Introduction to Statistics

Introduction to Statistics

  • Unit 1 Overview

What Are Statistics?

  • Definition: Statistics refers to the mathematical procedures used to summarize, analyze, and interpret observations that are collected and organized as data.

  • Applications of Data: We utilize data in various aspects of daily life, often without realizing it, such as in social media interactions and smart watches.

Types of Statistics

  • Descriptive Statistics:

    • Purpose: Descriptive statistics summarize and describe data to help understand a subset of a population, known as a "sample."

    • Characteristics:

    • Not based on probability.

    • Non-parametric methods: Tools do not rely on data meeting specific distribution criteria.

  • Inferential Statistics:

    • Purpose: Inferential statistics draw conclusions about a broader population based on sample data.

    • Characteristics:

    • Based on probability.

    • Parametric methods require certain assumptions about the data distribution.

Research Process in Statistics

  1. Ask a Question: Identify what you want to investigate.

  2. Set Up a Research Study: Define your research design and methodology.

  3. Measure/Observe Behavior: Collect data relevant to your research question.

  4. Evaluate Findings: Analyze your data to interpret results and draw conclusions.

Descriptive vs Inferential Statistics

  • Descriptive Statistics:

    • Describe how the data looks and provide insights into the sample.

  • Inferential Statistics:

    • Analyze how data behaves to draw conclusions about the entire population from which the sample is taken.

Definitions

  • Population:

    • The entire set of individuals or items of interest in a study; it is often characterized by parameters.

  • Sample:

    • A representative subset of a population, utilized for analysis.

Research Methods in Behavioral Research

  • Common research methods include:

    • Correlational Method: Identify relationships between variables without manipulation.

    • Experimental Method: Involves direct manipulation of variables to study effects on dependent variables.

    • Quasi-Experimental Method: Observes inherent differences in groups without random assignment.

Components of Research Design

  • Observing two or more variables and collecting data without changing the conditions or responses of participants.

  • Focuses on establishing cause and effect relationships with:

    • Manipulation: Altering an independent variable.

    • Control Group: A comparison group that does not receive the experimental treatment.

    • Randomization: Randomly assigning participants to different treatment levels to avoid bias.

Variables in Research

  • Independent Variable:

    • The variable that is manipulated to observe its effect on another variable.

  • Dependent Variable:

    • The outcome or effect that results from changes to the independent variable.

  • Control Variables:

    • Elements that are held constant to prevent them from affecting the outcome of the experiment.

Understanding Variables

  • When comparing dependent variables across groups, we recognize:

    • Cause = Independent Variable

    • Effect = Dependent Variable

  • If random assignment is unfeasible, researchers must use appropriate research designs to maintain validity.

Scales of Measurement

  • Variables are assigned numerical codes to interpret different levels of the variable. The meaning of a number depends on the type of variable.

Classification of Variables

  • Continuous vs. Discrete:

    • Continuous Variables: Measured along a continuum, allowing for decimals (e.g., height).

    • Discrete Variables: Separate and indivisible categories represented by whole numbers (e.g., number of children).

  • Quantitative vs. Qualitative:

    • Quantitative Variables: Vary based on amount (e.g., income).

    • Qualitative Variables: Vary in form or class (e.g., favorite color).

Types of Quantitative Variables

  • Nominal Variables:

    • Assign numbers to qualitative categories; useful for identifying group membership, but not mathematically computable.

    • Examples: Sex, political affiliation, favorite color.

  • Ordinal Variables:

    • Capture the rank order of categories, showing sequence but without equivalent intervals.

    • Examples: Queue position, rankings, letter grades.

  • Interval Variables:

    • Capture quantitative values of different levels with meaningful intervals, but no true zero point.

    • Examples: SAT/ACT scores, temperature in Fahrenheit, satisfaction ratings (1-7).

  • Ratio Variables:

    • Measure quantitative values with a true zero point which indicates absence of the variable.

    • Examples: Number of errors, income, exam scores, duration of drug abuse.