Data Science Core: 48 MCQs with answers

High veracity

High veracity (data uncertainty and quality) is one of the key traits of Big Data, along with volume, velocity, and variety.

NumPy

NumPy provides support for vectorized operations on arrays, which is essential for efficient numerical computations.

DataFrame

A DataFrame is a two-dimensional, labeled data structure in Pandas, similar to a table in a database.

Binomial

The binomial distribution models the number of successes in a fixed number of independent Bernoulli trials.

Scatter plot

Scatter plots display the relationship between two continuous variables, revealing patterns like correlation.

The value below which a given percentage of observations fall

A percentile indicates the value below which a certain percentage of the data lies; e.g., the 90th percentile is the value below which 90% of observations fall.

False

Reporting presents data in a structured format, while analytics involves deeper analysis to derive insights and support decisions.

True

The normal distribution is defined for continuous random variables and is characterized by its bell-shaped curve.

To summarize past data

Descriptive analytics focuses on summarizing historical data to understand what has happened in the past.

High variety

Big data is characterized by high variety, meaning it comes in various formats and types.

The systematic computational analysis of data

Analytics involves the systematic analysis of data to extract insights and support decision-making.

Pandas

Pandas is a powerful library in Python specifically designed for data manipulation and analysis.

Selecting a subset of data from a larger dataset

Sampling involves selecting a subset of data from a larger population to make inferences about that population.

NumPy

NumPy is specifically designed for efficient numerical operations in Python.

Analytics involves deeper insights than reporting

Analytics goes beyond reporting by providing deeper insights and interpretations of data.

To infer population parameters from sample data

Estimation is used to infer population parameters based on the analysis of sample data.

Data collection, analysis, and reporting

The analytics process typically involves data collection, analysis, and reporting to derive insights.

To provide historical insights

Descriptive analytics provides insights into historical data, helping to understand past trends and behaviors.

Diagnostic

Diagnostic analytics focuses on understanding the causes of past events, such as explaining why a sales drop happened.

Ratio

The ratio scale has a true zero, enabling comparisons like 'twice as much' (e.g., weight, height).

It becomes approximately normal as sample size increases, regardless of the population distribution.

The CLT states that the sampling distribution of the sample mean approaches a normal distribution as the sample size grows, irrespective of the population's distribution.

Skewness

Skewness measures the asymmetry of a distribution, while kurtosis measures the 'tailedness'.

Continuous

PDFs apply to continuous random variables, where probabilities are found by integrating the PDF over an interval.

Cluster sampling

Cluster sampling divides the population into clusters and randomly selects whole clusters to be included in the sample.

The standard deviation of the sampling distribution of the estimate

The standard error measures the variability of a point estimate across samples, i.e., the standard deviation of its sampling distribution.

Convenience sampling

Convenience sampling selects individuals based on ease of access, not random selection, making it a non-probability method.

Data engineering focuses on building pipelines and infrastructure; analytics focuses on deriving insights.

Data engineering involves designing and maintaining data pipelines, while analytics involves analyzing data to extract insights.

Data Analysis

The correct option is 'Data Analysis' because this phase involves interpreting the processed data to derive insights that can inform decision-making.

Descriptive analytics summarizes past data to inform future predictions.

The correct option is 'Descriptive analytics summarizes past data to inform future predictions' because descriptive analytics provides the context needed for predictive models.

Probability sampling ensures every member has a chance of being selected.

The correct option is 'Probability sampling ensures every member has a chance of being selected' because this method reduces selection bias by giving each individual a known chance of inclusion.

NumPy

The correct option is 'NumPy' as it is specifically designed for numerical operations and provides support for large, multi-dimensional arrays and matrices.

Volume

The correct option is 'Volume' because it specifically refers to the vast amount of data being generated and stored, which is a defining trait of big data.

It describes how the sample mean distribution approaches normality as sample size increases.

The correct option is 'It describes how the sample mean distribution approaches normality as sample size increases' because the CLT is fundamental in inferential statistics.

Reporting is static, while analytics involves dynamic data exploration.

The correct option is 'Reporting is static, while analytics involves dynamic data exploration' because analytics allows for deeper insights and exploration beyond simple reporting.

Confidence Interval

The correct option is 'Confidence Interval' because it provides a range of values that is likely to contain the population parameter, indicating the reliability of the estimate.

Histogram

The correct option is 'Histogram' because it is specifically designed to show the frequency distribution of a continuous variable, making it ideal for this purpose.

Point estimates give a single value as an estimate of a parameter.

The correct option is 'Point estimates give a single value as an estimate of a parameter' because point estimates provide a specific value rather than a range.

Maximum likelihood estimation

Maximum likelihood estimation (MLE) selects parameter values that make the observed data most probable under the assumed model.

Data Cleaning

Data cleaning is essential as it involves correcting or removing erroneous data, ensuring that the insights derived are valid and reliable.

Sample Size

The sample size directly influences the width of the confidence interval; larger samples lead to narrower intervals, reflecting increased precision.

Median

The median is the middle value and is less affected by outliers, making it a better measure of central tendency in such cases.

68%

According to the empirical rule, approximately 68% of data in a normal distribution lies within one standard deviation of the mean.

Identifying patterns in historical data

Descriptive analytics focuses on summarizing historical data to identify patterns and trends, providing a foundation for further analysis.

Independent t-test

The independent t-test is designed to compare the means of two independent samples, making it the appropriate choice in this scenario.

Normal Distribution

The CLT states that as the sample size increases, the sampling distribution of the sample mean approaches a normal distribution, regardless of the population's shape.

Variety

Variety refers to the different types and sources of data, highlighting the complexity involved in managing and analyzing big data.

Median Imputation

Median imputation is less sensitive to outliers and helps maintain the overall distribution of the data when handling missing values.

NumPy

NumPy is specifically designed for numerical operations and includes efficient implementations of linear algebra functions.