Introduction to Statistical Thinking Flashcards

Introduction to Statistical Thinking

• Core Inquiry Questions:

  • What is statistics?

  • Why should students study statistics?

  • Why should individuals study statistics?

• Scope of Inquiry:

  • Encompasses the foundations of statistical thinking across basic and applied concepts.

  • Provides a systematic framework for reasoning under uncertainty using empirical data.

The Meaning and Attributes of Data

• Historical Definition of Data:

  • Historically, data has been associated with measurements and numbers that were purposefully generated to help solve a specific problem.

• Modern Statistical Practice with Data:

  • Statisticians analyze data using visual representations (pictures) and summary measurements to build data-driven predictive models.

  • Statisticians develop methodologies for designing experiments and gathering data that are cost-effective and diminish bias.

  • Statistics is fundamentally defined as a formal way of thinking with data.

• General Definition and Scope of Statistics:

  • Statistics is the science of learning from data, defined as numbers with context.

  • It is the science of collecting, organizing, analyzing, and drawing conclusions.

  • It serves as the primary tool used to make sense out of data.

Big Data Attributes and Sources

• Conceptual Definition of Big Data:

  • Big Data is a loosely defined concept used to describe data sets produced by our globally networked, internet-driven, sensor-laden world.

  • Common Operational Definition: A set of data sufficiently large to be challenging to analyze at a typical data center.

• Scale Frame of Reference for a Large Data Center:

  • The minimum baseline capacity for a large data center is on the order of tens of thousands of servers.

  • The storage infrastructure includes thousands of data storage arrays.

• The Four Core Attributes of Big Data:

  • Volume: The scale of the data; Big Data inherently implies large volumes of data.

  • Variety: The different forms and structures that data can take.

  • Velocity: How fast data is being sent to the data processing and data management infrastructure.

  • Veracity: The trustworthiness, quality, and reliability of the data.

• Primary Domain Sources of Big Data:

  • Medicine (specifically Genomics)

  • Astronomy and Cosmology

  • Physics

  • Business and Industry

Practical Applications and Value of Studying Statistics

• Motivating Reasons to Study Statistics:

  • To become an informed consumer.

  • To make effective decisions based on empirical evidence.

  • To test and evaluate the qualities of products.

  • To evaluate decisions that directly affect everyday life, including:

  • Insurance pricing and coverage options

  • Financial aid availability and allocation

  • Medical resources and treatment availability

Core Statistical Definitions and Conceptual Foundations

• Population:

  • The total set of subjects or things that we are interested in studying.

• Frame:

  • A comprehensive list containing all members of the population.

• Census:

  • A survey that strictly includes all the elements or units in the frame.

• Parameters:

  • Facts or summary characteristics that describe an entire population.

• Sample:

  • A subset of the population which is used to gain insight about the population.

• Statistics (Sample Statistics):

  • Facts or characteristics describing the sample.

• Structural Relationship:

  • A Population is described by Parameters.

  • A Sample is described by Statistics.

Major Branches of Statistics and Descriptive Measures

• Two Primary Branches of Statistics:

  • Descriptive Statistics:

  • The collection, organization, analysis, and presentation of data.

  • Inferential Statistics:

  • The branch whose objective is to make reasonable guesses or inferences about population characteristics using sample data.

• Key Categories and Examples of Descriptive Statistics:

  • Frequency Distribution

  • Measures of Central Tendency:

  • Mean

  • Median

  • Mode

  • Measures of Dispersion:

  • Range

  • Variance

  • Standard Deviation

Applied Scenarios: Classifying Populations, Samples, Parameters, and Statistics

• Scenario Analyses for Population and Sample Identification:

  • Mazda 626 Crash Test Study:

  • Context: A consumer group conducts crash tests of new model cars to determine the severity of damage to $2003$ Mazda $626$ models resulting from a $10\,\text{mph}$ crash into a concrete wall. The research group tests $6$ cars of this type and assesses the amount of damage.

  • Target Population: All $2003$ Mazda $626$ cars.

  • Selected Sample: The $6$ specific $2003$ Mazda $626$ cars tested.

  • Auburn University Dormitory Preference Survey:

  • Context: Sampling $50$ AU students to determine the best dorm to live in.

  • Target Population: All AU students.

  • Selected Sample: The $50$ AU students sampled.

  • Cafeteria Football Attendance Survey:

  • Context: Surveying $20$ students in the cafeteria to find out whether they will attend the first football game.

  • Target Population: The full student body / all cafeteria students.

  • Selected Sample: The $20$ students surveyed in the cafeteria.

  • Quality Control Rope Strength Testing:

  • Context: Testing the breaking strength of manufactured ropes at a rate of $1$ rope per hour.

  • Target Population: All manufactured ropes produced by the facility.

  • Selected Sample: The individual ropes tested ($1$ per hour).

  • Mathematics Course Housing Distribution:

  • Context: A observation notes that $22$ out of $30$ students in a math class live in the dorm.

  • Frame / Population: The $30$ students in the math class.

  • Sample / Subset: The $22$ math class students living in the dorm.

  • Animal Shelter Demographic Assessment:

  • Context: An animal shelter houses $25$ dogs total, of which $12$ of them are puppies.

  • Frame / Population: The $25$ dogs in the animal shelter.

  • Sample / Subset: The $12$ puppies within the shelter.

• Scenario Analyses for Parameter versus Statistic Identification:

  • Gaming System Pricing:

  • Statement: The average price of a new gaming system is $\$325$.

  • Classification: Population Parameter (refers to the overall population price average).

  • Candy Color Coating Proportion:

  • Statement: $24\%$ of a popular chocolate candy is coated in a blue candy shell.

  • Classification: Population Parameter (refers to the overall production parameter of the candy).

  • College Off-Campus Living Survey:

  • Statement: A sample of $60$ college students found that $10\%$ live in an off-campus apartment their first year.

  • Classification: Sample Statistic (calculated directly from the sample of $60$ students).