This commentary on the previous data analysis chapters lays out a number of considerations for the data analyst, beginning with the research questions to be answered. These chapters focus on traditional variable-centered analyses (e.g., ANOVA, regression), person-centered analyses—looking for subgroups of participants with similar scores on a number of variables—and qualitative analyses of think-aloud protocols and other data about the learning process. Options are summarized with the pros and cons of each, depending on results of screening for statistical assumptions, sample size, data reduction (e.g., calculating factor scores), and some measurement considerations including whether multiple measures of construct(s) are gathered. Specific assumptions, sample size, and measurement needs for different tests are noted, as are approaches that may involve less stereotyping of demographic groups. Where the data analyst has more than one option for analysis, the choice that gives the most statistical power is noted.
|Original language||English (US)|
|Title of host publication||Handbook of Strategies and Strategic Processing|
|Editors||Daniel L. Dinsmore, Luke K. Fryer, Meghan M. Parkinson|
|Number of pages||13|
|State||Published - Feb 6 2020|
ASJC Scopus subject areas
- Social Sciences(all)