Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Coursera

How to Make Sense of Statistics

via Coursera

Go to class Write review

Overview

Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This practical guide helps you understand and apply statistical methods in research, from basic concepts like variables and tables to advanced techniques such as regression analysis and missing data handling. This resource provides a clear and practical introduction to statistical methods for research in the social sciences. It guides learners through foundational concepts and advanced techniques, emphasizing real-world application and effective data communication. Designed for online learning, it makes complex ideas accessible and relevant to a wide range of professionals. This resource is ideal for students, researchers, and professionals in social sciences, healthcare, and related fields. It assumes basic research knowledge but no prior statistical training. It provides practical insights for both beginners and intermediate learners, helping them build confidence in statistical analysis. This course provides a comprehensive, step-by-step approach to mastering key statistical techniques in social science research. By focusing on real-world applications and examples, it breaks down complex concepts into easy-to-understand processes, guiding readers through a logical progression from basics to advanced techniques. This course is based on How to Make Sense of Statistics, by Stephen Gorard. Copyright ©2021 by Sage Publications Limited. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies. Published by Sage Publications Limited, London. Used by arrangement with Sage Publications Limited.

Syllabus

  • Why we use numbers in research
    • This module explores how numbers are used in social science research, focusing on practical methods, critical thinking, and real-world applications. It simplifies the process of working with numerical data to make it more accessible and empowering for researchers. Learners will gain foundational knowledge and confidence in using numbers effectively in their studies.
  • What is a number? Issues of measurement
    • This module explores the fundamental differences between categorical and real numbers in social science, focusing on their classification, application, and significance in data analysis. Learners will gain an understanding of how numbers are used to represent and interpret social phenomena accurately.
  • Working with one variable
    • This module focuses on techniques for analyzing single variables in datasets, including summarizing categorical and numerical data, understanding distributions, and using measures of central tendency. Learners will gain skills in preparing data and interpreting statistical summaries effectively.
  • Working with tables of categorical variables
    • This module explores how to analyze relationships between categorical variables using cross-tabulations, odds ratios, and frequency analysis. Learners will gain the skills to interpret real-world data and uncover meaningful patterns. The focus is on applying these techniques to practical examples and datasets.
  • Examining differences between real numbers
    • This module explores methods for comparing real numbers across categories, focusing on analyzing differences, standardizing results, and interpreting effect sizes. Learners will gain skills in assessing real-world data and understanding the practical implications of statistical differences. The module also introduces tools like the number needed to treat (NNT) for evaluating interventions.
  • Significance tests: How to conduct them and what they do not mean
    • This module explores the fundamentals of significance tests, including chi-squared and t-tests, and how to interpret p-values. It addresses the limitations of statistical significance in research and provides guidance on how to report results without relying solely on p-values. Learners will gain critical thinking skills for evaluating statistical evidence in real-world scenarios.
  • Significance tests: Why we should not report them
    • This module explores the limitations of significance tests and introduces confidence intervals as more informative alternatives for statistical analysis. Learners will gain an understanding of how statistical methods can mislead if not interpreted correctly and how to apply more reliable approaches to data evaluation.
  • The role of judgement in analysis
    • This module explores the critical role of judgment in evaluating the trustworthiness, validity, and generalizability of research findings. Learners will develop skills in assessing the strength of evidence and interpreting analysis results through practical examples and exercises. It emphasizes how to apply the warrant principle to make informed judgments in research analysis.
  • Research designs
    • This module explores the fundamentals of research design, including how to define cases, select populations, and ensure research validity. Learners will gain an understanding of how design elements contribute to the trustworthiness and clarity of research. The module also covers practical exercises to evaluate and improve research quality.
  • Sampling and populations
    • This module explores the fundamentals of sampling and population in research, covering techniques to select representative samples, the importance of sample size, and strategies to ensure validity and reliability in research findings.
  • What is randomness?
    • This module explores the concept of randomness in statistics, including how it is defined, how random samples are generated, and the challenges involved in ensuring true randomness. Learners will gain insight into the implications of randomness for social science research and data analysis.
  • Handling missing data: The importance of what we do not know
    • This module explores the causes and consequences of missing data in research, equipping learners with strategies to identify, report, and manage missing data effectively. It covers how to analyze its impact on study results and emphasizes best practices for minimizing bias and ensuring transparency in data reporting.
  • Handling missing data: More complex issues
    • This module covers advanced strategies for managing missing data, including practical techniques for identifying, analyzing, and handling missing values in datasets. Learners will gain an understanding of complex methods like multiple imputation and how to apply them to maintain data integrity and accuracy.
  • Errors in measurements
    • This module explores the causes and implications of measurement errors in social science research. It covers how errors affect data reliability, validity, and interpretation, and provides strategies for assessing and mitigating their impact.
  • Correlating two real numbers
    • This module explores the fundamentals of correlation analysis, focusing on Pearson's R, its applications in multivariate data, and the interpretation of real-world examples. Learners will gain an understanding of how to evaluate correlations, recognize their limitations, and apply them in practical scenarios.
  • Predicting measurements using simple linear regression
    • This module focuses on the principles of simple linear regression, including how to identify variables, interpret relationships, and apply regression models to make predictions. Learners will gain practical skills in analyzing data and understanding the foundations of statistical modeling.
  • Predicting measurements using multiple linear regression
    • This module introduces learners to multiple linear regression, including how to model complex relationships using interactions and dummy variables. It covers the practical application of regression techniques with real-world datasets and emphasizes the importance of selecting relevant variables for accurate predictions.
  • Assumptions and limitations in regression
    • This module explores the key assumptions and limitations of multiple linear regression, including issues like case independence, hierarchical data structures, and multicollinearity. Learners will gain the knowledge to critically assess regression models and apply them appropriately in real-world scenarios.
  • Predicting outcomes using logistic regression
    • This module covers the fundamentals of binary logistic regression, including how to interpret log odds, apply the model to real-world scenarios, and adjust variables to improve predictive accuracy. Learners will explore how to use logistic regression for categorical outcomes and understand the impact of different predictor variables. The module also includes practical exercises to reinforce these concepts.
  • Data reduction techniques
    • This module covers essential techniques for data reduction, including factor analysis and reliability coefficients. Learners will gain an understanding of how to simplify complex datasets and evaluate questionnaire validity, while also recognizing the limitations of these methods in real-world scenarios.
  • Presenting data for your audience
    • This module equips learners with the skills to present numeric results effectively through clear writing, tables, and visualizations. It covers strategies for simplifying complex data and communicating findings in a way that is accessible to diverse audiences. Learners will gain practical knowledge on improving readability and clarity in research reports.

Taught by

Sage Instructors

Reviews

Start your review of How to Make Sense of Statistics

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.