Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
84 Cards in this Set
- Front
- Back
Primary Purpose of Quantitative research
|
To answer questions in such a way that the results, conclusions, and inferences drawn from the study can be offered with confidence and integrity.
|
|
Four reasons Quantitative research is undertaken
|
1. Exploration
2. Description 3. Explanation 4. Prediction |
|
Stages of research
|
1. Introduction
2. Conceptual Framework 3. Methods 4. Results 5. Conclusions 6. References |
|
Three factors of a hypothesis
|
1. States the expected relationship between variables
2. Is testable 3. Consistent with existing body of knowledge |
|
A good quant research design includes these 4 factors
|
1. provides framework for adequate testing
2. Specifies independent, dependent, and control variables 3. dictates or reflects type of analysis to be used 4. outlines possible conclusion |
|
4 Types of quant design validity
|
1. Statistical conclusion validity (Type I and II error)
2. Construct validity 3. Internal validity 4. External validity |
|
Forms of Control in an experiment
|
1. Manipulation
2. Elimination or inclusion 3. Statistical Control 4. Randomization |
|
Types of Validity
|
1.Statistical
2. Construct 3. Internal 4. External |
|
Statistical Conclusion Validity
|
Effect size, Type I and II error test, and power. Did you select the correct method to prove your relationship between the independent and dependent variable?
|
|
Construct Validity
|
When people take it does it come up with the answer you believe it should?
|
|
Internal Validity
|
Effects of the independent variables on the dependent variable. Are the correct ind variables affecting the dep variable or is it another?
|
|
Major Threats to Internal Validity
|
1. History
2. Maturation 3. Testing 4. Instrumentation 5. Regression toward the Mean 6. Selection 7. Mortality 8. Diffusion (imitation of treatments) 9. Compensatory Rivalry 10. Resentful demoralization |
|
Major Threats to External Validity
|
1. Treatment-Attributes
2. Treatment-Setting 3. Multiple-Treatment 4. Pretest sensitization 5. Posttest Sensitivity |
|
Steps of Scientific inquirey
|
1. Identification of the Problem
2. Statement of the problem 3. Formulation of hypothesis 4. Prediction of consequences 5. Testing hypothesis |
|
What is a Population?
|
The entire collection of events/participants. The definition should be as explicit as possible
|
|
What is a Sample?
|
A subset of the population that is used to infer something about the characteristics of the population.
|
|
What are the types of Sampling?
|
1. Non-probability (Convenience)
2. Probability 3. Simple Random 4. Systematic 5. Stratified 6. Cluster |
|
Nominal Scale
|
0 or 1, male of female
|
|
Ordinal Scale
|
Orders people such as rank of army, scale of life stress
|
|
Interval Scale
|
A measure that we can identify differences in scale points
|
|
Ratio Scale
|
One that has a true zero. Length, volume, time.
|
|
Correlation
|
obtain a statistic expressing the degree of relationship between the two variables.
|
|
Normal Distribution
|
1. Frequently assumed it will be the distribution if we obtained the entire population
2. Allows us various techniques 3. Allows us to use sampling distribution of the mean 4. Allows us to make inferences about the values |
|
Null Hypothesis
|
We can never prove something to be true, but we can prove something to be false. We say "retain the null hypothesis" or "fail to reject the null hypothesis"
|
|
Type I error
|
Probability of Rejecting the null hypothesis given that it is true
|
|
Type II error
|
Beta is the probability of failing to reject the null hypothesis when it in fact is false and the alternate hypothesis is true
|
|
Measurement Validity
|
refers to the extent to which an instrument measures what it is intended to measure. One validates, not a test, but an interpretation of the data arising from a specific procedure.
|
|
Content Validity
|
degree to which the items of the test are a representative sample of the universe of content and/or behavior of the domain being assessed.
|
|
Criterion Validity
|
Positive correlation between the test and the ability and the test predicts an outcome
|
|
Construct validity
|
Allows the test to identify a trait in the subject
|
|
Assumptions of ANOVA
|
1. Homogeneity of variance
2. Normality 3. Independence of observations |
|
Homogeneity of Variance
|
Each of the populations has the same variance
|
|
Normality
|
The assumption that the conditions are normally distributed around the mean
|
|
Independence of observation
|
the observations are independent from one another
|
|
What is a significant F in an ANOVA?
|
is simply an indication that not all the population means are equal. It does not tell us which ones are different.
|
|
A Priori Comparison
|
multiple comparison methods that are chosen before the data is collected
|
|
Post Hoc Comparison
|
comparison methods that are chosen after the data is collected. Data mining.
|
|
Best A Priori test
|
Bonferonni t - which states that the probability of occurrence of one or more events can never exceed the sum of their individual probabilities
|
|
Post Hoc Test
|
Tukey or Least Sig Difference
|
|
Two Way Anova
|
All combinations of the levels of two or more independent variables
|
|
Chi Squared
|
Read this again
|
|
Authors must establish the importance of their topics and
|
their knowledge of prior research on the topics in the introductory and literature review section. (Smart 2005)
|
|
the purpose of undertaking research is fundamentally
|
to contribute to the accumulation of systematic knowledge of a topic (Smart 2005)
|
|
Three benefits of theories (Smart 2005)
|
1. Bring order to our quest to understand a phenomena
2. contribute to the accumulation of systematic knowledge about a phenomenon 3. generate empirical research on the phenomenon because of the coherence they bring to inquiries |
|
Parsimony
|
Only focusing on a couple variables. Good research.
|
|
Acute Multidisciplinary among independent variables
|
throwing multiple independent variables in to a linear regression does not make valuable findings (Smart 2005)
|
|
Effect Size
|
Should be used in ANOVA designs as part of good research design. (Smart 2005)
|
|
Qualitative research is emergent, what does this mean?
|
It comes from the research rather than utilized to prove a point.
|
|
What paradigm is quantitative research operating from?
|
Positivist paradigm - which holds that behavior can be explained through objective facts (Firestone, 1987)
|
|
What paradigm is qualitative research operating from?
|
Phenomenological paradigm - which asserts there are multiple realities that are socially defined. The researcher is immersed and gives enough detail to make sense of the phenomenon. (Firestone, 1987)
|
|
4 assumptions in research
|
1. Assumptions about the world - Positivist v phenomenological
2. Purpose - Cause v understanding 3. Approach - experimental/correlational v. ethnography |
|
Qualitative researchers should provide access to...
|
the decisions that are made in the process (Anfara, 2001)
|
|
Definition of rigor in qualitative research
|
the attempt to make data and explanatory schemes as public and replicable as possible. (Anfara, 2001)
|
|
Strategies to Ensure Credibility and Rigor
|
1. Triangulation: Multiple data sources, multiple points of view, variety of methods
2. Prolonged engagement in the field 3. Member Checks 4. Using a community of practice |
|
reflexivity
|
Acknowledging the researchers bias
|
|
Audit Trail
|
documenting the decision making process for Rigor
|
|
Ontology
|
Stance toward the nature of reality
|
|
epistemology
|
Theory of knowledge
|
|
axiology
|
values
|
|
rhetoric
|
language
|
|
Rossman and Rallis (2003) suggest that the purpose of qualitative research may be to
|
1. Describe
2. Compare and Contrast 3. Forecast 4. Learn about some fact of the social world (and in many cases change it) |
|
Why do a qualitative study instead of a quantitative study?
|
1. The researcher has determined that the quantitative measures cannot adequately describe or interpret the situation.
2. The researcher seeks to more fully describe a phenomenon |
|
Qualitative research is fundamentally...
|
interpretive.
|
|
Rossman and Rallis describe 5 Qualitative research techniques, what are they?
|
1. Phenomenology
2. Ethnogrophy 3. Case Study 4. Action Research 5. Grounded Theory |
|
Phenomenology
|
The study of a phenomenon. Subjective reality of an event as perceived by the study population.
|
|
Ethnogrophy
|
Investigating a culture by collecting and describing data about the culture.
|
|
Grounded Theory
|
Qualitative research that generates theory. Going into the process with a general though on the phenomenon but being guided by the phenomenon.
|
|
Transferability in Qualitative Research
|
refers to the degree to which the results of qualitative research can be generalized or transferred to other contexts or settings
|
|
Dependability
|
aka reliability. The extent to which the study and be replicated and repeated.
|
|
Confirmability
|
The ways a qualitative researcher can confirm their findings (data check and recheck, devil's advocate, data audit)
|
|
Triangulation
|
Cross-checking information and conclusions through the use of multiple procedures or sources to get corroboration. (data, methods, investigator)
|
|
Participation feedback
|
Getting the input and interpretation from the participants for credibility and rigor
|
|
Emic v Etic
|
Emic - insiders point of view; Etic - outsiders view and voice
|
|
4 Ways to Use Qualitative Research (Rossman and Rallis, 2003)
|
1. Instrumental: solutions and recommendations
2. Enlightenment: contribute to general knowledge 3. Symbolic: New ways of expressing the phenomena 4. Emancipatory: Change Oppressive structures |
|
Coding
|
First Open coding, then selective coding
|
|
Memoing
|
recording the thoughts and ideas of the researcher as they evolve through the study
|
|
Criteria for judging Qualitative Research
|
1. Credibility
2. Transferability 3. Dependability 4. Confirmability |
|
In Quant it's internal validity...In Qual it's
|
Credibility (prolonged engagement, use of peer debriefing, triangulation, member checks)
|
|
In Quant it's external validity...In Qual it's
|
Transferability (Provide thick description, purposive sampling)
|
|
In Quant it's reliability...In Qual it's
|
Dependability (Creating an audit trail, Code-recode, Triangulation, Peer examination)
|
|
In Quant it's Objectivity...In Qual it's
|
Confirmability (Triangulation, Practice reflexivity)
|
|
The purpose of analysis is to..
|
Bring meaning, structure, and order to data (Anfara)
|
|
Constant Comparative Analysis is...
|
In qualitative data analysis when simultaneously collecting data and analysing data to generate categories with two iterations.
|
|
Internal validity in Qualitative Research
|
concerned with how trustworthy the conclusions are that are that are drawn from the data and the match of these conclusions with reality.
|