HCILecture_Week5A_5B - , ^ > / Z d , ^ / d & , h ^ h W > /...

Info iconThis preview shows pages 1–10. Sign up to view the full content.

View Full Document Right Arrow Icon
Evaluation: Randomised Controlled Trials Human-Computer Interaction Comp 3900 and Comp 6390 Semester 2, 2010 1 Lecture 5A & 5B: Human-Computer Interaction, Semester 2, 2010
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Types of evaluation (1) Evaluation to match requirements/specification Fault finding Cognitive walkthroughs Heuristic evaluation nit testing/laboratory testing Lecture 5A & 5B: Human-Computer Interaction, Semester 2, 2010 2 Unit testing/laboratory testing System/integration testing Evaluation to test observable qualities Usability lab Performance measures on standard data sets (for example, timing tests)
Background image of page 2
Types of evaluation (2) Evaluation in actual use Qualitative evaluation What will the users do with this system? How will they use the system? Lecture 5A & 5B: Human-Computer Interaction, Semester 2, 2010 3 Quantitative evaluation How well does this system compare to previous or competing systems?
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Quantitative evaluation Requires a quantity (i.e. a measurement) Uses a measurement of performance to compare the system being evaluated with other Lecture 5A & 5B: Human-Computer Interaction, Semester 2, 2010 4 competing systems. Uses statistical analysis to make judgements about the comparison between measurements taken with one system and measurements taken with another system.
Background image of page 4
Statistics (1) A statistic is a measurement of some attribute (variable) of one member of a population. A sample is a group of members taken from a Lecture 5A & 5B: Human-Computer Interaction, Semester 2, 2010 5 population. Sample statistics are the set of measurements of an attribute (variable) of the members in the sample (that had been taken from a population).
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Statistics (2) The distribution of a variable for a particular sample is the way that the Lecture 5A & 5B: Human-Computer Interaction, Semester 2, 2010 6 values of that variable are spread along the number line. Shown graphically as a histogram.
Background image of page 6
Statistics (3) Second example: the variable can have values with decimal places Lecture 5A & 5B: Human-Computer Interaction, Semester 2, 2010 7 (“real” numbers)
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Statistics (4) We can do arithmetic with the values of a variable: Compute the mean and variance and standard deviation Lecture 5A & 5B: Human-Computer Interaction, Semester 2, 2010 8 Find the median (line them up in increasing order and find the middle value) Find the mode (the most common value)
Background image of page 8
Sample versus Population A sample is a subset of a population. Example: You might interview a sample of 100
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 10
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/12/2010 for the course CSIT COMP3900 taught by Professor Duncanstevenson during the Three '10 term at Australian National University.

Page1 / 26

HCILecture_Week5A_5B - , ^ > / Z d , ^ / d & , h ^ h W > /...

This preview shows document pages 1 - 10. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online