates the effect is statistically significant.

Answer

The odds of churn are multiplied by 0.8 for each additional call.

Answer

Support calls have no significant effect on churn.

Answer

For each additional support call, the probability of churn increases by 80%.

Question 3

A dataset contains customer records with a column for 'Phone Number' that should be unique. However, the analyst finds several duplicate phone numbers. Which data quality dimension is primarily affected?

Accepted Answer

Uniqueness. Uniqueness refers to the expectation that each record or attribute value should be unique. Duplicate phone numbers violate uniqueness.

Answer

Completeness

Answer

Accuracy

Answer

Consistency

Question 4

A data analyst is examining the relationship between advertising spend (in thousands) and sales (in thousands). The Pearson correlation coefficient is computed as r = -0.85. Which of the following interpretations is correct?

Accepted Answer

There is a strong negative linear relationship.. Pearson r measures linear correlation: -0.85 indicates a strong negative linear relationship (as one increases, the other decreases). The magnitude |0.85| is close to 1, so strong.

Answer

There is no linear relationship.

Answer

There is a strong positive linear relationship between advertising spend and sales.

Answer

There is a weak negative linear relationship.

Question 5

A data analyst is cleaning a dataset with missing values in a time series of daily temperatures. The missing values occur sporadically. Which imputation method is most appropriate to maintain the temporal trend?

Accepted Answer

Interpolation. Interpolation estimates missing values by using surrounding data points and is suitable for time series with a trend. Forward-fill carries the last observation forward, which may not capture trend well. Mean imputation ignores order.

Answer

Forward-fill

Answer

Mean imputation

Answer

Median imputation

Question 6

A data analyst wants to test if the proportion of customers who prefer Product A over Product B is different from 50%. She surveys 200 customers and finds that 120 prefer Product A. Which statistical test should she use?

Accepted Answer

One-sample z-test for proportions. A one-sample z-test for proportions compares a sample proportion to a hypothesized population proportion. Here, the null is p=0.5. A chi-square test for goodness-of-fit could also be used, but the z-test is standard for a single proportion.

Answer

Chi-square test of independence

Answer

ANOVA

Answer

Two-sample t-test

Question 7

A data analyst is performing data cleaning on a dataset and identifies several outliers in the 'age' column. Which TWO methods are appropriate for handling these outliers? (Select two.)

Accepted Answer

Capping. Capping limits extreme values to a threshold, and removal deletes outlier records. Transformation (e.g., log) can reduce impact but is more for skewness. Imputation and binning are for missing data or discretization, not directly for outliers.

Answer

Mean imputation

Answer

Transformation

Answer

Binning

Question 8

A company is planning an A/B test to compare two website designs. Which THREE of the following must be determined before the test begins to ensure valid results? (Select three.)

Accepted Answer

The desired effect size. Sample size (based on power and effect size), significance level (α), and desired effect size are all pre-specified to design the test. The p-value is an outcome, not a pre-test parameter. The hypothesis is defined beforehand, but which one is false? Actually null and alternative hypotheses should be pre-specified, but the phrasing 'which one is true' is not determined before; the test determines that. So correct are: determine minimum sample size, determine significance level, and determine desired effect size.

Answer

The p-value of the test

Answer

Which hypothesis is true

Question 9

A data analyst wants to segment customers based on purchasing behavior such as frequency, monetary value, and recency. Which TWO clustering evaluation methods can help determine the optimal number of clusters? (Select two.)

Accepted Answer

Silhouette score. The elbow method uses within-cluster sum of squares, and the silhouette score measures cohesion and separation. Both help choose k. Correlation coefficient is for association, not clustering. ANOVA and t-test are for hypothesis testing.

Answer

Correlation coefficient

Answer

ANOVA

Answer

t-test

Question 10

A data analyst is reviewing a dataset containing house prices. The mean price is $350,000 and the median is $280,000. Which of the following best describes the distribution of house prices?

Accepted Answer

The distribution is right-skewed.. When the mean is greater than the median, the distribution is right-skewed (positively skewed) because higher values pull the mean upward.

Answer

The distribution is symmetric.

Answer

The distribution is left-skewed.

Answer

The distribution is bimodal.

Question 11

A data scientist runs a linear regression model to predict customer spending based on income. The R-squared value is 0.45 and the p-value for the slope coefficient is 0.03. At a significance level of α=0.05, which of the following conclusions is correct?

Accepted Answer

The slope is statistically significant, and the model explains 45% of the variance.. The p-value (0.03) is less than α (0.05), so the slope is statistically significant. R²=0.45 means the model explains 45% of the variance.

Answer

The slope is not statistically significant, and the model explains 55% of the variance.

Answer

The slope is statistically significant, and the model explains 55% of the variance.

Answer

The slope is not statistically significant, and the model explains 45% of the variance.

Question 12

Which TWO of the following are measures of central tendency?

Accepted Answer

Median. Mean, median, and mode are measures of central tendency. Range and standard deviation measure dispersion.

Answer

Range

Answer

Variance

Answer

Standard deviation

Question 13

A data analyst is cleaning a dataset with missing values. Which TWO of the following are acceptable methods for handling missing numerical data?

Accepted Answer

Mean imputation. Mean imputation and deletion (listwise) are common methods. Mode imputation is for categorical, and forward-fill is for time series; min-max is normalisation.

Answer

Min-max normalisation

Answer

Forward-fill

Answer

Mode imputation

Question 14

An analyst wants to compare the average sales revenue across three different store locations. Which TWO statistical methods are appropriate for this comparison?

Accepted Answer

ANOVA. ANOVA compares means of three or more groups. A t-test compares only two groups. Chi-square tests categorical independence. Correlation measures linear relationship. Descriptive stats summarise but don't compare multiple groups inferentially.

Answer

Two-sample t-test

Answer

Descriptive statistics

Answer

Chi-square test

Question 15

Which TWO of the following are appropriate uses of min-max normalisation?

Accepted Answer

Scaling features to a range of 0 to 1. Min-max normalisation scales data to a fixed range (often 0-1), useful for distance-based algorithms like k-NN and neural networks. Standardisation (Z-score) is better for algorithms assuming Gaussian distribution.

Answer

Transforming data to have mean 0 and standard deviation 1

Answer

Preparing data for linear regression with normally distributed residuals

Answer

Handling missing values