Research Methods Tutorials: Introductions to Quantitative and Qualitative Methods

In the Social Sciences, the goal of a quantitative research study is to determine the relationship between one thing and another within a population. For example, the grades students achieve in a given course and the instructors for the different sections. Quantitative research designs can be either descriptive (subjects typically measured once) or experimental (subjects measured before and after a treatment). A descriptive study establishes only associations between variables; an experimental study establishes causality.

(Click here to view a larger version of this graphic)

Text description of "Main Characteristics of Quantitative Research" for web accessibility. 

The aim of a quantitative research study is to classify features, count them, and construct statistical models in an attempt to explain what is observed.

When reporting the results of a study using quantitative methods:

1. Explain the data collected and their statistical treatment as well as all relevant results in relation to the research problem you are investigating. Interpretation of results is not appropriate in this section.
2. Report unanticipated events that occurred during your data collection. Explain how the actual analysis differs from the planned analysis. Explain how you handled any missing data and why any missing data does not undermine the validity of your analysis.
3. Explain the techniques used to "clean up" your data.
4. Choose a minimally sufficient statistical procedure; provide a rationale for its use and a reference for it. Specify any computer programs used.
5. Describe the assumptions for each procedure and the steps you took to ensure that they were not violated.
6. When using inferential statistics, provide the descriptive statistics, confidence intervals, and sample sizes for each variable as well as the value of the test statistic, its direction, the degrees of freedom, and the significance level [report the actual p value].
7. Avoid inferring causality, particularly in nonrandomized designs or without further experimentation.
8. Use tables to provide exact values; use figures to convey global effects. Keep figures small in size; include graphic representations of confidence intervals whenever possible.
9. Always tell the reader what to look for in tables and figures.

If you are using pre-existing data:

You should still explain the methods used to obtain the data, describe any missing data and be able to explain why the missing data does not undermine the validity of your end product.  

You should be able to defend every part of your project. It may be helpful to look at your proposed research design or final product critically, as though you were trying to find problems with it. That way you can address those before your share your results.

Adapted from USC's Research Guide on Quantitative Methods. 

At its core quantitative research includes applying statistical techniques to numerical data. 

This will require you to:

• gather data, either on your own or by obtaining a pre-existing dataset.
• clean it. Make sure that there aren't any errors and that everything is formatted properly. 
• determine the appropriate test or analysis.
• interpret your results to draw conclusions.

There are a lot tools out there to help you plan your research project and navigate the analysis process. One of those tools is the Sage Research Methods Project Planner. This section on Data Analysis & Interpretation may be especially helpful. 

Another great tool is the Sage Research Methods Stats Test, which can help you identify an appropriate test given your research conditions. 

Statistics is a class that many of us only take once and it's okay to reference text books or other materials to familiarize yourself with the material when you need it. 

Sage Research Methods also publishes a number of Little Green Books on Quantitative Research. This can be a great place to go to learn more about different methods or to get ideas for your study. 

Additional resources that may be helpful: