INTRODUCTION TO DATA ANALYSIS

OBJECTIVES

KEY VOCABULARY

DEFINITIONS

Data

Anything that has the potential to yield meaning 

Data Analysis

The conscious search for patterns in data, the explanation of why those patterns exist, and the justification of how those patterns answer the research question. 

Understanding Data Analysis

What do you do with words? Qualitative data?

By GT, I mean using an inductive data analysis method to search for repeated ideas, elements, or concepts.  For that end, I will start by reading the summaries in their entirety several times and immerse myself in the details, trying to get a sense of the collected data as whole. Reading the summaries in their entirety several times will enable me to start noticing patterns. While discovering patterns that are apparent, in other words, repeated ideas, elements, or concepts, I will engage in critically challenging them. I will look beyond the obvious to uncover hidden patterns. Once I will be satisfied with the uncovered patterns, they will be tagged with codes. I will apply the coding scheme to the entire data set. The codes will then be grouped into concepts, and then into categories. The categories will be used as the basis for a new theory about the reading process of different types of texts factoring in the language proficiency of the participants.

Grounded Theory Steps Summary

  1. Read the data several times to get a general idea
  2. Read again paying attention to details
  3. Keep reading and pay attention to patterns repeated ideas, elements, or concepts
  4. Critically challenge those patterns; think about what the data tells you, but also about what is missing
  5. Once you are satisfied with the uncovered patterns, tag them with codes
  6. Apply the coding scheme to the entire data set
  7. Group the codes into concepts
  8. Group the concepts into categories
  9. Use the categories to form a theory

What do you do with numbers? Quantitative Data?

  • mean – sum of observed outcomes divided by the total number of outcomes
  • median – the middle score 
  • mode – the number with the highest frequency in a set 
  • outlier – an outcome that is far from the rest of the data 
  • Standard Deviation – determine how spread the data is
  • z score – indicates how many standard deviations an element is from the mean
  • p value – Determine the likelihood of the null hypothesis to be true 
  • r value – correlation coefficient