Research & Stats

A researcher discovers that the students she is observing have been getting better grades in their classes. The teacher informs her that their grades began to improve the first week the researcher was present. This could be an example of: A. Selection bias B. Hawthorne effect C. Endogenous change D. History effects E. Placebo effect

Hawthorne effect

Comparison group

In an experiment, a group that has been exposed to a different treatment (or value of the independent variable) than the experimental group.

Experimental group

In an experiment, the group of subjects that receives the treatment or experimental manipulation.

Posttest

In experimental research, the measurement of an outcome (dependent) variable after an experimental intervention or after a presumed independent variable has changed for some other reason.

A study assessed the school success of kids in middle school whose parents were divorced, and compared them to that of their peers whose parents were not divorced. School success was assessed by GPA. The researcher conducted the study at the school where her spouse teaches. What was the research question in this study? Is there a relationship between parent's marital status and school success of their middle school children? Is there a relationship between being divorced and having children in middle school? Is there a relationship between school success of middle school children and being divorced? What is the relationship between being divorced and school success?

Is there a relationship between parent's marital status and school success of their middle school children?

The following is an example of a nominal level variable: Social Security Number Number of children Satisfaction from service received at a restaurant measured on a scale of 1-5 (1-very dissatisfied, 5-very satisfied) Temperature in degrees Celsius

Social Security Number

The following is an example of a interval level variable: Social Security Number Number of violent incidences on the playground at recess Satisfaction from service received at a restaurant measured on a scale of 1-10 (1-very dissatisfied, 10-very satisfied) Temperature in degrees Fahrenheit

Temperature in degrees Fahrenheit

Randomized comparative change design

The classic true experimental design in which subjects are assigned randomly to two groups; both these groups receive a pretest, then one group receives the experimental intervention, and then both groups receive a posttest. Also known as a pretest-posttest control group design.

The potential for context effects is greatest when two or more questions concern the same issue or closely related issues. True or False

True

Unless your focus is on major events that are unlikely to have been forgotten, limit survey questions about the past to no more than the past month. True or False

True

Intent-to-treat analysis

When analysis of the effect of a treatment on outcomes in an experimental design compares outcomes for all those who were assigned to the treatment group with outcomes for all those who were assigned to the control group, whether or not participants remained in the treatment group.

The following is an example of a double-barreled question: Do you agree or disagree that taxes should be raised and that more money should go to public schools? True or False?

true

In experimental and quasi-experimental designs, the independent variable is measured by using the: A. pretest B. experimental treatment C. post test D. comparison group E. control group

experimental treatment

For a study about the relationship between marital status and subjective well-being, 100 respondents ages 18 and over where asked to answer the following question "Please circle the option that best represents you marital status: a. single, b. married, c. separated, d. divorced, e. widowed, f. other." The level of measurement for this variable is: Ordinal Nominal Ratio Interval

nominal

An alien landed on earth, and the president of the earth offered him the best chocolates as a sign of hospitality and friendship. The alien tasted the chocolate, spit it out and concluded that food on earth is not edible. This is an example of the following type of error: -resistance to change -overgeneralization -illogical reasoning -selective observation

overgeneralization

Response rates are higher for telephone surveys than with any other survey design True or False?

False

Ex post facto control group design

A nonexperimental design in which comparison groups are selected after the treatment, program, or other variation in the independent variable has occurred, but when the participants were able to choose the group in which they participated. Often confused with a quasi-experimental design.

Differential attrition (mortality)

A problem that occurs in experiments when comparison groups become different because subjects are more likely to drop out of one of the groups for various reasons.

Matching

A procedure for equating the characteristics of individuals in different comparison groups in an experiment. Matching can be done on either an individual or an aggregate basis. For individual matching, individuals who are similar in key characteristics are paired before assignment, and then the two members of each pair are assigned to the two groups. For aggregate matching, also termed blocking, groups are chosen for comparison that are similar in the distribution of key characteristics.

Time series design

A quasi-experimental design consisting of many pretest and posttest observations of the same group over an extended period.

before and after design

A quasi-experimental design consisting of several before-after comparisons involving the same variables but no comparison group.

Nonequivalent control group design

A quasi-experimental design in which experimental and comparison groups are designated before the treatment occurs but are not created by random assignment.

Repeated measures panel design

A quasiexperimental design consisting of several pretest and posttest observations of the same group.

Regression-discontinuity design

A quasiexperimental design in which individuals are assigned to a treatment and a comparison group solely on the basis of a cutoff score on some assignment variable and then treatment effects are identified by a discontinuity in the regression line that displays the relation between the outcome and the assignment variable at the cutoff score.

Quasi-experimental design

A research design in which there is a comparison group that is comparable with the experimental group in critical ways, but subjects are not randomly assigned to the comparison and experimental groups.

Contamination

A source of causal invalidity that occurs when either the experimental or the comparison group is aware of the other group and is influenced in the posttest as a result.

External events

A source of causal invalidity that occurs when events external to the study influence posttest scores; also called a history effect.

History effect

A source of causal invalidity that occurs when events external to the study influence posttest scores; also called an effect of external events.

Regression effect

A source of causal invalidity that occurs when subjects who are chosen for a study because of their extreme scores on the dependent variable become less extreme on the posttest because of natural cyclical or episodic change in the variable.

Selection bias

A source of internal (causal) invalidity that occurs when characteristics of experimental and comparison group subjects differ in any way that influences the outcome.

Placebo effect

A source of treatment misidentification that can occur when subjects receive a fake "treatment" they think is beneficial and improve because of that expectation even though they did not receive the actual treatment or received a treatment that had no real effect.

Field experiment

A study using an experimental design that is conducted in a real-world setting.

Factorial survey

A survey in which randomly selected subsets of respondents are asked different questions, or are asked to respond to different vignettes, to determine the causal effect of the variables represented by these differences.

Randomized comparative posttest design

A true experimental design in which subjects are assigned randomly to two groups—one group then receives the experimental intervention and both groups receive a posttest; there is no pretest. Also known as posttest-only control group design.

Compensatory rivalry (John Henry effect)

A type of contamination in experimental and quasi-experimental designs that occurs when control group members are aware that they are being denied some advantage and increase their efforts by way of compensation.

Demoralization

A type of contamination in experimental and quasi-experimental designs that occurs when control group members feel they have been left out of some valuable treatment and perform worse as a result.

Hawthorne effect

A type of contamination in research designs that occurs when members of the treatment group change relative to the dependent variable because their participation in the study makes them feel special.

Solomon four-group design

A type of experimental design that combines a randomized pretest-posttest control group design with a randomized posttest-only design, resulting in two experimental groups and two comparison groups.

Multiple group before-and-after design

A type of quasi-experimental design in which several before-and-after comparisons are made involving the same independent and dependent variables but different groups.

The ethical question that arises most frequently for group surveys is: A. Respondents may feel coerced to complete surveys. B. Respondents may discuss their answers with one another. C. It is very difficult to establish confidentiality within a group. D. Informed consent cannot be given by group leaders. E. The researcher can see the people who complete the surveys.

A. Respondents may feel coerced to complete surveys.

Surveys are popular research designs because they are versatile. This means: A. They can enhance understanding of just about any social issue. B. Questionnaires can easily be revised. C. Questions can be used from pre-existing, validated surveys. D. Response categories can be manipulated. E. Interviewers can modify questions during the course of an interview.

A. They can enhance understanding of just about any social issue

If a respondent is forced to choose an answer from a list of responses, but the respondent doesn't really know anything about the question, the person who designed the survey has not taken which of the following into consideration: A. context B. floaters C. double-barreling D. bias E. fence-sitting

A. context

Selective distribution of benefits

An ethical issue about how much researchers can influence the benefits subjects receive as part of the treatment being studied in a field experiment.

Double-blind procedure

An experimental method in which neither the subjects nor the staff delivering experimental treatments know which subjects are getting the treatment and which are receiving a placebo.

The size of a social worker's workload is measured by the number of cases assigned to the social worker. This is an example of: A conceptual definition of workload A nominal way to measure workload A valid and reliable way to measure workload An operational definition of workload

An operational definition of workload

Interactive voice response surveys are most effective when: A. Respondents are offered a token financial incentive B. Respondents are highly motivated to participate C. Respondents have higher education and income D. Respondents have greater familiarity with computers E. Respondents have a rapport with the interviewer

B. Respondents are highly motivated to participate

"Do you disagree that schools should not allow morning prayer?" is an example of: A. a double-barreled question B. a double negative C. a skip pattern D. a filter question E. a contingent question

B. a double negative

Which of the following is NOT an error in survey research stated in the book? A. Sampling error B. Poor measurement C. Miscalculation D. Nonresponse E. Inadequate coverage of the population

C. Miscalculation

A phone survey conducted with random digit dialing has all but which of the following features? A. Designation of telephone exchanges to be called B. Machine-based calling of random phone numbers C. Postcard follow-ups to those who don't answer the phone D. Screening questions to identify appropriate respondents E. Personnel training

C. Postcard follow-ups to those who don't answer the phone

Informed consent is a hallmark of research with human subjects. Some populations are suggested to have diminished autonomy, and consent procedures must take this into account and ensure special protections when conducted research with them. Examples of populations with diminished autonomy may include: College students, children, persons over 65 years of age Children, people who are incarcerated or involuntarily detained, people who are unconscious Children, Women, people who are incarcerated or involuntarily detained Persons over 65 years of age, people who are incarcerated or involuntarily detained, pregnant women

Children, people who are incarcerated or involuntarily detained, people who are unconscious

Researchers designed a study to explore the relationship between creativity and social support. They defined social support as "the perception and actuality that one is cared for, has assistance available from other people, and that one is part of a supportive social network. These supportive resources can be emotional (e.g., nurturance), tangible (e.g., financial assistance), informational (e.g., advice), or companionship (e.g., sense of belonging) and intangible (e.g., personal advice). This is an example of a: Conceptual definition Valid definition Positive definition Operational definition

Conceptual definition

A study assessed the school success of kids in middle school whose parents were divorced, and compared them to that of their peers whose parents were not divorced. School success was assessed by GPA at the end of the school year, as was the marital status of the parents. The researcher conducted the study at the school where her spouse teaches. The research design used here is: True experimental design Quasi-experimental design Cross-sectional survey - non-experimental design Longitudinal - non-experimental design

Cross-sectional survey - non-experimental design

The type of survey design that is most expensive per completed survey is: A. Mailed survey B. Group survey C. Phone survey D. In-person interview E. Electronic survey

D. In-person interview

Behavior coding is possible for which of the following: A. Interactive voice response B. Mailed survey C. Web survey D. In-person survey E. None of the above

D. In-person survey

In order to keep response rates high, researchers decide to first collect data by mailing surveys to potential respondents, after which they will begin calling respondents on the telephone. This method is known as: A. Context B. Random digit dialing C. Double-barreling D. Mixed-mode E. Fence-sitting

D. Mixed-mode

In-person interviewing has all of the following advantages compared to other survey designs EXCEPT: A. High rates of response B. Questionnaire can be longer and more complex C. Physical and social context can be monitored D. The interviewer has little effect on how the respondent answers E. Interpretations of questions can be probed and clarified

D. The interviewer has little effect on how the respondent answers

Which of the following survey methods is extremely affordable and quick to implement but cannot ensure questionnaire completion. A. Mail survey B. Phone survey C. In-Person survey D. Web survey E. Both B and C

D. Web survey

A professional and persuasive cover letter should contain: A. Reference to a credible researcher or organization B. A personalized salutation C. A phone number that can be called to get more information D. B and C E. All of the above

E. All of the above

True experiment

Experiment in which subjects are assigned randomly to an experimental group that receives a treatment or other manipulation of the independent variable and a comparison group that does not receive the treatment or receives some other manipulation; outcomes are measured in a posttest.

A researcher gets a list of all students enrolled at a particular school. They randomly select 100 students from the school to participate in the study. They give all 100 students a questionnaire assessing their studying and sleeping patterns. True or False: This design uses both random selection and random assignment.

False

Floaters are people who are neutral but will choose an answer if not given a neutral response choice True or False?

False

In an experiment, a random distribution of benefits is ethical only if researchers are unsure of the effects of a treatment. True or False?

False

A group of researchers wanted to explore how self-esteem of children is affected by compliments they receive from their parents and/or guardians in households with 3 or more children. They randomly assigned 40 families into two groups of 20. They asked the parents/guardians of the first group to complement their children 5 times a day for one week, and the parent's/guardians of the second group to refrain from complimenting their kids for the entire week. The children's self-esteem was measured before and right after the intervention at the end of the week. What is a possible way to phrase the research question? Is there a relationship between number of children in a household and self-esteem? Is there a relationship between whether or not parents/guardians compliment children and the children's self-esteem? Is there a relationship between number of children in a household and whether or not parents/guardians compliment children? Should we compliment kids in order to increase their self-esteem?

Is there a relationship between whether or not parents/guardians compliment children and the children's self-esteem?

The following is an example of a ratio level variable: Temperature in degrees Fahrenheit Social Security Number Satisfaction from service received at a restaurant measured on a scale of 1-10 (1-very dissatisfied, 10-very satisfied) Number of violent incidences on the playground at recess

Number of violent incidences on the playground at recess

A researcher designed a new intervention to increase social support for elderly adults hospitalized for heart failure, in order to reduce their period of hospitalization. The researcher sampled 10 patients from each of the 10 hospitals within 30 miles of his workplace. He randomly assigned the 100 patients into 2 groups: 50 received his intervention, and 50 continued to receive regular care without his intervention. He then measured the number of days spent in the hospital. Select the correct sentence below: The number of days spent at the hospital is the dependent variable and is measured at a nominal level of measurement The number of days spent at the hospital is the independent variable and is measured at a ratio level of measurement The number of days spent at the hospital is the independent variable and is measured at a nominal level of measurement The number of days spent at the hospital is the dependent variable and is measured at a ratio level of measurement

The number of days spent at the hospital is the dependent variable and is measured at a ratio level of measurement

Researchers wanted to explore the relationship between social workers' experience in their jobs and their attitudes towards management. Experience was measured using years of tenure in current position and attitudes towards management were assessed by asking participants how interested they are in managerial positions in the future - 1 - not interested at all, 2 - not interested, 3 - a little interested, 4 - interested, 5 - very interested. 400 social workers were randomly selected from a list of all registered social workers in Florida and were sent a questionnaire with questions about their tenure and attitudes. What can be said about the study? The study incorporated both random sampling and random assignment The study incorporated random assignment but not random sampling The study incorporated a random sampling but there was no random assignment The study did not incorporate random assignment or random sampling

The study incorporated a random sampling but there was no random assignment

A Likert scale involves response choices that range from "strongly agree" to "strongly disagree". A. True B. False

True

A Solomon Four Group design is best employed if a researcher suspects that the pretest will change how subjects respond to the experimental treatment. True or False?

True

A researcher gets a list of all students enrolled at a particular school. They intentionally select 100 students with the lowest test scores from the school to participate in the study. The names of the 100 selected students are placed in a hat and 50 are chosen to receive the intervention (the treatment group), while the remaining 50 students serve as the control group. True or False: This design uses random assignment, but does not use random selection.

True

External events are a major threat to validity in evaluation studies that compare programs in different cities and states. True or False?

True

According to ASA codes of conduct, deception is acceptable: A. When subjects are not harmed B. With IRB approval C. If debriefing occurs D. All of the above E. None of the above

all of the above

Selection bias occurs in comparison groups because of which of the following: A. Differential attrition B. Some subjects may drop out C. The groups are initially different D. Subjects were not assigned randomly E. All of the above

all of the above

True experiments utilize comparison groups because they help reduce which of the following threats to internal validity? A. Testing B. Instrumentation C. Maturation D. Regression E. All of the above

all of the above

During an experiment, the comparison group becomes aware of the other group and as a result, is negatively influenced in the posttest. This is known as: A. Demoralization B. Placebo effect C. Hawthorne effect D. Selection bias E. Contamination

contamination

After an experiment involving deception, researchers should explain to subjects the true nature of the experiment. This procedure is known as: A. Factorial surveying B. Process analysis C. Debriefing D. Clarification E. Factor analysis

debriefing

Research on marital status, health, and mortality has supported the following hypothesis: relatively unhealthy men are more likely to be remarried than their healthier counterparts. Their health, in other words, is said to affect their decision to remarry. What is the dependent variable in this study? -health -mortality -decision to remarry -men

decision to remarry

Your control group figures out they have been receiving a placebo and begin to answer questions without any detail or enthusiasm, and begin to drop out of the study. This process creates a problem in the comparability of your control and experimental known as:

demoralization

Researchers sometimes find that subjects in the experimental group seem more motivated than the subjects in the comparison group, which leads to greater drop out from the comparison group. This is known as: A. Demoralization B. Placebo effect C. Differential attrition D. Selection bias E. Endogenous change

differential attrition

Abrefa-Gyan, T., Cornelius, l., & Okundaye, J. (2015). Gender and children as the moderators of the relationship between social support and quality of life: An empirical study of people living with HIV/AIDS in Ghana. Social Work in Public Health, 00, 1-9. Although gender differences persist in the receipt of social support and the report of quality of life among people living with HIV/AIDS in Sub-Saharan Africa, the knowledge base on this topic is scant. For those living with HIV/AIDS, women tend to participate more than men in support group activities, but their gender predisposes them to lower quality of life. Therefore, this study seeks to determine what demographic factors moderate the relationship between social support and quality of life among those living with HIV/AIDS in Ghana. A convenience sample of 300 HIV/AIDS support group members who have experience participating in research studies and was obtained for use via cross-sectional design survey in September and October 2013. The Medical Outcome Studies (MOS) HIV Health Survey, the MOS Social Support Survey, and demographic questionnaire instruments were used to assess quality of life, social support, and demographic information respectively. Gender (male) F(3, 296) = 66.04, t = 2.26, p =.024) and having children (have children) (F(5, 294) = 40.34, t = 2.50, p = .013) moderated the relationship between social support and quality of life. Implications of the findings for practice, policy, and research in Ghana and the rest of the developing world were discussed. (Journal Abstract). This abstract describes what type of research? explanatory exploratory evaluative descriptive

exploratory

A true experiment's experimental group and control group are one and the same. A. True B. False

false

Unlike true experiments, before-and-after designs: A. Do not use randomization for assignment into groups B. Use matching for assignment into groups C. Measure the dependent variable after treatment D. Have no comparison group E. Have three or more comparison groups

have no comparison group

Researcher L was studying preparedness for natural disasters in a field experiment when a particularly destructive hurricane hit a neighboring stat What problem is likely to occur when establishing internal validity in L's research? A. History effect B. Selection bias C. Endogenous effect D. Regression E. Maturation

history effect

In a study in measuring the importance of Facebook in one's daily life, several questions from previous research to measure this single concept ("Facebook is part of my everyday activity", "Facebook has become part of my daily routine", "I feel out of touch when I haven't logged onto Facebook for a day"). In terms of my measurement reliability, the researchers have to establish that these items are in fact measuring a single concept. What type of measurement reliability will they try to establish? Correct! Interitem reliability (internal consistency) Interobserver reliability They don't need to establish reliability, only validity Test-retest reliability

interitem reliability (internal consistency)

A recent study confirmed the hypothesis that frequently playing violent first-person shooter games as an adolescent increased the likelihood of having violent tendencies as an adult. What is the dependent variable in this study? Playing violent first-person shooter games Media Adolescent Correct! likelihood of violent tendencies as an adult

likilhood of violent tendencies as an adult

The size of a social worker's workload is measured by the number of cases assigned to the social worker. What level of measurement was used? Interval Ratio Ordinal Nominal

ratio