Podcast
Questions and Answers
What defines the quality of data integrity in an organization?
What defines the quality of data integrity in an organization?
Which characteristic refers to the up-to-date nature of data?
Which characteristic refers to the up-to-date nature of data?
What type of data is characterized as being highly organized and easily understood by machine language?
What type of data is characterized as being highly organized and easily understood by machine language?
Which metric related to data assesses whether the data variables are pertinent to a specific study?
Which metric related to data assesses whether the data variables are pertinent to a specific study?
Signup and view all the answers
What factor is critical to determining if a data source can be trusted?
What factor is critical to determining if a data source can be trusted?
Signup and view all the answers
Which of the following describes nominal data?
Which of the following describes nominal data?
Signup and view all the answers
What is the primary characteristic of ordinal data?
What is the primary characteristic of ordinal data?
Signup and view all the answers
Which type of data is characterized by an absolute zero point?
Which type of data is characterized by an absolute zero point?
Signup and view all the answers
What is one of the main goals of data preprocessing?
What is one of the main goals of data preprocessing?
Signup and view all the answers
Which of the following is not a stage in data preprocessing?
Which of the following is not a stage in data preprocessing?
Signup and view all the answers
Study Notes
Business Intelligence, Analytics, and Data Science: A Managerial Perspective
- This is a textbook about Business Intelligence, Analytics, and Data Science.
- The fourth edition is mentioned
- The book is authored by Ramesh Sharda, Dursun Delen, and Efraim Turban.
- The publisher is Pearson.
Chapter 2: Descriptive Analytics I
- Focuses on the nature of data, statistical modeling, and visualization.
- Data is a collection of facts obtained from experiences, observations, or experiments.
- Data can be numbers, words, images, etc.
- Data is the foundational concept from which information and knowledge are derived.
- Data quality and integrity are critical for analytics.
The Nature of Data
- Accuracy, completeness, consistency, and validity of data are essential.
- Data comes from various sources such as business processes, internet/social media and machines/internet of things.
- Data is stored, protected, and used for analytics.
- Data is then used to generate trends and patterns.
- Data visualization is used for exploring, understanding, and communicating data.
Metrics for Analytics Ready Data
- Data source reliability: Confidence and belief in its source.
- Data content accuracy: The right data for the task.
- Data accessibility: Easy data access when needed.
- Data security and privacy: Secure data use by authorized personnel.
- Data richness: Comprehensive or nearly complete data.
- Data consistency: Accurate collection and combination of data.
- Data currency/timeliness: Up-to-date and recent data.
- Data validity: Matching actual and expected data.
- Data relevance: Relevant variables related to the study.
- Data granularity: Definition of variables at the lowest level of detail.
A Simple Taxonomy of Data
- Data (datum): Singular form of data, factual information.
- Structured data: Standardized format, well-defined structure, easy access (e.g., names, dates, credit card numbers).
- Unstructured data: Any combination of textual, imagery, voice, or web content.
- Semi-structured data: Extensible Markup Language (XML), Hyper Text Markup Language (HTML), JavaScript Object Notation (JSON), log files.
Categorical and Numerical Data
- Categorical data represents types that can be grouped (e.g., race, sex).
- Nominal data: Uses labels without quantitative values (e.g., gender, color).
- Ordinal data: Ordered categories with meaningful differences between values (e.g., Likert scale).
- Numerical data represents values that can be measured and ordered logically (e.g., height, weight).
- Interval data: Values with order and meaningful differences (e.g., temperature, age).
- Ratio data: Values with order and meaningful differences and a true zero point (e.g., income, height).
Data Preprocessing
- The real-world data is complex and might need modification before using it in analytics.
- Data preprocessing is needed and involves:
- Data consolidation: Collecting, selecting, and integrating data.
- Data cleaning: Imputing values, reducing noise, and eliminating duplicates.
- Data transformation: Normalizing, discretizing, or creating attributes.
- Data reduction: Reducing dimensionality or the volume of data.
- Sampling
- Balancing/stratification
Dimensionality Reduction
- Reducing the number of data dimensions or features to make the data simpler.
- It helps decrease the complexity of large datasets.
Balancing/Stratification
- Stratified sampling: Selecting random samples from different strata (groups) in a population to ensure representation of all important subgroups.
Discretization Data
- This process converts continuous data into discrete intervals or categories.
- It helps in simplifying and reducing complexity of data sets.
Data Normalization & Creating Attributes
- Normalizing data removes unstructured and redundant data to standardize the data format.
- Attributes are created to store more data about the objects. (e.g., priority)
Statistical Modeling for Business Analytics
- Presents various analytical approaches including:
- Descriptive analytics
- Predictive analytics
- Prescriptive analytics
Descriptive Statistics
- Statistics are a collection of mathematical techniques for data characterization and interpretation.
- Describing data as it is. (e.g. measures of central tendency and dispersion)
- Arithmetic mean
- Median
- Mode
- Range
- Variance
- Standard deviation
- Mean absolute deviation (MAD)
- Histograms
- Skewness
- Kurtosis
- Describing data as it is. (e.g. measures of central tendency and dispersion)
Regression Modeling for Inferential Statistics
- Regression is a technique used in inferential statistics to analyze the relationship between explanatory (input) and response (output) variables.
- Used in hypothesis testing and forecasting.
Business Reporting
- Report: Information for decision making.
- A report's purpose may include improving managerial decision-making, maintaining departmental functioning, providing information, analyzing results, persuading others to act, and documenting organizational knowledge.
- Formats include text, tables, graphs, charts.
- Distribution channels include printed reports, emails, portals, and intranets.
Types of Business Reports
- Metric Management Reports: Help manage business performance using metrics.
- Dashboard-Type Reports: Graphical presentation of key performance indicators.
- Balanced Scorecard Reports: Management system for achieving strategic outcomes (financial, customer, process and learning).
Data Visualization
- Using visual representations to explore, make sense of, and communicate data.
- Includes various formats like charts, graphs, and illustrations.
Visual Analytics
- Combining information visualization with predictive analytics.
Performance Dashboards
- Summarized displays of important data to aid in quick decision making.
- Dashboard design focuses on displaying information clearly and quickly.
- Includes monitoring, analysis, and management.
- Dashboards use visual elements to highlight exceptions and require minimal training for users.
Best Practices in Dashboard Design
- Using industry standards to benchmark Key Performance Indicators (KPIs).
- Including metadata for context.
- Validating dashboard design with usability specialists.
- Prioritizing and ranking alerts and exceptions.
- Incorporating feedback from business users.
- Presenting information at various levels (e.g. summary, detail).
- Choosing appropriate visual constructs.
- Implementing guided analytics functionality.
Studying That Suits You
Use AI to generate personalized quizzes and flashcards to suit your learning preferences.
Related Documents
Description
This quiz explores Chapter 2 of the textbook 'Business Intelligence, Analytics, and Data Science', focusing on descriptive analytics. It covers the nature of data, including its sources, quality, and importance in statistical modeling and visualization. Test your understanding of fundamental concepts related to data in analytics.
