Designing Experiments

Posted by Winnie Melda on February 8th, 2019

Introduction

There has been a focus on the on the theoretical model approach and the survey-based methodology for testing. However, there has also been growing criticism of that model due to its ineffectiveness. The incorporation of a greater emphasis on experimental studies is a route to advancements in this domain (White & Sabarwal, 2014). The inclusion of experimental research in information systems is receiving a lot of attentions and for that reason it is imperative to understand how to design experiments and achieve suitable results. The experimental study is also a powerful tool in the expansion of the scientific knowledge according to Konda and colleagues (1999).

How to design an experiment for collecting data

Designing a suitable experiment for testing a given hypothesis requires some suspicion and ingenuity (Boslaugh & Watters, 2008). In my case, I will begin by defining the objectives of the experiment in black and white of the hypothesis I will be testing. That will help me have a direction of what I want to achieve at the end of the experiment and how to approach it. I will then devise a strategy in a precise manner in light of how I will achieve the laid down objectives. That will incorporate thinking about the size as well as the structure of the experiment. I will also include the way the analysis of information will take place at this step. The third thing to do is to set down the operational details concerning how the practical performance of the experiment will takeplace. I will plan it according to the time frame available for conducting it, including the deliverables at each step.

Addressing validity threats

I will ensure that the experiment is valid by making sure that it does represent what its intention was. Experimental validity is the manner of presentation of the variables that impact the research outcomes and population generalizability (Shadish et al., 2002). There are majorly two types of validity: internal and external. Internal validity is where the ability of the study to determine whether there is a causal relationship between the independent or dependent variables while external validity is the generalizability of the study. In my plan to address the threats to the experimental validity, I will first have to know those threats and then apply a control mechanism against each specific threat. I will ensure that the study does not rely on some basic and unreliable assumptions, and I will also ensure that I use the as much sample size as possible from different locations. I will ensure that I thoroughly test the results many times in many environment and platforms before drawing my conclusion.

Will it be a true/quasi-experiment?

The experiment will be a quasi-experiment due to lack of randomly assigned groups as required by a quasi-experiment. It will also be a quasi-experiment because I am trying to demonstrate how one variable influences another variable. The experiment is also a type of cause and effects, making it serve as a quasi-experiment. It entails assigning groups randomly so that there are no pre-existing conditions that can influence variables and consequently mess up the study outcomes (Leedy & Ormrod, 2010). It will help me to me to have results that are true and reliable as per the samples used in the experiment. It will also make analysis easy.

References

Boslaugh, S., & Watters, P. A. (2008). Research design. In Statistics in a nutshell. Sebastopol, CA: O'Reilly Media.

Konda. R., Rajurkar, K., Bishu, R. & Guha, A. (1999). Design of experiments to study and optimize process performance. International journal of quality & amp reliability management, 16(1), 56-71.

Sherry Roberts is the author of this paper. A senior editor at MeldaResearch.Com in graduate paper writing service if you need a similar paper you can place your order from custom research paper writing service.