week2 lec1

Welcome and Introduction

• SPEAKER 1 (Humberto): Course Welcome

  • Welcomes students to the course "Data Analysis for Psychology" (shortened as Tapar One).

  • Patrick is introduced as the co-instructor of the course.

• Responsibility: Humberto and Patrick are the course organisers, overseeing its academic administration.

Course Structure Overview

• Teaching Duration: Patrick will lead the first 5 weeks of the course, addressing the initial block focused on exploratory data analysis.

• Study:

  • The course runs for multiple blocks with distinct topics. The first five weeks are outlined as follows:

  1. Week 1: Research design and data

  2. Week 2: Describing categorical data

  3. Week 3: Describing continuous data

  4. Week 4: Describing relationships

  5. Week 5: Functions.

  • The subsequent sections will cover probability, inference, and hypothesis testing in later weeks.

Introduction to the Study

• Study Participant Invitation:

  • Humberto invites students to participate in a university study regarding their expectations versus experiences in statistics training.

  • Ethics approval has been received for this study, ensuring confidentiality of responses (instructors won't have access to personal feedback).

• Voluntary Participation:

  • The study is voluntary, does not affect grades or course assessments.

Programme Representative Information

• Recruitment for Programme Reps:

  • The School of PPLS seeks new first-year program representatives. Instructions for applying are provided through a QR code.

  • Being a rep is a valuable experience that enhances CVs and interpersonal skills, beneficial for internships or job applications.

Course Materials and Structure

• Access to Materials:

  • A dedicated folder for the first week contains essential materials, including:

  • Overview videos

  • Assessment structure

  • Important course dates.

  • Students should complete tasks required to access RStudio software ahead of lab sessions starting Wednesday and Thursday.

• Attitude Towards Learning:

  • Humberto encourages students to adopt a positive mindset towards learning statistics, stressing that practice reports are not graded.

  • Emphasis on submitting all practice reports for feedback, which has predictive value for performance in final assessments.

Transition to Patrick

• Humberto introduces Patrick for the main teaching of the lecture.

Course Learning Objectives

• SPEAKER 2 (Patrick):

  • Details course mechanics: lectures, live R sessions, and lab sessions.

• Course Structure:

  • Lectures on Mondays and additional R programming sessions on Tuesdays. Labs are scheduled for Wednesdays and Thursdays.

Measurement and Data

• Theoretical Constructs:

  • Concepts such as intelligence and memory are discussed as abstract constructs within psychology that can be measured through various methods.

Levels of Measurement

• Three Levels:

  • Measurement is discussed in an abstract framework, with distinct levels:

  1. Construct Level: Abstractions (e.g., intelligence)

  2. Measurement Level: Methods (e.g., questionnaires to measure reading habits).

  3. Data Level: Specific variables generated from the measurements (e.g., number of books read).

Data Characteristics

• Statistical Error:

  • Discusses the concept of error as random variation affecting measurement (e.g., child distraction during tests).

Key Terms

• Reliability:

  • A reliable measure yields consistent results across multiple trials (e.g., repeated testing of the same individual).

• Validity:

  • Valid measures accurately assess the constructs they're designed to measure (e.g., a cognitive test reflects true cognitive ability).

Types of Data

• Categorical vs Numeric Data:

  • Data is categorized into mathematical types:

  • Categorical Data: Encompasses groups/categories without a numerical relationship. Examples include favorite pets or hair color.

  • Numeric Data: Represented by real numbers applicable to a continuous range, such as height or weight.

Categorical Data Breakdown

• Types Include:

  • Ordinary Data: Ordered category (e.g., Likert scale).

  • Binary Data: Only two categories possible (e.g., yes/no questions).

Subcategories of Numeric Data

• Continuous Data: Any value within a range (e.g., height).

• Discrete Data: Specific counts (e.g., number of books).

Levels of Measurement by Stevens

• Defined levels (1946) include:

  1. Nominal: Categorical data without order (e.g., hair color).

  2. Ordinal: Categorical data with order (e.g., Likert scales).

  3. Interval: Numeric data without a true zero point (e.g., temperature in Celsius).

  4. Ratio: Numeric data with a true zero point (e.g., height in centimeters).

Differences Between Measurement Types

• Nominal and Ordinal:

  • Nominal lacks a ranked relationship; ordinal has a meaningful order but not quantifiable differences.

• Interval vs Ratio:

  • Interval lacks a true zero (e.g. temperature in Celsius), while ratio has a meaningful zero allowing for ratio comparisons.

Data in R Programming

• Data Types in R:

  • Character: Nominal or categorical variables that don't hold numeric meaning.

  • Numeric: Continuous data, supporting mathematical operations based on measurement type.

  • Factors: Categorical variables with meaningful relationships for statistical analysis.

Structural Elements of Data Sets

• Tidy Data in R:

  • Features variables as columns and observations as rows. Each value must belong uniquely to a variable and observation.

Summary and Course Tasks

• Review of key objectives: connection of study design and data, understanding different data types, and application within R.

• Weekly Tasks:

  • Attend all lectures and labs.

  • Complete practice quiz available on the course site.

  • Utilize office hours for assistance and questions.

• Engagement: Interaction through discussion forums and seeking out student advisors when necessary.

Conclusion

• Patrick provides final remarks and encourages an active approach to learning in the course.