Research final exam
The experimental group is the group that receives: a. The dependent variable b. The most improvement c. No treatment of any kind d. The treatment
d. The treatment
The control group is the group that receives: a. the treatment b. the dependent variable c. the independent variable d. no treatment or alternative treatment
d. no treatment or alternative treatment
Identify two flaws with the following potential survey question: What is your income? a. $10,000 to $20,000 b. $20,000 to $30,000 c. $30,000 or more
if you made $20,000 you wouldnt know whether to select a or b, and if you make $30,000 you wouldnt know whether to select b or c. The amount isn't evenly distributed, as it's only asking about an income from $10,000 to $30,000
If you wanted to test if voting preference (democratic, republican, independent) differed based on MSW concentration (clinical, macro), what type of inferential statistic would you run?
chi-square
What do I mean by a representative sample?
A sample that represents the population. How similar the sample is to the population
Write a directional hypothesis with alcohol use as the dependent variable and parental monitoring as the independent variable. Why did you choose that answer?
As parental monitoring increases, alcohol use decreases Because increase and decrease make it directional
The literature review can provide all of the following except: a. Help you to identify an appropriate topic for study b. Help you to decide the outcome of your study c. Help you to understand the problems involved d. Help you to become more knowledgeable about the profession
B. Help you to decide the outcome of your study
If you wanted to test if the mean depression score of a sample of adolescents hospitalized following a suicide attempt is different before and after receiving a motivational interviewing intervention, what type of inferential statistic would you run? a. Independent group t-test b. Independent samples t-test c. Paired samples t-test What's a potential risk of this study?
C. Paired samples t-test (because it tests pre-intervention, post-intervention) (Is there a change over time with the same group following exposure to something) Potential risks of this study: MI could harm or could be unhelpful, asking them to disclose sensitive information, risk of breaking confidentiality
What is the primary function of the Institutional Review Board (IRB)?
Considers Belmont report, Review and approval of research Exempt, Expedited review or full committee review Exempt - there is no risk to the participants Expedited review Data that isn't anonymous, but theres minimal risk Full committee review Majors Standards of IRB Voluntary informed consent anonymity/confidentiality No unnecessary pain and suffering Need to conduct research Culturally competent research
What type of inferential statistic would you run if you were interested in the relationship between height (measured in inches) and weight (measured in pounds)?
Correlation When to use correlation? It describes the degree of relationship between two continuous variables. To compare 2 continuous variables Other types: T-tests and Chi-Square When to use T-Tests: Used to compete the means of 2 groups to see if they're different from one another (at least one continuous variable) When to use Chi-Square: When you don't have 2 continuous variable, Seeing if there's a relationship between the two categorical variables (nominal)
2. Research hypotheses can be directional, non-directional, or have no relationship. What type of hypothesis is the following hypothesis: College graduates and non-college graduates have different levels of Employment
Non-directional hypothesis
Research can be exploratory, descriptive, or explanatory. In one research study, a group of researchers are conducting a qualitative study to look at the perceptions of fear-based programs among MSW students. The researchers want to know the degree to which fear based programs are recognized as a problem, and if people are really aware of their short falls. Not much prior research, if any at all, has looked at MSW students perceptions of Fear based programs. What type of research is this?
Exploratory, because it is qualitative research and they don't know much about the phenomenon
What is external validity?
Generalizability of the sample of the population. Can you take your results and apply it to the real world, beyond the cases in your study?
Who decides if research study is ethical and can be conducted
IRB (Institutional review board)
What is a value label?
Label for the value when analyzing data Ex. 1=yes 2=no Words or numbers that denote the different measurements of a variable
What is a sampling error?
Natural differences from the sample to the population
What are the Nazi and Japanese medical experiments and identify 2 reasons they were unethical
Nazi's did experiments on people during WWII. Did experiments on undesirable groups (chambers for oxygen or lack oxygen) Exposure to life threatening diseases and decompression chamber participation wasn't voluntary, harm outweighs benefits (ends didn't justify means)
How would you move the construct depression into a variable?
Operationalize depression
A researcher is interested in studying adolescent substance use treatment. Match the example on the right with the concept on the left: Population Sampling Frame Sample Case A.Adolescents receiving treatment at the Adolescent Substance Abuse Program (ASAP) B. Suzy C. Adolescents receiving substance abuse treatment D. Who we choose from ASAP
Population - C Sampling Frame - A (the specific list of the names of people you can sample) Sample - D Case - B
Task such as selecting a field site; participant observation; and focus groups would likely represent what type of research? a. Qualitative b. Quantitative c. Deductive d. All of the above
Qualitative
3. What are the three main principles from the Belmont Report?
Respect for persons-individuals are autonomous agents, and people with diminished autonomy are entitled to special protections (pregnant women, children and prisoners Beneficence-do no harm, maximize the possible benefits, minimize the possible harms Justice- Fair procedures and outcomes are used to select research participants, and there is a fair distribution of benefits and burdens to populations who participate in research
Which of the following are types of probability samples (Check all that apply)? Simple Random Sample Purposive Sample Convenience Sample Quota Sampling Systematic Random Sample Snowball Sample
Simple Random Sample Systematic Random Sample
What does it mean to operationalize a variable?
Specifying actual measuring devices or methods that will be used to measure key variables. The development of specific definitions of key variables. Example: Suicide Ideation Severity will be measured using the Suicide Ideation Questionnaire
Choosing every nth on a list of potential participants is an example of what type of sampling strategy? a. Systematic Sampling b. Snowball Sampling c. Random Sampling d. Stratified Sampling
Systematic Sampling ALSO probability sampling(general category), which is the most robust type of sampling. Uses random selection. There is an equal chance of selection across everyone on sampling frame
What is missing in the hypothesis to make it more clear and testable: a. Young children are more imaginative
The comparison group (more imaginative compared to what?)
What is the difference between an experimental design and a quasi-experimental design?
There is no control group in quasi-experimental design and there's no random assignment of participants in quasi-experimental design. Experimental design has a control group, quasi has a comparative group SAME EXACT THING as true experimental, except you DONT have random assignment
What is a potential threat to internal validity?
Threats to internal validity include: history, passage of time, regression to the mean, testing, instrumentation change, sampling bias, ambiguity about the cause and effect There is a difference between validity of measurement and internal validity of design. Internal validity is when only exposure to the IV produces change in the DV and no other factors can account for these changes. CAUSALITY! 3 conditions 1. Covariation of cause and effect There has to be a relationship between independent and dependent variable 2. Temporal precedence Ind variable has to have occurred prior to dep variable 3. No plausible alternative explanation But in social science research theres a lot of confounding variables But in true experimental research you can have cause and effect
How might a social worker incorporate research into her/his practice with individuals in a clinical setting? Give an example.
User evidence-based practice when working with clients (EBP is a process in which the practitioner combines well-researched interventions with clinical experience, ethics, client preferences, and culture to guide and inform the delivery of treatments and services) Learn and document how their interventions affect clients Use the findings of a research report to improve their practice Justify that a client's treatment should be extended Example: When doing CBT with a client, document how this therapy is affecting client over time. Also researching how CBT has affected this population in the past and using findings to improve practice with a client. Also using research to justify if CBT should be extended or not
6. I am interested in studying the relationship between Cognitive Behavioral Therapy (CBT) and depression. My hypothesis is that CBT will reduce depression in adolescents. a. What is the independent variable? b. What is the dependent variable? c.What is the population?
a. CBT b. depression in adolescents c. adolescents
I am interested in studying the impact of state marijuana policies on adolescent marijuana use. a. What is the Independent variable? b. What is the dependent variable? c. What is a possible control variable?
a. State marijuana policies b. Adolescent marijuana use c. Confounding variables are variables that confuse relationship between IV and DV. Any other variable that may affect the outcome Ex age, race, sex
What categories are considered special populations? a.children b. pregnant women c. college students d. prisoners
a., b., and d
What would you be doing if you administered the same measuring instrument to the same group of people on two separate occasions to observe the similarities between the results? Why this one and not the other ones? a. Parallel forms reliability b. Split half reliability c. Test-retest reliability d. Content validity
a.Parallel forms reliability - administering different versions of an assessment tool (both versions must contain items that probe the same construct, skill, knowledge base, etc.) to the same group of individuals. The scores from the two versions can then be correlated in order to evaluate the consistency of results across alternate versions. b. split-half reliability- A measure of consistency where a test is split in two and the scores for each half of the test is compared with one another. If the test is consistent it leads the experimenter to believe that it is most likely measuring the same thing. This is not to be confused with validity where the experimenter is interested if the test measures what it is suppose to measure. c. Test-retest reliability-Used to assess the consistency of a measure from one time to another. We estimate test-retest reliability when we administer the same test to the same sample on two different occasions (CORRECT ANSWER) d. Content validity - Content validity is an important research methodology term that refers to how well a test measures the behavior for which it is intended Coefficient alpha reliability- estimate the reliability, or internal consistency, of a composite score. Theoretically, Cronbach's alpha results should give you a number from 0 to 1, but you can get negative numbers as well. A negative number indicates that something is wrong with your data—perhaps you forgot to reverse score some items. The general rule of thumb is that a Cronbach's alpha of .70 and above is good, .80 and above is better, and .90 and above is best. Inter-observer agreement-the same behavior independently (to avoided bias) and compare their data. If the data is similar then it is reliable.
What is the difference between anonymity and confidentiality?
anonymity- no one, not even researcher, can identify a given response with a given participant confidentiality- researcher is able to identify a given persons response but will not reveal them publicly
The social worker who is doing a support group believes the interventions are effective, but wants objective research to support that assumption. An anxiety scale is used to measure anxiety in the group members. What type of variable is anxiety? a. Independent b. Dependent c. Independent and Dependent d. Confounding
b. dependent (the variable being measured)
Looking at the numbers below, identify the: 5, 7, 9, 2, 5, 7, 22, 5, 5, 5 mode median range
mode: 5 median: 5 range: 20
5. Variables can be measured at the nominal, ordinal, interval, or ratio level. What level of measurement is race?
nominal
Height and weight are typically positively or negatively correlated?
positively correlated
Explain the difference between random selection and random assignment
random selection has to do with sampling and selecting who will participate in the study. It's when you randomly select people to participate in study random assignment has to do with design. Once you have sample how will you assign them into different groups (If you want types of people to be equal across the board, computer programs can help the groups to be random but have equal types of people)
What type of research design would you use if you wanted to examine treatment effectiveness over time, for one client?
single-case research design: In-depth investigation of a problem in one or more real-life settings over an extended period of time
Using referrals from current participants to recruit other participants is what type of sampling strategy? Why? a. Systematic Sampling b. Snowball Sampling c. Random Sampling d. Stratified Sampling
snowball sampling because systematic sampling is choosing every nth on the list random sampling is when you have sampling frame and you assign number to every person on sampling frame to randomly select your participants (like flipping a coin or pulling out of a hat) stratified sampling is organizing your sampling frame into subsets, and then select from those subsets (ex. Organize list into subsets based on race, drinking status, mental health status, and select from those strata)
