flashcards- Review Sheet Final Exam.txt
Home > Flashcards > Print Preview
The flashcards below were created by user
on FreezingBlue Flashcards
. What would you like to do?
what is a hypothesis? and what is its format?
- * A tentative and testable prediction about how changes in one thing is expected to explain and be accompanied by changes in something else.
- * The IF will HAPPEN when ALTER something statement
what are the strengths of qualitative research?
- * Research methods that emphasize depth of understanding and the deeper meanings of human experience, and that aim to generate theoretically richer, albeit more tentative, observations.
- * Commonly used qualitative methods include participant observations, direct observation, and unstructured or intensive interviewing.
What is Evidence-based practice?
- using evidence in practice- it is a process in which practitioners make practice decisions in light of the best research evidence available.
- * Involves evaluating the outcomes of practice decisions.
Ethical guidelines like
- * Voluntary participation
- * Informed consent- participants know what they are agreeing too.
- * No harm to the participant- unless knowingly and willingly accept risks of harm
- * No Deceiving subjects
- * Long term benefits outweigh violation of certain ethical norms
what is a paradigm?
- A model or frame of reference that shapes our observations and understandings.
- It interprets the world
- o For example, �functionalism� leads us to examine society in terms of the functions served by its constituent parts, whereas �interactionism� leads us to focus attention on the ways people deal with each other face-to-face and arrive at shared meanings for things.
what does functionalism paradigm say?
looks at everything as having a function.
What does interactionism paradigm say?
focuses on people's interaction face-to-face.
what does postmodernism?
completely impossible for anyone to be completely objective/ everything is subjective/ no objective truth.
what does Contemporary positivism paradigm say?
cannot be completely objective; there is objective truth to situations.
what does the Interpretivism paradigm say?
gain empathetic understanding of how people feel inside- deeper meanings of feelings
what does the critical Social Science paradigm say?
o focuses on oppression and competition between groups
what is deductive Approach relating to theory?
(top down) - start with known theory and create hypothesis
what is a theory:
* A systematic set of interrelated statements intended to explain some aspect of social life or enrich our sense of how people conduct and find meaning in their daily lives
what is inductive Approach related to theory?
- (bottom up) start with observations, create and test hypothesis then develop theory
- * Example: use of child theory and play therapy to allow a child to play with figures in a sand tray.
what is the definition of a concept?
* A mental image that symbolizes an idea, an object, an event, or a person.
what are the four types of non-probability sampling?
- 1. Accidental
- 2. Snowball
- 3. Quota
- 4. judegmental
what is the definition of sampling?
* A sampling method aimed at ensuring that enough cases of certain minority groups are selected to allow for subgroup comparisons within each of those minority groups.
define Quota sampling:
- a) A type of nonprobability sample
- units are selected into the sample on the basis of prespecified characteristics so that the total sample will have the same distribution of characteristics as are assumed to exist in the population being studied.
what are the advantage and limitation of quota sampling?
- i) Advantage: Convenience and more representative than accidental sampling
- ii) Limitations: Stratification is only limited to few variables and thus may not be representative of population
define Deviant case sampling:
- a) A type of nonprobability sampling in which cases selected for observation are those that are not thought to fit the regular pattern.
- i) For example, the deviant cases might exhibit a much greater or lesser extent of something.
what are the types of probablility sample?
- 1. stratified random sample
- 2. simple random sample
- 3. cluster smaple
define Stratified sampling:
- a) A probability sampling procedure
- uses stratification (breaking into groups then randomly selecting) to ensure that appropriate numbers of elements are drawn from homogeneous subsets of that population.
what are the advantages to stratified sampling?
- i) Advantages: Ensures that diverse elements of the population are included
- ii) Limitations: Must know where each element will fall into the strata
define Snowball sampling:
a) A nonprobability sample that is obtained by asking each person interviewed to suggest additional people for interviewing.
what are the advantages and limitations of snowball sampling?
- i) Advantages: Useful when potential subjects are hard to locate
- ii) Limitations: Favors the opinions of its starting point. Very easy to miss other networks
define Cluster sampling:
a) A multistage sampling procedure in which natural groups (clusters) are sampled initially, with the members of each selected group being sub sampled afterward.
what are the advantages and limitations of cluster sampling?
- i) Advantages: Good for larger studies, as it makes it more manageable
- ii) Limitations: Can be problematic if random selection is not used
define Simple random sampling:
a) probability sample in which the units that compose a population are assigned numbers. A set of random numbers is then generated, and the units having those numbers are included in the sample.
what are the advantages and limitations to simple random sampling?
- i) Advantages: very systematic, ensures that every element has the same chance of being chosen
- ii) Limitations: Can be limited by the sampling frame and minority elements may be under represented
define Systematic sampling:
a) probability sample in which every kth unit in a list is selected for inclusion in the sample.
define Disproportionate stratified sampling:
a) A sampling method aimed at ensuring that enough cases of certain minority groups are selected to allow for subgroup comparisons within each of those minority groups.
define Contingency questions:
- a) A survey question that is to be asked of only some of the respondents, depending on their response to some other questions.
- i) For example, all respondents might be asked whether they belong to the KKK, and only those who said yes would be asked how often they go to meetings. The latter would be a contingency question.
define Judgmental sample:
- a) nonprobability sample in which we select the units to be observed on the basis of our own judgment about which ones will be the most useful or representative.
- b) Another name for this is purposive sample.
what are the advantages and limitation to judgmental sampling?
- i) Advantages: Useful in exploratory studies, developing theory
- ii) Limitations: Bias exists, No way to know extent of representativeness
define Accidental sampling:
- a) A sampling method that selects elements simply because of their ready availability and convenience.
- b) Frequently used in social work because it is usually less expensive than other methods and because other methods may not be feasible for a particular type of study or population.
what are the advantages and limitations to accidental sampling?
- i) Advantages: Easy and convenient. Would suffice with testing new intervention
- ii) Limitations: No way to know if the sample is typical to the population at interest
definition of Research designs:
* A term often used in connection with whether logical arrangements permit causal inferences; also refers to all the decisions made in planning and conducting research.
define Trend study:
Longitudinal- purpose is to study one characteristic over time
define Descriptive study:
- a. Usually termed �survey�, Examines the distribution of one variable
- b. A system for collecting info to describe, compare, or explain knowledge, attitudes, or behavior
- c. Used when population is too big or disperse to view collectively
- d. Common to explore questions
- e. Sometimes experimental or quasi-experimental
define Longitudinal studies
- monitor a given characteristic of some population over time.
- a. An example would be annual canvasses of schools of social work to identify trends over time in the number of students who specialize in direct practice, generalist practice, and administration and planning.
define Cohort study:
- longdituinal study- Examine more specific subpopulations (cohorts) as they change over time.
- information from different member of the group may be used at each point of collection
purpose of Exploratory study:
a. Gain familiarity with a problem Often qualitative
purpose of Explanatory study:
a. Purpose to explain situation- qualitative
what is a Cross-sectional study:
a. Research studies that examine some phenomenon by taking a cross section of it- at one time and analyzing that cross carefully.
what is a Quasi-experiment:
- a. research Design that attempts to control for threats to internal validity and allow for causal inferences
- different from true experiments primarily by the lack of random assignment of subjects.
definition of an experiment? what three elements do all experiments have (3)
- a. A research method that attempts to provide maximum control for threats to internal validity by:
- 1. Randomly assigning individuals to experimental and control groups,
- 2. Introducing the IV (which typically is a program or intervention method) to the experimental group while withholding it from the control group
- 3. Comparing the amount of experimental and control group change on the DV
what is a Case study:
a. An idiographic examination of a single individual, family, group, organization, community, or society using a full variety of evidence regarding that case.
a. quasi-experimental designs- multiple observations of a dependent variable are conducted before and after an intervention is introduced.
- what are the Rules for writing survey:(8)
- o Clear instructions, no double barreled questions, short, overall very neutral, purposeful order, pre-test survey, exhaustive- all options available, mutually exclusive- can�t belong to two categories
what are the Strengths of surveys: (5)
o Inexpensive, can reach large populations, able to generalize data, able to analyze multiple variables at the same time, high reliability
what are the Weakness of surveys:(4)
o Limited ability to show causality, rely on self-report- not able to measure social behavior, not able to include life context, questionable validity
define Operational definitions:
- * The concrete and specific definition of something in terms of the operations by which observations are to be categorized.
- o Example: �improvement� in school as the concept. Improvement means getting better grades, less times in detention, joining after school club/sports teams
- The overall research process & designing a study
Three Basic Elements of a Good Experiment
- * Random assignment of subjects to experimental and control groups
- * Manipulation of independent variable
- * Control over extraneous variables
what are the steps to the Research Process: (8)
- Choose a problem- look a relevant theories, other research already done,
- Formulate hypothesis- identify IV, DV, extraneous variables
- Select research design- quasi experimental vs experimental
- Select sample- how are you going to get sample? Control vs experimental groups
- Develop instruments of measurement- used established or create own
- Collect data
- Analyze data
- Write the report
- In quantitative studies, the researcher predicts in advance the relationship they expect to find between variables. That prediction is called a hypothesis.
- Most hypotheses predict which variable influences the other, in other words, that which is the cause and that which is the effect.
what is Research Design
- a) Refers to the decisions made in planning and conducting research
- b) Often used in connection with whether logical arrangements permit causal inferences
what is a Sample?
a) People or things actually studied
what is good Measurement?
- a) A single problem can/should have multiple indicators
- 1. Increases reliability/validity
- 2. Allows for triangulation
in the research process what decision need to be made about Data Collection?
- How you will collect the data (experiment vs. survey vs. field research vs. historical)
- when, where and by whom your data will be collected with each instrument.
what is data Analysis
- a) Process of synthesizing raw observances to demonstrate patterns (e.g. statistical tests)
- b) Statistical analysis specifies the statistics to be computed and statistical tests to be used in analyzing the data collected. It determines whether or not the data support the hypothesis.
what are the rules for reporting results?
a) Start with a review of your original question (What was your interest in this area of study?, What, if any, research or theory informed your investigation?)b) Provide a detailed description of your methodology, Design, sample, Interview guide (described in text but attached as appendix), Method of analysis, Describe findings
what are the Purposes for data analysis?
- 1. Data reduction (description)
- 2. Pattern Identification (description & inference)
- 3. Generalizability (inference)
what is important in Qualitative results reporting?
- Organize by themes
- Use verbatim quotes to support interpretations
- discuss the meaning and implications of what you found
o Pretest-Posttest Control Group Design OR Classical Experimental Design:
o Posttest-Only Control Group Design:
o Solomon Four-Group Design:
o Alternative Treatment Design with Pretest:
o Dismantling Studies:
- R O Xab O
- R O Xa O
- R O Xb O
o Nonequivalent Comparison Group Design:
- two existing groups that appear to be similar and measures change before and after an intervention is introduced into one of the groups.
- O X O
- O O
o Time-Series Designs:
- multiple observations of a dependent variable are conducted before and after an intervention in introduced.
- The more observations, the better- more data points help rule out history, maturation, or statistical regression.
- O O O O X O O O
what is a probe?
- qualitative research technique
- * A technique employed in interviewing to solicit a more complete answer to a question, this nondirective phrase or question is used to encourage a respondent to elaborate on an answer
- * It helps encourage the interviewee to give a full a response as possible.
- examples: please tell me more about that. Can you clarify?
what are the Level of measurement:(4)
nominal, ordinal, interval, ratio,
define Nominal level of measure:
measures refer to those variables whose attributes are simple different form one another. An example would be gender
define Interval level of measure:
refer to those variables whose attributes are not only rank ordered by also separated by a uniform distance between them. An example would be IQ.
define Ordinal level or measure
refer to those variables whose attributes may be rank-ordered along some progression for more too less. An example would be the variable prejudice as composed of the attributes very prejudiced somewhere prejudiced and not at all prejudiced.
define Ratio level of measure:
rank order, uniform distance, also based on a true zero are. example age
- * A time-series design used to evaluate the impact of an intervention or a policy change on individual cases or systems.
- * Comparison of baseline and intervention phase
- * AB design A=baseline B= intervention
- o Positives: clear understanding of clients problems, easily apply to practice, client intervention specific
- o Limitations: may not be able to accurately get baseline because of clients needs, not, no time to use because of heavy caseloads
what is Internal validity
confidence that study accurately depicts whether one variable causes another
what are the Threats to internal validity (7) THIS RAM
- o Maturation- passage of time
- o History- other major life events happen that skew causality
- o Testing- clients get used to testing process
- o Instrumentation change- make sure to use same measures at pre and post test
- o Regression to the mean- (statistical regression)- things naturally improve on their own- people in crisis don�t stay in crisis
- o Selection bias- make sure control and experimental groups are comparable
- o Ambiguity about the direction of the causal influence- making sure the IV happened in time before the DV
what is needed to Establish a causal relationships (7)
- * Association- showing the IV and DV are associated (go together) either positively or negatively
- * Time Priority- IV happened BEFORE the DV
- * This happens through logic,manipulation of IV (experiment)
- * Ruling out alternative explanations- dcontrol other variables
- * Sampling- choose not to use participants that may give alt explanations
- * Random Assignment
- * Statistical Analysis- after study is complete
- * Theoretical explanations- if association between variables can be explained by a theory its more likely that there is a causal relationship
what are Attributes of a good research questions
- Mutually exclusive- only fit into one category ex. Age: 0-5, 6-10,11-15
- Exhaustive- all categories are represented ex. Gender: male, female, transgender
Single System Design compare what?
comparison of baseline to intervention phase.
what is Frequency distribution:
- * A description of the number of times the attributes of a variable are observed in a sample.
- Example:The report that 53 % of a sample was men and 47% were women would be a simple example of a frequency distribution.
- o Another example would be the report that 15 of the cities studied had population under 10,000, 23 had populations between 10,000 and 25,000.
what are the 6 Types of statistics that can be calculated with continuous data?
Mean, median, mode, range, variance, standard deviation
what is the definition of Mean:
mathematical average: to compute the mean add the scores of all the caes and divide by the numbers of cases
what is the definition of Median:
The middle- the point on the scale below which lies 50% of the cases and above which lie 50%
what is the definition of Range:
difference between the largest and smallest responses
what is the definition of Mode:
most often- category of the variable OR the interval on the scale that contains the most cases
What is the definition of Variance:
the value repsorents how much the scores vary from the mean.
sum of the squared deviations about the mean, divided by the number of responses.
what is the definition of standard Deviation:
the positive square root of the variance. It is the 'average' difference scores are from the mean.
what is the definition of Reliability:
- that quality of a measurement method that suggests that the same data would have been collected each time in repeated observations of the same phenomenon.
- results in studies r= 0-1 (closer to 1 is best) o For example: In the context of a survey, we would expect that the question �did you attend church last week?� would have higher reliability that the question �about how many times have you attended church in your life?
what are the ways to test reliability?
- Test-retests- If answers are consistent when given the same test at different points
- Split-half (coefficient alpha)- most common. Extent to which different samples of items from an instrument are consistent with the entire set. for example, Correlation of even number responses to odd number of responses
- Parallel Forms Reliability- Two groups, two different versions of same measurement instrument. Same instrument- questions asked in different order.
- Inter-rater Reliability- Making sure the observers, or clinicians delivering treatment are measuring same concept based on same measurement
what is Validity:
- a descriptive term used of a measure that accurately reflects the concept that it�s intended to measure.
- o For example, your IQ would seem a more valid measure of your intelligence than would the number of hours you spending the library. Realize that the ultimate validity measure can never be proven, but we may still agree to its relative validity, content validity, construct validity, internal validation, and external validation.
Validity in measurement tools and scales-
purpose- does the measure reflect the concept intended
What are the types of validity
Face value- Does it appear to measure the intended concept
Content validity- Covers the theoretical domain of concept- group of experts review
Statistical power increases when:
- *large sample sizes are selected,
- * higher significance levels are used, and
- * a stronger relationship in the population is assumed.
what are the characteristics of Good abstracts in written papers
- * Immediately after the title page.
- * Briefly summarizes the study
- * Between 75-150 words
- * Being with a sentence identifying the purpose of the research
- * Next, a sentence or two that summarizes the main features of the research design and methodology.
- * The main findings are then highlighted in one or two sentences followed by a brif mention of any major implications.
what are the types of qualitative questions? (3)
- * Grand tour- General overview of topic
- * Example/story- Respondent provides a personal example or story of specific event
- * Structure or contrast- Respondent is asked to reflect on contrasting situations/responses
What are mail surveys?
* A mailed questionnaire that requires no return envelope
what are Acceptable response rates with mail surveys:
- o 50% adequate
- o 60% good
- o 70% very good
what is the definition of Retrospective baselines
o Looking back and asking client to tell you about their behavior prior to treatment/intervention. When you aren�t able to observe the baseline because of crisis or timing
Correlation v. Causation:
- * In scientific perspective, we can NEVER EVER NEVER establish true causality
- * Association- Showing that the independent and dependent variables �go together� or vary systematically in relation to each other.
- o For example:If one is true, the other is true. - As one goes up, the other goes up (or down)
- * But NOT: they have no relationship
- * Time priority- Showing that independent variable (A) preceded dependent variable (B)
what is Triangulation:
The use of more than one imperfect data-collection alternative in which each option is vulnerable to different potential sources of error
what are the Strengths qualitative research
- * Strengths:
- o Depth and richness of data
- o Research happens in natural setting
- o Ability to understand ongoing social processes (usually longer, able to see change over time)
what are the Weaknesses of qualitative research:
- o Instruments
- o Ethical Concerns
- o Sampling- non-probability
- o Little validity or reliability
what is causal inference:
o Implies that the IV has a causal impact on the DV
What are the 6 characteristics for ensuring rigor?
- 1. Prolonged Engagement - mult interviews or
- lengthy stay in the field
- 2. Triangulation – Having multiple sources of data
- 3. Peer Debriefing - Consult other researchers to
- monitor bias
- 4. Member Checking –Verification of interpretations
- with respondents
- 5. Negative Case Analysis –Search for cases that refute
- 6. Audit Trail –Document everything: steps taken,
- decision points, interpretations, etc.
what part does the IV play in research design?
Independent variable is attribute variable
What would you like to do?
Home > Flashcards > Print Preview