STAT 302: Introduction to Statistics

Statistical Methods (STAT 302) - Chapter 1: Introduction to Statistics

Course Overview

  • Copyright Notice: 2025 by Aburweis. All rights reserved.
    • No part of this work may be reproduced in any form without written permission.

Course Learning Objectives

  • By the end of this course, students will:
    • Recognize the central role of statistics in fostering critical thinking in academic, professional, and everyday decision-making.
    • Understand that engaging with statistics will reward their studies and enhance their ability to use numerical information effectively.

Chapter 1 Learning Objectives

  • After this chapter, students will be able to:
    • Understand and Utilize Fundamental Terminology: Gain fluency in the terminology and vocabulary utilized in statistics.
    • Differentiate Between Types of Statistics: Identify distinguishing characteristics of descriptive and inferential statistics.
    • Distinguish Population vs. Sample: Differentiate between populations, samples, parameters, and statistics.
    • Classify Variables: Identify variables as qualitative or quantitative, and classify these as nominal, ordinal, discrete, or continuous.
    • Apply Levels of Measurement: Recognize and apply appropriate levels of measurement for statistical analysis.
    • Understand Sampling Techniques: Demonstrate knowledge of fundamental sampling techniques and their applications in research.
    • Data Handling: Collect, organize, and analyze data through well-structured statistical studies.

What is Statistics?

  • Statistics is not merely about calculating batting averages or poll results.
    • Definition: Statistics is the science of:
    • Collecting,
    • Classifying,
    • Organizing,
    • Summarizing,
    • Analyzing,
    • Interpreting data to make informed decisions.

Why Should We Study Statistics?

  • Tools provided by statistics help navigate the vast amounts of data encountered in daily life.
    • Provides clarity on information in fields such as sports, politics, medicine, and news.
    • Enables the design and execution of personal studies on topics of interest (e.g., health effects of chocolate).
    • Promotes critical engagement with data analysis and the transformation of raw information into actionable insights.

The Importance of Statistics in the Modern World

  • Examples of Questions Statistics Can Answer:
    • Do individuals who consume high-fiber cereal for breakfast weigh less than those who skip breakfast?
    • Does a new research drug achieve a higher cure rate than existing treatments?
    • How do state differences appear in undergraduate students who engage in online gaming?

Branches of Statistics

  • Descriptive Statistics:
    • Involves organizing, summarizing, and presenting data in an informative way.
  • Inferential Statistics:
    • Involves determining characteristics about populations based on a sample and making decisions/predictions about populations.

Interface Between Probability and Statistical Inference

  • Overview of key concepts: Probability, Population, Sample, Inference.

Examples of Statistical Application

  • Example 1: Crime Analysis in Austin

    • Data on police reports across ZIP codes is represented in a heat map.
    • Question: Does the heat map depict descriptive or inferential statistics?
    • Answer: Descriptive statistics.

  • Example 2: Future Crime Prediction

    • Data points for daily police incidents with predictive future trends shown via best fit lines.
    • Question: Is this prediction portion descriptive or inferential statistics?
    • Answer: Inferential statistics.

  • Example 3: Sunflower Height Analysis

    • Three statements analyzed as sample averages.
    1. Average height of East Texas sunflowers: 140 cm – Descriptive statistics.
    2. Average height of West Texas sunflowers: 134 cm – Descriptive statistics.
    3. Conclusion about height difference – Inferential statistics.

Your Turn Activity

  1. Classify the following examples from the course as descriptive or inferential statistics:
    • Average exam score of 89 on STAT 302 final.
    • Households with children are more likely to have internet access (77%) compared to those without children (68%).
    • Sara had 25 customers last week.

Definition of Data

  • Data: Collection of numbers, characters, images, or other items conveying information regarding a particular subject matter.

Key Terminology in Statistics

  • Population: A complete set of units of interest in a study. Can be finite or infinite.
  • Sample: A representative subset of the population.
  • Census: A comprehensive data collection from every member of a population.
  • Parameter: A numerical characteristic summarizing data from a population.
  • Statistic: A numerical summary from sample data.
  • Unit/Subject: An entity observed or measured in a statistical study.
  • Variable: A characteristic of individual units discernible in a population or sample.

Data Collection Examples in Research

  • Example 4: Suicidal Ideation Among Teens

    • Study finds 12% of participants despite being surveyed.
    • Population: All U.S. teens aged 13-18.
    • Sample: 6,482 teens surveyed.
    • Variable: Yes/No suicidal ideation representation.
    • Population Parameter: Proportion from all U.S. teens.
    • Sample Statistic: Proportion in the study's sample.

  • Example 5: Left-Handedness in Americans

    • Population: All Americans, Sample: 3 left-handed students out of 95.
    • Population Parameter: 11% left-handed amongst U.S. population.
    • Sample Statistic: 3.16% of surveyed students were left-handed.

Identifying Variables in Research

  • Types of Variables:
    • Qualitative (Categorical): E.g., car model, gender, etc.
    • Quantitative (Numerical): e.g., GPA, height, income.

Levels of Measurement

  • Levels include nominal, ordinal, interval, and ratio:
    • Nominal: Data categorized into unranked groups.
    • Ordinal: Data in ranked categories without defined intervals.
    • Interval: Ordered data allowing for meaningful differences, yet lacking a true zero.
    • Ratio: Contains all interval properties plus a true zero, allowing for meaningful ratio comparisons.

Sampling Principles in Statistics

  • Sampling is necessary due to challenges in studying entire populations:
    • Access difficulties, limited resources, and potential destructiveness of measurements.

Common Sampling Methods

  • Simple Random Sampling (SRS): Equal chance for all combinations.
  • Stratified Sampling: Population divided into strata, using SRS within each strata.
  • Cluster Sampling: Random clusters drawn, with all members sampled within selected clusters.
  • Systematic Sampling: Randomly select starting point and sample every kth member.
  • Convenience Sampling: Selecting individuals from convenient sources, generally non-representative.

Errors in Sampling

  • Sampling Errors: Differences caused by sample statistics not reflecting population parameters due to bias or variability.
  • Non-Sampling Errors: Errors not related to sampling; includes measurement, response bias, and non-response bias.

Data Collection Techniques

  1. Observational Studies: Collect behavior data without intervention.
  2. Experimental Studies: Introduce interventions to establish cause-and-effect.

Conclusion

  • This chapter introduces core principles and terms essential for understanding and applying statistical methodologies effectively in real-world contexts, informing both academic pursuits and professional practices.