Powell Ch 9 Analysis of Data
4 Roles of Statistics
#1 Indicate the central point around which a mass of data revolves
#2 Show the broad or diverse the spread can be for a mass of data
#3 Reveal how closely or distantly certain features within the mass of data are related
#4 Indicate the degree to which the facts might have occurred by mere chance, or if there is a probability of their having been influenced by some factor other than pure chance.
Basic Steps in Statistical Analysis
a) Categorizing the data
b) coding the data
c) calculating the appropriate statistics
Wildemuth Ch 29 Content Analysis
Content analysis - the systematic, objective, quantitative analysis of message characteristics. The meaning of the term message in content analysis is broad.
The analysis procedures should be unbiased, valid, reliable, and replicable.
Ch 30 Qualitative Analysis of Content
Qualitative content analysis involves a process designed to condense raw data into categories or themes based on valid inference and interpretation.
It is a valuable alternative to more traditional quantitative content analysis, when the researcher is working in an interpretive paradigm.
Ch 31 Discourse Analysis
Discourse analysis is a tool that can be used to uncover other meanings (aside from literal) - meanings that we negotiate in our everyday and professional interactions, but that are rarely made explicit within those interactions.
It offers ILS researchers the potential to explore paths of inquiry that can provide us with a far greater understanding of some of the phenomena that affect us all, but its practice takes rigor, clarity, and even self-inquiry.
Ch 32 Analytic Induction
It is a specific form of inductive reasoning (taking specific facts and arriving general conclusion) used to analyze qualitative data. It is a formalized method for developing and refining a theory or hypothesis, directly from the data.
It has not been used in ILS research at this time.
Ch 33 Descriptive Statistics
Descriptive statistics is to summarize your results.
Descriptive statistics are the most essential view of your study findings and are so critical components of any report of your research.
Ch 34 Frequencies, Cross-tabulations, and the Chi-square Statistic
Graphical displays of data should show the data clearly, make large data sets coherent, present many numbers in a small space, and avoid distorting what the data have to say.
It is worthwhile to report descriptive statistics on your study's findings, including frequency distributions on key categorical variables.
Ch 35 Analyzing Sequences of Events
It's not enough to know which behaviors/actions occur most frequently - we also need to know the sequence of those actions and which sequences occur most frequently.
You can use step-by-step approach through simple first-order Markov models and transition matrices, look for frequently occurring longer sequences using maximal repeating patterns analysis, or focus directly on the similarity between sequences through optimal matching algorithms.
Ch 36 Correlation
Correlation helps you to examine the relationship between two variables.
Specifically it is the proportion of the variability in one variable that is explained by the variability in the other variable.
Correlation can be graphically represented by a scatter diagram.
Ch 37 Comparing Means: t Tests and Analysis of Variance
Lots of research questions in ILS fields compare two systems, etc. You usually calculate a mean for each group. The problem is that because you probably are using a sample from your population of interest, you need to take into account the variability across different samples and within each sample. The t test and ANOVA can tell the likelihood that the difference you observed will hold tru across the entire population of interest.
No comments:
Post a Comment