Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
Research Design
Midterm
| Question | Answer |
|---|---|
| Qualitative Research | Exploring and understanding the meaning individuals/groups ascribe to a social/human problem. Involves emerging questions & procedures, data collected in part. setting, identify themes during data analysis. More flexible. Data tends to be textual. |
| Types of Qualitative Research (6) | 1. Narratives (biographical study, oral history) 2. Phenomenology 3. Ethnography 4. Grounded Theory 5. Case Study 6. Content Analysis |
| Qualitative Research | Testing objective theories or non-theory based ?s by examining the relationship among variables. Measured w/ instruments, # data, analyzed using statistics. More concrete, use of scientific method. Intro, lit & theory, methods, results, & discussion |
| Types of Quantitative Research (2) | 1. Experimental Designs 2. Non-Experimental Designs |
| Mixed Methods Research | Approach to inquiry that combines or associates both qualitative and quantitative forms. |
| What is a worldview and what are the 4 worldviews? | A basic set of beliefs that guide action. 1. Positivism/Post-positivism 2. Constructivism 3. Transformative 4. Pragmatism |
| Positivism/Post-positivism | Emphasizes quantitative approach, empirical observation & measurement & theory verification. Scientific method accepted approach to research. Can't know 100% but can build knowledge through careful observation and measurements of the objective reality |
| Constructivism | Assumes individuals seek to understand the world they live & work in. Relies on subjective meanings & participants view of situation/phenomenon being studied. Use structured interviews, open ended ?s. Reality is subjective & experiential. Qualitative |
| Transformative | Research should include political policy & need to change policies to make change to decrease/ rid social oppression. Widely held by action researchers, agendas to support various movements or oppressed/minority individuals. Equality and social change. |
| Pragmatism | Arises out of actions, situations and consequences rather than antecedent conditions. "Whatever works is likely true." Researchers may use all approaches available to understand problem, most likely to use mixed methods research, works w/other worldviews |
| Guidelines when conducting research (5) | 1.minimize the risk of harm 2. obtain informed consent 3. protecting anonymity and confidentiality 4. avoiding deceptive practices 5. Providing the right to withdrawl |
| Debriefing | After the data has been collected, it involves explaining the study in more detail or answering questions. APA requires debriefing after a study that includes deception or may cause harm |
| APA guideline #4 regarding multicultural issues | Culturally sensitive psychological researchers are encouraged to recognize the importance of conducting culture-centered and ethical psychological research among persons from ethnic, linguistic, and racial minority backgrounds. |
| What are researchers encouraged to consider in conceptualizing their research design? | Psychological (rather than demographic)contextual factors of race, ethnicity, language, gender, sexual orientation, socio-economic status, and other social dimensions of personal experience |
| What are statistics and what are the two kinds? | A branch of applied mathematics that deals with the collection and interpretation of quantitative. Descriptive and inferential |
| Descriptive statistics | May be a graph or plot of the data, a picture that describes the data, or may be a numerical quantity that characterizes the data. |
| Histogram | Grouping of data into bins, also called a frequency distribution |
| Positive Skew | down from left to right with low outlier |
| Negative Skew | up from left to right with low outlier |
| Normal | Mean and equal bars going down on each side, bell curve |
| What are numerical summaries? | Measures of central tendency, indicating the middle or center of the data (where most data falls): mean, median, mode |
| Mean | (M) The arithmetic average, sum of all the observations divided by the total number of observations (N). It is worthless without the standard deviation |
| Median | (Md) Found in the middle of the set of data values |
| Mode | The most frequently occurring value, good measure to use when evaluating nominal data (something that can't be measured continually, w/numbers) |
| What is dispersion and how is it described (3) | the spread of the values (data); variance, standard deviation, and range |
| Variance (draw a picture of low and high variance) | Indicates how much variability, used to characterize the dispersion of data in a given population calculate mean of data, subtract amount each score deviates from mean, square that deviation. |
| Standard deviation | (SD) The square root of the variance, provides a more accurate and detailed view of the dispersion of data. Must accompany the mean. |
| What percentage are within 1, 2, and 3 standard deviations from the mean? | 68.26% (1st SD 34.13), 95.46% (2nd SD 13.6), 99.73% (3rd SD 2.14) |
| Range | the highest value (max) minus the lowest value (min) |
| Scales of measurement (3) | Nominal: gender, color, marital status Ordinal: ranked (hospital pain scale) Continuous: (interval or ratio) height of boy over time, varying temperature on a particular day (within range) |
| Statistical inference | the act of generalizing from a sample to a population with a calculated degree of certainty OR making inferences about a population on the basis of a sample. |
| Independent variable | the variable believed to influence or cause the other variables/ the outcome. Could be a variable you control such as treatment or one not controlled such as exposure. Could also be demographic factors such as age or gender. |
| Dependent variable | The variable that is influenced or modified by the other/ some treatment or exposure. May represent the variable you are trying to predict, also called the outcome variable, it's definition depends on the context of the study. |
| P-values | level of significance = alpha , probability of error accepted when determining that the observed results are valid, not due to chance. P< or = alpha means statistically significant |
| True experimental design | researcher manipulates an IV with treatment and comparison groups and attempts to exercise high degree of control by randomly assigning participants |
| Quasi-Experimental design | "Sort of" an experiment, includes manipulated IV but lacks important controls (random assignment) OR lacks manipulated IV but has controls |
| Non-equivalent group design | Study includes a manipulated independent variable but lacks random assignment of participants to conditions(offering a class a two times and allowing students to choose which they want instead of randomly assigning) |
| Pretest-posttest design | single group of participants measured on the DV before and after the manipulation of the IV, NO CONTROL GROUP (DARE program) |
| Interrupted Time-Series Designs | examine a series of observations both before and after a treatment, evidence of treatment effect occurs when there are abrupt changes (discontinuities) in the time series data at the time treatment was implemented n(# of falls on ice) |
| Time Series with Nonequivalent Control Group | researchers make a series of observations before and after treatment for both treatment group and comparison group |
| Non-Experimental Designs (3) | AKA correlational studies, researcher looks for associations among naturally occurring variables, no manipulation of IV. 1.Naturalistic observation 2.survey research 3.archival research/ historical or retrospective |
| Naturalistic observation | observing and recording the variables of interest in the natural environment, no manipulation by researcher |
| Archival/ historical or retrospective research | involves data that is already collected and recorded and therefore cannot be manipulated |
| Moderating variables | change the relationship or level of effect between two variables. May increase relationship strength, decrease it, or change the direction of the relationship. Generally nominal, INFLUENCES THE STRENGTH OF RELATIONSHIP |
| Mediator/ co-variates | accounts for the relation between the predictor and the criterion, RESPONSIBLE FOR RELATIONSHIP |
| Internal validity | IV produces the observed effect on the DV, THE STUDY MEASURES WHAT IT IS SUPPOSED TO |
| Threats to internal validity (7) | 1.history 2.maturation 3.testing 4.instrumentation 5.statistical regression 6.selection 7.mortality |
| History | an event (external to participants) occurs that may have an effect on the outcome variable. Most likely a problem in pre-post designs (students in gun program also hear of school shooting and and that influences their post-test attitudes towards guns) |
| Maturation | Systematic, time-related changes in the participants that occur between presentation of the levels of the IV in a repeated design or time series design |
| Testing | Repeated measurement on the same variable leads to improved performance due to learning from practice |
| Instrumentation | Values of the DV change because of faulty experiment, human scorer gets tired, etc...(not calibrating the scale) |
| Statistical regression | pre-post dsign when people score extremely high or low the first time, will see regression towards the mean on the second test so unable to conclude post DV resulting from treatment or regression towards the mean |
| Selection | choice of participants for treatment (or control) groups that is based on criteria such as gender, SES, mental health diagnosis, etc. Pre-existing differences between levels of each factor, unable to know if IV produced effect or pre-existing differences |
| Mortality | Loss of participants from the treatment or control groups due to death or dropping out |
| What is a survey? | A method of gathering information from a sample of individuals. Can be descriptive, marketing, etc... |
| Steps in planning a survey (4) | 1.ask clearly what is the research objective or question 2.Decide how data will be collected (mail, electronic, etc...) 3.Decide target population to be sampled (helps decided #2 4.Search lit to help decide what info need to gather |
| Types of sampling (4) | 1.simple random sampling 2.systematic sampling 3.stratified random sampling 4.cluster sampling |
| Simple Random sampling | every person in the population has an equal chance of being chose |
| Systematic sampling | pull every 5th file, every 3rd person will be in the control (assuming the number is not related results) |
| Stratified random sampling | Strata= group, sampling multiple sub-populations (whites, blacks, Hispanics)use simple random sampling or systemic sampling for each strata. |
| cluster sampling | households become participants, students in a district, each school is a cluster |
| Multi-stage sampling | Combining more than one type, cluster & simple random, systematic & cluster, etc. |
| Designing survey questions (5) | -K.I.S.S. -need demographic ?s & answer research ? -closed-ended but at least one open ended, allow participant to include something researcher hadn't thought of -open ended= continuum (age) -language understandable not insulting |
| Avoid these when designing research questions (4) | -?s that tax memory -?s that might be self-incriminating -biasing or leading the respondent -Double questions |
| Formatting the questionnaire (6) | -K.I.S.S.- explain your interests -Attractive & readable (font size, color, images, inviting, thank them) -Title -brief, clear instructions bold or underlined -demographics- placement -order of ?s , first light/inviting, research ? in middle |
| Pretesting the survey(4) | -select a small sample (10-20 ppl) -explain your intentions -survey just as planned -look for errors, missing responses, inconsistencies, etc. |
| Cover letter (6) | -authority, important endorsement -appeal to self-interest -appeal to professional interest -appeal to altruism -appeal to curiosity -incentive |
| How to increase survey response (6) | -brief, <15 mins to complete -appealing format -motivating cover letter -prepaid postage if a mailed survey is used -follow up after survey is sent out -guarantee confidentiality or anonymity |
| External Validity | degree to which the results can be generalized to other individuals and other settings |
| Threats to external validity (2) | 1.population validity 2.ecological validity |
| Population validity | the extent to which one can generalize from the study SAMPLE to a defined POPULATION (study on 5th graders can't be generalized to 3rd graders) |
| Ecological validity | extent to which the results of a study under certain environmental conditions can be generalized to other or different environmental conditions (study on students in rural school can't be generalized to students in city school) |
| What is qualitative research? | seeks out the "why", not the "how" of it's topics, analysis of unstructured information like interviews, emails, notes, feedback forms,etc.. |
| What is the purpose of qualitative research? | Used to gain insight into people's attitudes, behaviors, value systems, concerns, motivations, aspirations, culture, or lifestyles. To understand how people make sense of their lives and experiences |
| Phenomenology | attempt to understand the meaning of events & interactions to ordinary people in particular situations Foundation ?: what is the meaning, structure, & essence of lived experience of this phenomenon by one or many individuals? MOST COMMON IN SS |
| Grounded Theory | development of inductive, "bottom-up," theory that is "grounded" directly in empirical data. Foundation ?: What theory or explanation emerges from analysis of data collected about this phenomenon? GOAL IS THEORETICAL SATURATION |
| Ethnography | From Anthro, the discovery & description of culture of a group of people. Foundation ?: What are the cultural characteristics of this group of people or of this cultural scene? ETIC vs EMIC (science/observe/document vs culture/ask them driven approach) |
| Trustworthiness | includes credibility, transferability, dependability, and confirmability |
| Credibility | Qualitative term for internal validity How to achieve: prolonged engagement, peer debriefing, member checks (at least 2 checkers) |
| Transferability | Qualitative term for external validity: can the research be applied to other groups experiencing the same phenomenon? How to achieve: thick description of the participants in this sample |
| Dependability | Qualitative term for reliability How: internal auditor keep meticulous records of interviews, observations, & document process of analysis in detail; External auditor, not part of the experiment verify process, analysis, & logic used to interpret data |
| Confirmability | Qualitative term for objectivity: degree to which the findings are product of focus of the inquire and not bias of researcher. How: Maintain trustworthiness, keep a journal, document clearly any conclusions, have evidence to support |
| Steps of qualitative research (7) | 1.transcribe interview 2.clean interview 3.code interview 4.review your questions for next interview 5.repeat 6.domains, categories, themes (sub themes) 7.results |
| Transcribe interview | Type out EVERY single word, utterance, sigh, etc on the recording- everything has meaning. Do not correct wrong words, slang, etc |
| Clean the interview | take out all questions and comments made by the interviewer |
| Code the interview | -Begin reading through cleaned interview -Use highlighting and colored text and start separating out the different themes -Begin listing themes as KEY |
| Review questions | -look to see if you are getting the information that you wanted -were you questions good? Did participants understand them? -Make any edits to questions for the next interview |
| Domains, Categories, & Themes | -Using your KEY, start organizing all your themes into categories -Themes show up in at least two interviews -group those categories into domains |
| Example of domains, categories, & themes | Domain I: Support Category I: The couple Theme I: pre-existing condition Category II: outside support Theme I: Extended fam Theme II: other women with endo Category III: lack of support Theme I:family Theme II: medical professionals |
| Results | -Introduce your participants: use synonyms -Provide your results: use direct quotes, pick best that accurately represents theme, try to use quote from every participant |
Created by:
klthomas0123
Popular Psychology sets