Start learning →

M.Sc Data Science Data Science and Analytics — practice questions

Explore 6 free Data Science and Analytics questions in M.Sc Data Science Datascience. Open each question or exercise to read its content, reference answers and available explanation.

Practise Data Science and Analytics with Quill →

Data Science and Analytics questions and exercises with answers

Showing questions 1–6 of 6.

Who does the framework credit with coining the term fourth paradigm, and in what year?Read the answer and worked solution →How does the framework define data mining?Read the answer and worked solution →What term does the framework say has been used pejoratively for browsing data for something interesting?Read the answer and worked solution →Order the data science methodRead the answer and worked solution →Data science bingoRead the answer and worked solution →What a data scientist spansRead the answer and worked solution →

Worked practice questions

Who does the framework credit with coining the term fourth paradigm, and in what year?

  1. Dr. Gordon Moore, in 1965
  2. Dr. Jim Gray, in 2007
  3. Dr. Nancy Grady, in 2000
  4. Dr. Jim Gray, in 1997
Show answer and solution

Correct answer: B. Dr. Jim Gray, in 2007

1. The framework attributes the term in the same sentence that introduces it: "The fourth paradigm is a term coined by Dr. Jim Gray in 2007." 2. Both halves have to match, which is why the same name appears twice in the options with different years. 3. Gordon Moore and 1965 are also real in this document, but for something else entirely: the 1965 paper estimating that transistor density was doubling every two years, which the framework cites as Moore's Law. 4. Nancy Grady is credited in the document too, in a footnote acknowledging that one of the figures was provided courtesy of her, not for coining any term. 5. The year 2000 belongs to CRISP-DM, the Cross-Industry Standard Process Model for Data Mining, which the framework says was published that year. _Source: NIST SP 1500-1r2 "NIST Big Data Interoperability Framework: Volume 1, Definitions" (Oct 2019), p.26 section 5 "Data Science"_

Open this question →

How does the framework define data mining?

  1. The application of specific algorithms for extracting patterns
  2. The overall process of discovering useful knowledge from data
  3. Systematic processing of data to uncover historical trends
  4. Selection of a subset of data from a larger data population
Show answer and solution

Correct answer: A. The application of specific algorithms for extracting patterns

1. The framework gives data mining a deliberately narrow definition: "Data mining is the application of specific algorithms for extracting patterns from data." 2. Narrow is the point. Data mining is one step, not a whole process, and the framework says so directly when it contrasts the two terms. 3. The broader term is knowledge discovery in data: "the overall process of discovering useful knowledge from data". The framework notes "this process involved the entire data analytics life cycle ... whereas the specific analytical step was known as data mining." 4. Systematic processing to uncover patterns, relationships and historical trends is the framework's definition of analytics, a third term again. 5. Selecting a subset from a larger population is data sampling, which the framework describes as "a central concept of statistical analysis". _Source: NIST SP 1500-1r2 "NIST Big Data Interoperability Framework: Volume 1, Definitions" (Oct 2019), p.27 section 5.1.1 "Data Mining"_

Open this question →

What term does the framework say has been used pejoratively for browsing data for something interesting?

  1. Data dredging
  2. Data fusion
  3. Data locality
  4. Data governance
Show answer and solution

Correct answer: A. Data dredging

1. The framework uses the term while describing the statistical tradition's suspicion of open-ended exploration. 2. It writes: "The discovery process, or browsing data for something interesting, has been described pejoratively as data dredging, which does not result in definitive answers to a hypothesis." 3. The complaint is about what dredging cannot deliver. Without a hypothesis stated in advance, a pattern found by searching is not a definitive answer. 4. The framework then rehabilitates the practice for data science: "As opposed to the data dredging of statistics or data mining, broader understanding of the data leads to either discovery of insights, or the formulation of hypotheses for testing." 5. So exploration is legitimate when it feeds the hypothesis cycle rather than substituting for it, which is exactly what the definition of data science allows with its "discovery or ... hypothesis formulation and hypothesis testing". 6. Data fusion, data locality and data governance are all real terms in the document, describing the integration of datasets, the co-location of processing with storage, and the policy system around data respectively. _Source: NIST SP 1500-1r2 "NIST Big Data Interoperability Framework: Volume 1, Definitions" (Oct 2019), p.26 section 5.1 "Data Science and Analytics"_

Open this question →

How to practise

  1. Choose a Data Science and Analytics question and try to work out your answer.
  2. Open the question to check the correct answer and read its worked solution.
  3. Continue in the app for bite-sized lessons, explanations and review with Quill. You can start without creating an account.

More Datascience topics

Understanding DataBig Data Reference Architecture TaxonomyBig Data DefinitionsBig Data Characteristics