Quantitative: Deciding on the Right Analysis
​Topic 3: Data Analysis
Deciding on the appropriate analysis technique to address your research questions depends on several considerations, such as:
  1. Whether you are conducting descriptive research or correlational/causal research (i.e., have an independent (IV) and dependent variable (DV)).
  2. The level of measurement (e.g., nominal, ordinal, continuous) of each of your variables.   
  3. The nature of the inference in the research question you are asking. For example, each of the following inferences requires a different analytical approach:  
    1. to determine a relationship between variables
    2. to predict the magnitude of one variable based on another
    3. to examine the differences between groups
    4. to describe a population or sample
    5. to look at change over time. 
  4. Whether your data violate any of the assumptions of a specific analysis technique. In that case, you may have to choose another test.
    1. For example, perhaps your data are not normally distributed, but you want to examine the differences between two groups.  Rather than using the parametric approach (t-test), it may be more appropriate to use the nonparametric approach (chi-square). 

Before deciding on the appropriate technique for analyzing your data, make sure you have considered each of the points outlined above. You should also consult one or more of the following resources prior to beginning your analysis:
  • Creswell, J. W. (2008).  Research design: Qualitative, quantitative, and mixed methods approaches. Thousand Oaks, CA: Sage Publication. (p. 164, Table 8.3)
  • Pallant, J. (2013). SPSS Survival Manual (5th ed.). New York, NY: McGraw-Hill.
  • Salkind, N. J. (2011). Statistics for people who (think they) hate statistics. Thousand Oaks, CA:  Sage Publications.
  • William M. K. Trochim’s web application for selecting statistics: http://www.socialresearchmethods.net/selstat/ssstart.htm
  • The Dissertation Support Center Fellows.  
Back