Quantitative Research Designs

Quantitative Research Designs

Introduction

Quantitative research deals with the analysis of numeric data and interpretation of results by the up a correspondence use of different statistical tools. The hypotheses in quantitative research are tested by different statistical tests. The main features of various quantitative studies are the use of instruments such as statistical tests or surveys to gather data, and dependence on the theory of probability to test statistical hypotheses that match to research questions of interest (Michael R, 2011).

The discussion below covers the comparison of two different types of research designs including experimental and non experimental research designs. It also reflects the strengths and weaknesses of both the designs. The last part of the discussion covers some issues of both the designs which include legal, ethical and socio-culture.

Discussion

There are three basic types of quantitative research designs which include

Non-Experiment

Experiment

Experimental Design and Non experimental Design

A study based on experimental design is that in which the respondents face to the agent because the researcher has assigned the exposure to the objective on the basis of study design.

This type of research design is based on trial and error method. This quantitative research design is consider strongest because the main objective of this design is to find “cause and effect” relationship between the variables. The key feature of any experimental design is “control”. The degree of control depends upon the alteration of the independent variable and the creation of equivalent experimental grouped.

In non experimental design the researcher cannot control the situations of the exposure of the subject. The application of these types of designs can be observed in descriptive studies. The study under these designs does not allow any manipulation in independent variable. Correlation analysis is the part of non experimental design which refers the relationship between the variables. But correlation ...