WGU C224 - STUDY GUIDE WITH COMPLETE SOLUTIONS.

Characteristics of Quantitative Research numerical data (quantity); hypothesis & research procedure are stated BEFORE data collection; large sample size; rely on statistical procedure; low interaction with subjects; rely on controlling, measuring, and generalizing; objective by nature Quantitative Methods/Designs survey research; correlational research; causal comparative; experimental; single subject experimental Sampling techniques for quantitative research simple random; stratified; cluster; systematic; Simple random (quant) selection using table of random numbers Stratified (quant) selection based on dividing up into subgroups which have roughly equal representation Cluster (quant) intact groups are selected as by classroom, efficient but less representative Systematic (quant) take a population and select every Kth invidual i.e. sample population = 100 and you select every 5th person on list. Qualitative Research emphasis on words and feelings; research problems/methods evolve as understanding of topic increases; smaller sample sizes; relies on categorizing & organizing data into themes or patterns to describe & synthesize the data; high level interaction with subjects; many possible contexts & meanings for different people; *subjective by nature Qualitative Research Methods observation/field notes; interviews: face-to-face, phone, focus group; questionnaires; archival documents; journals; audio/video Qualitative Sampling Techniques intensity; homogenous; criterion; snowball; random purposive Characteristics of Action Research (comes out of qualitative research) persuasive & authoritative b/c it's done by teachers for teachers; relevant b/c solves real world problems; accessible b/c teachers already have built-in audience as test subjects; encourages school reform by providing an action plan; *practical by nature (see ch20). Selecting topics - Characteristics of good research topics researchable (can be solved by collecting and analyzing data); interesting enough to hold your attention (love it); significant (contributes to field of knowledge); ethical (no harm done); *manageable (keep it in scope) How to write a good research question solvable by collecting data; cannot be answered with simple yes/no; what is the effect of x on y (x is indep. Variable, y is dependent variable); i.e. What is the effect of an after school reading program (x) on students' reading comprehension scores (y)? Purpose & function of literature review see what's already been done; reveals what needs to be done; addresses the research questions; provides rationale for your hypothesis; avoids mistakes of others; may suggest ideas not previously considered; *provide new direction to your research Resource Identification Evaluation & Selection primary & secondary sources; WGU library: books, articles, e-reserves, ERIC; What was problem statement?; Who was studied?; Where was source published?; When was source published?; How was study conducted?; see ch 3 for more detail 5 types Hypotheses 1. Deductive, 2. Inductive, 3. Directional, 4. Non-directional, 5. Null Hypothesis based on sound reasoning consistent with theory or observation; provides reasonable explanation for a predicted outcome; states the expected relationship between variables; is testable within a reasonable time frame Evaluating a research report does it include all appropriate heading according to the research design? (i.e. intro, prob. Stmt., lit review, hypothesis, etc.); enough detail to allow the reader to completely understand the what, why, when, and how.; look out for researcher bias; review comprehensive list in ch. 22 Measurement instruments reliability - degree to which a test consistently measures whatever it is measuring; validity - degree to which a test measures what it is intended to measure; *validity assumes reliability Factors that threaten validity of measurement instruments unclear test directions; ambiguous test items; complex vocabulary & sentence structure; subjective scoring; items on test not covered in instruction; inconsistent testing procedures; *cheating (see pg 158) How to determine reliability? stability (test - re-test); equivalence (2 similar tests); *Internal Consistency (requires only 1 test administration) split half, Kuder Richardson, Chronibachs Alpha) ; see chapter 6 Types of Measurement Instruments (see Ch. 6) Achievement tests; aptitude tests; Affective tests; Projective tests Dependent variable the effect or outcome Independent variable the cause or treatment Measurement Scales variables - a placeholder that can assume any one of a range of values Variables nominal - named categories i.e. male/female; ordinal - ranks form high to low, i.e. class rank; interval - scores on achievement tests i.e. 90% and 100%; ratio - has true zero point i.e. height, weight, time, distance, *(pp145-146) Attitude scales commonly used in education likert - strongly agree to strongly disagree; semantic differential - select a position on a continuum i.e. Better to worse; *Rating scales - various forms i.e. select the statement that best describes you Data analysis (ch. 18) categorical analysis for qualitative data; statistical methods for quantitative data Analyzing Qualitative Data -reading/memoing; -classifying; -identifying themes & patterns; -coding Analyzing Quantitative data (commonly used statistical procedures) -descriptive statistics = describes a set of data; -inferential = tests of significance between two or more means, allows generalization, significance level p. <.05 or .01 Types of descriptive statistics (measures of) frequencies; central tendency; variability; relative position; relationship Types of inferential statistics t-tests; ChiSquare; Anova t-tests statistical measure: test means of 2 independent samples, significantly different? ChiSquare statistical measure: used for nominal scales (male/female), compares proportions actually observed to the proportions expected to see if they are significantly different, ie flipping a coin 50x Anova statistical measure: 2 or more means statistically different? Errors Null; Type I; Type II Null Hypothesis no difference between variables, any difference will be due to chance Type I error you determine the null hypothesis is false & it is actually true (0 difference); false positive (think you're pregnant but you're not) Type II error You determine the null hypothesis is true and it is false (there IS a difference), false negative (you think you are NOT pregnant, but you are), LESS COMMON (see pg 331) Survey research(quant) determines & reports the way things are, collect numerical data to test hypothesis or answer questions about current status of subject of study. I.e. political polls survey preferences, attitudes, practices, concerns or interests of voters. Correlational research (quant) collect data to determine whether and to what degree a relation exists between 2 or more quantifiable variables. Requires info about at least 2 variables obtained from single group of participants. Causal comparative research (quant) attempts to determine the cause or reason for existing differences in the behavior or status of groups of individuals. Cause = behavior or characteristic believed to influence some other behavior or characteristic Experimental research (quant) at least 1 independent variable is manipulated other relevant variables are controlled, and the effect on one or more dependent variables is observed. True experimental Research provides strongest results of any quantitative research Single subject experimental research (quant) used to study the behavior change that an individual or group exhibits as a result of some intervention or treatment Inductive reasoning developing generalizations based on observation of a limited number of related events or experiences Deductive reasoning arriving at specific conclusions based on general principles, observations, or experiences Basic Research pure research that aims to confirm an existing theory or to learn more about a concept or phenomenon Applied research research undertaken to solve a specific problem Intensity sampling (qual) selecting participants who permit study of different levels of the research topic; i.e. Select some good and some poor students, experienced and inexperienced teachers, or teachers with small and large classes Homogenous sampling (qual) selecting participants who are very similar in experience, perspective, or outlook. Produces a narrow, homogenous sample - makes data collection and analysis simple Criterion sampling (qual) selecting all cases that meet some set of criteria or have some characteristics. Researcher might select students who have been held back in 2 successive years or teachers who left the profession to raise children and then return to teaching Snowball sampling (qual) selecting more participants than needed for the study. I.e. if 25 participants were purposively selected by researcher but only 10 could take part a random sample of 10 from 25 potential participants would be chosen. This strategy adds credibility to study although initial sample based on purposive selection Random purposive sampling (qual) selecting more participants than needed for the study. i.e. if 25 were purposively selected by researcher but only 10 could take part a random sample of 10 from 25 potential participants would be chosen. This strategy ads credibility to study although initial sample based on purposive selection Achievement tests test that measures individual's current proficiency in given areas of knowledge or skill. Provide info re: how well test takers have learned material introduced. Standardized. Standard deviation a computed measure of how much scores vary around the mean score Aptitude tests test to predict how well an individual is likely to perform in a future situation variance a difference between what is expected and what actually occurs Affective tests test to measure affective characteristics - related to emotion, such as attitude, interest, and value. "Which would you prefer?" Pearson r used to correlate interval or ratio data Projective tests test that is ambiguous and not obvious to respondents. Respondents project their true feelings or thoughts in an ambiguous stimulus. -Rorschach inkblots, word associations Analysis of variance ... quartile deviation one half the difference between the upper quartile and the lower quartile in a distribution Wilcoxon signed-rank ... Spearman rho Correlation between ranks Action Research studies undertaken by practitioners in schools that address an actual problem or issue in the school or classroom. descriptive research Refers to research that describes an existing or past phenomenon in quantitative terms. inductive research the type of research in which general conclusions are drawn from specific data; compared to deductive research refereed journal articles reviewed by a panel of experts in the field, thus seen as more scholarly and trustworthy than articles from non-refereed or popular journals interval variable is a variable that has numbers as its values; the distance (or interval) between pairs of consecutive numbers is assumed to be equal ratio variable A variable that meets the criteria for interval variables but also has a meaningful zero point ordinal variable a qualitative variable that incorporates an order position, or ranking nominal variable a qualitative variable that categorizes an element of a population. Not only are arithmetic operations not meaningful for data that result from a nominal variable, but also an order cannot be assigned to the categories semantic differential a question format that asks respondents to rate their place on a scale between two bipolar adjectives, for example: happy or sad. Ethnographic research The study of human behavior in its natural context; involves observation of behavior and physical setting inferential analysis Measuring characteristics of only a sample from the population and then making inferences or estimates about the corresponding characteristics of the population from which the sample was drawn. types of descriptive statistics frequency, measures of central tendency (mean, median, and mode) Descriptive Research randomly select a sample; determine characteristics; infer characteristics of population based on sample Explanatory Research testing hypothesis and theories that explain the functions of a phenomenon in detail (cause and effect). Predictive Research predict the future status of 1 or more dependent variables based on one or more independent variables emic perspective insider's perspective; "get in their head" etic perspective external, social scientific perspective Basic Type of Research aimed at generating knowledge and theoritcal understanding about primary human function (ex. priming the memory) Evaluation Research Type of Research Determine how well social or educaitonal programs work in real world: Formative - developing judgements Summative: Tests ... Action type of reserarch addressing and solving specific problems which local practitioners confront in their schools/communities Orientational Type of Research Focus on collecting info to aid in advancing idealogical, political position, or orientation that a researcher believes will improve society (giving a voice to something) Applied type of research Answering real world, practical questions in order to provide relatively immediate results (solutions). ex:effects of student retention ... Epistemology studying knowledge itself Empricism idea that all knowledge comes from experience (look, feel, smell, taste, hear) Rationalism the philosophical idea that reason is the primary source of knowledge Deductive Reasoning process of drawing a conclusion that is essentially true if the underlying premises are true Inductive Reasoning holds that the fundamental premises act as helpful, but not decisive reason towards acceptance of a conclusion Quantitative Underlying Philosophy Things are stable controlled; facts are obtained ... Quantitative Purpose Test something to resolve ... to predict ... Quantitative Viewpoint Logical Empirical ... Deductive(LED) ... Quantitative Context Control; context is not taken into consideration, but controlled via methodological procedures Quantitative Focus Particularistic Specific, predetermined variables are studied ... Quantitative Orientation To solve To conclude ... To verify a predetermined hypothesis ... Quantitative Data NUMERICAL; data is in the form of numbers & statistics Quantitative Analysis Statistical techniques Descriptive Statistics ... Inferential Statistics ... Quantitative Instruments/Methods of data collection Tests closed-ended Surveys ... Rating Scales ... Statistics; Something is counted ... Quantitative Results Generalizable Findings can be generalized to other populations Qualitative Underlying Philosophy Things are dynamic; they change. What is "true" depends on the situation & setting Qualitative Purpose Describe something Understand something ... Qualitative Viewpoint Situational Inductive ... Qualitative Context Context matters; values, feelings, opinions, individual participants MATTER Qualitative Focus Holistic To see the "big picture" ... Qualitative Orientation To discover To explore ... Qualitative Data NARRATIVE or VISUAL; data is in the form of words, sentences, paragraphs, notes, or pictures/graphics, etc. Qualitative Data Analysis Generally accepted techniques for analyzing qualitative data such as reading/re-reading, memoing, coding, categorizing Qualitative Instruments/Methods of data collection Interviews, Observations, Focus Groups, Open-ended Questionnaires, etc. Qualitative Results Particular/specialized findings Findings are less generalizable ... Action Research Underlying Philosophy Goal to effect positive change Transformative ... Action Research Purpose To address or correct every day problems Action Research Viewpoint Applied research Practical ... Realistic ... Participatory ... Action Research Context Relevancy in a particular setting - often referred to as "local context" (school, classroom, district, community, etc.) Reflective ... Action Research Focus Problem-focused; focus on solving local problems Action Research Orientation To resolve; To make something better in local or immediate environment/setting ... Action Research Data All types of data may be involved; many action research studies utilize both quan & qual data Action Research Data Analyhsis Combination of techniques Statistical techniques used for numerical data ... Qual techniques used for narrative/visual data ... Action Research Instruments/Methods of data collection TYPICALLY a mixture of quant & qual methods are used(but doesn't have to be a mixture) Action Research Results Actions Learning