Introduction to Statistics and Collecting Data

Research Objectives and Data Collection

Statistics begins with the process of posing a question, known as the research objective. Data collection is essential for making informed decisions, whether in social concerns, business, government, or consumer contexts. The research objective is often composed of several related questions, each of which can be addressed by gathering relevant data.

• Research Objective: The main question guiding the data collection process.

• Variables: Characteristics of interest measured for individuals in a population.

• Data: The information obtained from measuring variables; can be qualitative (categorical) or quantitative (numerical).

• Example: Deciding which college to transfer to involves collecting data on enrollment, housing, degree programs, tuition, class size, and location.

Types of Variables

Variables are classified based on the type of data they yield. Understanding the distinction between qualitative and quantitative variables is fundamental in statistics.

• Qualitative (Categorical) Variables: Yield data in the form of word responses or categories (e.g., "yes" or "no").

• Quantitative (Numerical) Variables: Yield data in the form of numbers (e.g., "5050 students").

• Classification Example:

  • Q1. Number of students: Quantitative

  • Q2. On-campus housing: Qualitative

  • Q3. Degree program availability: Qualitative

  • Q4. Tuition cost: Quantitative

  • Q5. Class size: Quantitative

  • Q6. College location: Qualitative

Describing Data: Classification of Variables

Quantitative Variables: Discrete vs. Continuous

Quantitative variables can be further classified as discrete or continuous based on how their values are obtained.

• Discrete Variables: Values are counted and come from a finite list of possibilities (e.g., number of classes taken).

• Continuous Variables: Values are measured and come from an infinite set of possibilities (e.g., time taken to log in).

• Example:

  • Q1. Number of students: Discrete

  • Q4. Tuition cost: Continuous

  • Q5. Class size: Discrete

Qualitative Variables: Nominal vs. Ordinal

Qualitative variables are classified based on whether their categories have a natural order.

• Nominal Variables: Categories have no natural order (e.g., major, ZIP code).

• Ordinal Variables: Categories have a natural order (e.g., class year, course rating).

Summary Table: Classification of Variables

The following table summarizes the classification of variables based on their properties:

Decision Tree for Classifying Variables

A helpful approach to classifying variables is to follow a logical decision tree:

• Does the variable describe a category or measure/count a quantity?

• If it describes a category: Qualitative

• If it measures/counts a quantity: Quantitative

• If qualitative, do categories have a natural order?

• No natural order: Nominal

• Natural order: Ordinal

• If quantitative, are values counted or measured?

• Counted: Discrete

• Measured: Continuous

Key Definitions and Examples

• Population: The entire group of individuals or items of interest.

• Sample: A subset of the population used to collect data.

• Variable: A characteristic measured for each individual in the population.

• Data: The values obtained from measuring variables.

• Example: In a survey of college students, variables might include age (quantitative), major (qualitative), and GPA (quantitative).

Formulas and Notation

While this section focuses on classification, introductory statistics often uses the following notation:

• Population size:

• Sample size:

• Variable:

• Data value:

For example, if is the number of courses a student is taking, could be 3, 4, or 5 for different students.

Applications and Importance

Classifying variables correctly is essential for choosing appropriate statistical methods and interpreting results. For example, qualitative variables are summarized using frequency tables and bar charts, while quantitative variables are analyzed using measures of central tendency and dispersion.

• Application: In business, classifying customer feedback as ordinal (e.g., ratings) helps in analyzing satisfaction trends.

• Application: In health studies, distinguishing between discrete (number of doctor visits) and continuous (blood pressure) variables guides the choice of statistical tests.

Additional info: The classification tree image visually reinforces the decision process for classifying variables, directly supporting the explanation in the paragraph above.