Introduction

Learning Objectives

By the end of this section, you should be able to:

• Explain why standardized scales are important for measuring subjective experience in HCI
• Compute and interpret SUS (System Usability Scale) scores
• Compute and interpret NASA-TLX (Task Load Index) scores
• Visualize and compare scale scores across conditions using ggplot2
• Assess scale reliability using Cronbach's alpha
• Describe the principles behind Likert scale construction, reliability, and validity
• Understand the intuition behind Exploratory Factor Analysis and Confirmatory Factor Analysis
• Specify, fit, and interpret CFA and SEM models in R using the lavaan package
• Report fit indices, factor loadings, and structural paths according to current standards

1. Introduction

Why Measure Subjective Experience Quantitatively?

In HCI research, objective metrics like task completion time and error rate tell only part of the story. Two interfaces might produce identical performance numbers, yet users strongly prefer one over the other. Subjective experience --- perceived usability, mental workload, satisfaction, aesthetic appeal --- is a first-class outcome in HCI studies.

Quantifying subjective experience through standardized questionnaires lets us:

• Compare conditions statistically, just as we would with task times or error counts.
• Replicate across studies. When everyone uses the same scale, results are directly comparable. A SUS score of 72 means the same thing whether the study was run in Tokyo or Toronto.