Analyzing Research Data and Presenting Findings Introduction to Educational Research (5th ed.) Craig A. Mertler & C.M. Charles Chapter 8 Analyzing Research Data and Presenting Findings
Qualitative versus Quantitative Data Qualitative data Analyzed inductively—thought process using logic to make sense of observations Goal is to uncover patterns, themes, categories, etc. Quantitative data Analyzed mathematically Goal is to describe data, show degree of relationship or difference, & determine likelihood that sample findings also exist in population
Analyzing Ethnographic Data Differs from the generic description of qualitative analysis Research questions often emerge after data collection (and even analysis) have begun; they are not foreseen Conclusions are drawn from a broad view of human behavior Analytical process is somewhat iterative and circular Identify topics (through data collection) Cluster topics into categories Form categories into patterns Draw explanations (conclusions) from patterns This on-going analytical process is known as logico-inductive or hypothetico-inductive analysis A very subjective process—bias is a strong possibility
Analyzing Quantitative Data Key is the separation of the researcher from the participants and the data—objectivity! Parameters—numerical indices that describe populations Statistics—numerical indices that describe samples parameters populations statistics samples
What Statistics Are Used For To summarize data in order to reveal what is typical and atypical about a group To show relative standing of individuals in a group To show relationships among variables To show similarities and differences among groups To identify error inherent in sample selection To test for significance of findings To make inferences about a population
Descriptive Statistics Numerical indices and procedures that summarize and simplify data about samples Measures of central tendency: Mean (M) Median (Mdn or Md) Mode (Mo) Measures of variability: Range (R) Variance (s2) Standard deviation (s or SD)
Descriptive Statistics (cont’d.) Measures of relative position: Percentile rank (%ile or PR) Stanine Converted scores (z-score, T-score, grade-equivalent, etc.) Measures of relationship: Pearson correlation coefficient (r) Many other correlation coefficients
Inferential Statistics Numerical indices and procedures used to make inferences about a population based on information from a sample Error estimates Confidence intervals Tests of significance Significance of correlation Significance of differences between means (t-tests, F-tests, etc.)
Cautions in Using Statistics Don’t try to do too much... Stay within your skills and knowledge of statistics! Your research questions and/or hypotheses should guide your analysis Statistical significance vs. practical significance
Presenting Your Findings Research findings are the information that results from your analysis Findings from qualitative data analysis are usually presented as summary statements and discussion about the patterns which were observed Findings from quantitative data analysis are typically presented in narrative form as well as visually (in tables or graphs)
Applying Technology… Web sites covering topics related to data analysis Dr. Trochim’s discussion of "Data Preparation" (http://trochim.human.cornell.edu/kb/statprep.htm) Dr. Trochim’s discussion of "Descriptive Statistics" (http://trochim.human.cornell.edu/kb/statdesc.htm) Dr. Trochim’s discussion of "Correlation" (http://trochim.human.cornell.edu/kb/statcorr.htm) Dr. David W. Stockburger’s online statistics textbook (http://www.psychstat.smsu.edu/sbk00.htm) Dr. David W. Stockburger’s bibliography and statistics web resources (http://www.psychstat.smsu.edu/introbook/biblio.htm) WebStat online statistical analysis program (http://www.webstatsoftware.com/) Dr. Trochim’s interactive page for "Selecting Statistics" (http://trochim.human.cornell.edu/selstat/ssstart.htm)