Introducing Programmers to Pair Programming: A Controlled Experiment

Abstract

Pair programming is a key characteristic of the Extreme Programming (XP) method. Through a controlled experiment we investigate pair programming behaviour of programmers without prior experience in XP. The factors investigated are: (a) characteristics of pair programming that are less favored (b) perceptions of team effectiveness and how they relate to product quality, and (c) whether it is better to train a pair by giving routine tasks first or by giving complex tasks first. Our results show that: (a) the least liked aspects of pair programming were having to share the screen, keyboard and mouse, and having to switch between the roles of driver and navigator (b) programmers solved complex problems more effectively in pairs compared to routine problems, however, perceptions of team effectiveness was higher when solving routine problems than when solving complex problems and (c) programmers who started pair programming with routine tasks and moved on to complex tasks were more effective than those who started with complex ones and moved on to routine ones. We discuss how these results will assist the industry in inducting programmers without prior pair-programming experience into XP process environments.