NexP:

A Beginner Friendly Toolkit for Designing and Conducting Controlled Experiments

2017.09 | Interact 2017

In this paper, we introduce NexP (Next Experiment Toolkit), an open-source toolkit for designing and running controlled experiments. Unlike previous toolkits, it is targeted for the unmet needs of the beginners in experimental design, who may not have had prior statistical training, or experience in creating, implementing and executing controlled experiments. To accommodate such users, NexP features a hypothesis development process that scaffolds beginners into bridging the gap between daily language and formal statistical language. In our evaluation, we compared NexP against a state-of-the-art experimental design toolkit. Results showed that novices considered NexP more intuitive and easier to use. Users also reported that NexP helped them to better understand the experimental design process, making it a useful tool for both productivity and education.

Keyword

NexP, controlled experiment, toolkit, design platform

Publication

Part of the Lecture Notes in Computer Science book series (LNCS, volume 10515)

Publication

Project Info

Date:

2017-09-21

Author:
Xiaojun Meng, Pin Sym Foong, Simon Perrault, and Shengdong Zhao