Saturday, March 28, 2009

Quantitative Descriptive Research, True/Quasi Experiments

Very rough notes.
Lauer and Asher, “Quantitative Descriptive Research.”
Goes one step ahead of descriptive research designs like ethnography and case studies. It not only identifies variables, but also isolates the most important ones and quantifies them to some extent. It also interrelates those variables. However, no controls groups are created and no treatment is applied.
Class comment:
correlational research, Morgan.
actually it is still a qualitative research as it does not make causal relationship.
And relationship can both be negative or positive.
Subject Selection:
More than in both case studies and ethnography. More than the variables: at least 1:10. For representativeness.
Variable Selection: Independent and dependent variables: Independent variables do not depend on treatment. dependent variables change due to treatment.
Hypothesis: alternative hypotheses. but for different reason, it helps for understanding, but also is important statistically. Null hypothesis is key in chi analysis. You have to assume the null hypothesis.
Statistical analysis of two variables:
class comment:
N:k=10:1 (at least)
(significant: likelihood of occurance by chance, typical is 0.05, significant does not mean important)
what sense doe it make in such correlational research to differentiate dependent and independent variables?
Try to stay away from differentiating.
variance is imp: spread of data from mean. what of the other variables might be accounting for that variance.
Moderator variables

Faber’s “Popularizing Nanoscience; The Public Rhetoric of Nanotechnology, 1986-1999
Purpose: how new subjects in science and technology are represented in the popular media; how discourse works to imterpret and translate technical material and to build public recognition and awareness of science, technology and other specialized academic fields.
Subject Selection: Faber studies how new subjects in science and technology are represented in public media. So, the subject selection here becomes his selection of articles published in popular media. He searched "nanotechnology" and "nanoscience" and he found 885 articles in his first search in his university database. Then he later separated 203 articles that were published in popular media. He collected articles published between 1986 to 1999.
Data Collection:
ABI/ProQuest database
From 1986to December 1999
Use of keywords nanotechnology and nanoscience
Article texts as the search criteria
‘All’ for publication type
Result: 885 articles
Popular media: 203
Data Analysis:
· Categorized articles by month and year.
· Analysis of both propositional and grammatical structure (combined give meaning)
· Use of descriptive categories theme, rheme, (before verb and after verb) and topic (content-based interpretative summary of the propositional content)
· Correlated these catogeries to propositional content to create representation (fourth category)
· 39 topics (termed these topics representations as that is how nanoscience was represented)
· Categorized representations temporally,
· Created three-part hierarchy by frequency of mention in the data set. The hierarchy consists of “high-occuring,” “average-occurring,” and “low occurring.”
· Temporal findings: the representations manufacturing, medical applications, and science fiction endured across the entire data-collection time.
· Limitedness of the generalization: “this study is limited by the temporal choices of articles and my own decision to restrict my analysis to the general representations of nanoscale science technology presented by each article. Lack of third-party testing.
Conclusion: the process of presenting technical information for general audiences can be enabled by combining social and technical approaches.

Golen, “A Factor Analysis of Barrier to Effective Listening
Purpose/Research Question:
· To determine which barriers are perceived to be the most frequently encountered that may affect listening effectiveness among business college students and to expand the Watson and Smeltzer study
· How frequently do barriers to effective listening affect the listening process as perceived by business college students?
o What specific listening barriers do students perceive as the most frequent?
o How do the listening barrier factors differ based on selected student demographic variables?
Subject Selection:
· 3 large business com lecture sections of approx 400 each; there were 33 breakout sections with 35 students each.
· Random sample of 10 sections was selected from 33 sections
Data Collection:
· Each student completed a questionnaire containing 25 barriers to effective communication
· Total of 279 questionaires were collected
Data Analysis:
· Variable identification: 25 barriers
· Then obtained the most common barriers through literature review, feedback from advanced students, and interview with professors—reliability
· Independent variables: major, age, sex
· Dependent variables: listening for details; distraction by noise; daydreaming; detour due to the speaker’s ideas; lack of interest in the subject …. (mean).
· Relationship between independent and dependent variables: only gender.
Lauer and Asher, “True/Quasi Experiments.”
· True Experiments:
o Treatment
o Cause and effect relationship between treatments and later behaviours
o Randomization to avoid threats to internal and external validity
o Hypothesis
o Measurements and statistical analyses
· Quasi-experiments
o Useful when researchers cannot randomize groups
o Enables researchers to make cause-effect inferences
o Three distinguishing features:
§ No randomization
§ Should have at least one pretest or prior set of observations to examine whether the groups are initially equal or unequal
§ There must be research design hypotheses to account for ineffective treatments and threats to internal validity
o Strong and weak quasi-experiments
Carroll et al, “The Minimal Manual.”
Purpose: to examine whether Minimal Manual “affords more efficient learning progress than standard self-instruction manual or not.”
Subject Selection:
· Two experiments:
o Experiment 1: performance on 3 days of simulated office work experience
o 19 subjects, 10 in MM and 9 in SS. Screened on the basis of their prior experience
o Experiment 2: 32 subjects (same selection criteria)
Data Collection:
· Experiment 1
o Periodic performance tests
o Subjects in a simulated atmosphere
o At the end of every day, an interview and administrative sessions held; 8 performance tasks
· Experiment 2
o Observer makes a detailed notes about the activities and outcomes during the hands-on portion
o Six performance tests
Data Analysis:
· Experiment 1
o Two dependent measures were collected and analyzed in this experiment: time to complete training and performance tasks; b) performance on eight word processing tasks. (summing the number of correct activities)
· Experiment 2
o Same process, summing of the number of correct.
Their analysis supported their hypothesis that MM affords better learning experience than SS.
This research seems to have problems like the lack of interrater reliability and the lack of randomization. This is a quasi-experimental research. However, the groups are not kept intact, Notarantonio, “The Effects of Open and Dominant Communications Styles on Perceptions of the Sales Interaction.”
· Whether or not communicator styles affect perceptions of the sales interaction
· The study hypothesizes that a) openness of the salesperson adds effectiveness to selling; b) the more dominant the salesperson, the more effective she or he would be
Subject Selection:
· 80 subjects (undergraduate business adm), 41.3% male and 58.7% female; Freshman 92.1%
Data Collection:
· A complete self-report
· After viewing the tape, subjects were asked to complete a questionnaire consisting of 42 items. (likert scale, but not specified)
Data Analysis:
· No analysis on self-reports
· For data received from questionnaire, separate two-way ANOVAS were run with Openness and Dominance as independent variables for the measures of openness, dominance, and the six composite measures. All measures ranged from 1 to 7

Kroll’s “Explaining How to Play Game.”
· One goal was to examine changes in the informational adequacy of the explanations as a function of grade level

Subject Selection:
· 24 students in grade 5, 26 in grade 7, 19 in grade 9, 27 in grade 11, and 27 college freshmen
Data Collection:
· Students were asked to view the film about playing game and then write explanations
· Then ten-item multiple choice quiz was given to test their knowledge of the game
· Game quiz was validated by testing it with advanced students who did not know about the game
· Two raters independently scored all explanations from students
· One rater was vaguely aware of the purposes whereas the other was not
· However, the correlation between them was strong
Data analysis:
· One goal was to examine changes in the informational adequacy of the explanations as a function of grade level
· The effect of grade level on game information scores was analyzed with a one way ANOVA
· In addition to total scores for overall informativeness, scores for each of the ten individual game elements were examined
· Z statistics were used to order the ten game elements from those exhibiting the strongest developmental trends to those with the weakest trends
· Finally Chi-square tests were performed to assess the statistical significance of the association between grade level and students’ listing of the game pieces, between grade level and students’ mentioning the object of the game, and between grade level and students’ use of the three explanatory approaches

No comments:

Post a Comment