adeola final essay questions
5. Why aren't experiments very generalizable? What can be done to improve the external invalidity of experiments?
• The requirements of experimental design usually preclude large-scale studies and so limit generalizability to a degree that is unacceptable to many social scientists. The generalizability of experimental results declines if the study conditions are artificial and the experimental subjects are unique. • The external validity of causal conclusions is determined by the extent to which they apply to different types of individuals and settings. When causal conclusions do not apply to all the subgroups in a study, they are not generalizable to corresponding subgroups in the population— and sos they are not externally valid with respect to those groups. Causal conclusions can also be considered externally invalid when they occur only under the experimental conditions.
1. What is focus group? What type of information is generated using focus group?
• A focus group is a qualitative method that involves unstructured group interviews in which the focus group leader actively encourages discussion among participants on the topics of interest. Focus groups are groups of unrelated individuals that are formed by a researcher and then led into group discussion of a topic for 1 to 2 hours. Focus groups are used to collect qualitative data, using open-ended questions posed by the researcher (or group leader.) A focused discussion mimics the natural process of forming and expressing opinions. No formal procedure exists for determining the generalizability of focus group answers, but careful research should conduct at least several focus groups on the same topic and check for consistency in the findings. Focus groups discover unanticipated findings and explore hidden meanings. Reveals the language participants used to discuss topics and think about their experiences.
9. What is the difference between anonymity and confidentiality? When is each appropriate?
• Anonymity: provided by research in which no identifying information is recorded that could be used to link respondents to their responses. • Appropriate: Phone surveys that are meant only to sample opinion at one point in time, as in political pools, can safely be completely anonymous. Group surveys can also do so when no further follow up in needed. They can also be done in mail surveys by omitting identification codes from the questionnaire and include self addressed, stamped postcard so respondent can return without linkage. • Confidentiality: Provided by research in which identifying information that could be used to link respondents to their responses is averrable only to designated research personnel for specific research needs. Primary focus of ethical concern in research surveys. Researcher must preserve subject confidentiality. • Appropriate: For all survey purpose participants should be linked to an encoding number. Subject confidentiality should always be preserved.
10. Describe each of the five criteria for identifying a causal effect and provide an example of each.
• Causal Effect: when a series of concrete events, thoughts, or actions results in a particular event or individual outcome. • Empirical Association: A criterion for establishing a nomothetic causal relationship between tow variables: variation in one variable is related to variation in another variable. • Example: We can determine association exists between the independent and dependent variables in a true experiment because there are two or more groups that differ in their value on the independent variable. Association between aggressive intentions and intoxication (for angry students) experiment because the level of aggressive intentions varied according to whether students were intoxicated. • Appropriate Time Order: Must also ensure that the variation in the dependent variable occurred after the variation in the independent variable. This is the time order. Our research design determines our ability to determine time order. • Example: First had some students drink alcohol and some experience the anger-producing manipulation and then measured their level of aggressive intention. If we find an association between intoxication or anger and aggressiveness outside of an experimental situation, the criterion of time order may not be met. • Nonspuriousness: A criterion for establishing a causal relation between two variables; when a relationship between two variables is not caused by variation in a third variable. —some respects most important • Example: Relationship between two variables is not spurious when it is not caused by variation in a third variable. • spurious relationship: relationship between two variables that is caused by variation in a third variable • Mechanism — Why a causal connection exists— Discernible process that creates a causal connection between two variables. • Example: In a study that reanalyzed data, pathbreaking study of juvenile delinquency, found that children who grew up with structural disadvantages such as family poverty and geographic mobility were more likely to become juvenile deliquesces. These structural disadvantage led to lower levels of informal social control in the family (less parent-child attachment, less maternal supervision, and more erratic or harsh discipline). Informal social control served as the mechanism for structural disadvantage and juvenile delinquency. • Context— When or under what conditions the causal effect occurs— A set of interrelated circumstances that alters a relationship between other variables or social processes. • Example: In countries having a relatively large underclass and poverty concentrated among minorities, juvenile cases were more likely to be treated harshly. These relationships occurred for both African American and white juveniles, but were particularly strong for African Americans. The results of this research suggest the importance of considering social context when examining criminal justice processes.
2. Outline how a research might conduct complete observation, covert participation, and participate observation in studying how unions recruit in new settings. What are the advantages and disadvantages to each approach? What are the ethical considerations that need to be addressed for each?
• Complete Observation requires a researcher to not participate in group activities and is publicly defined as a researcher. • In the union recruits setting a complete observer would not participate but people would know that they are conducting research. • Advantages and Disadvantages: try to see things as they happen without fully participating. Try to identify who, what, when, where, why and how of activities. You are indeed acting differently from others in the setting of which you are studying. Always evaluate how your actions in the setting and your purposes for being there may affect the actions of others and your own interpretations. • No ethical issues recorded. • Covert Participation requires the researcher to act like other group members and not disclose their research role. • In the union recruits setting a covert participator would act as a group member but not allow people to know their research role. EX. Laud Humphreys • Advantages and Disadvantages: Because their research role is unknown they cannot take notes openly or use any obvious recording devices. They cannot ask questions that would arouse suspicion, this is difficult to play successfully. Need to keep up the act at all times while in the setting under study. • Argued by Erikson that it is by nature unethical and should not be allowed except in public settings. Covert participation cannot anticipate the unintended consequences of their actions for research subjects. Although, some data can only be contrived through these secret, covert, concealed, and disguised— is necessary and appropriate in some cases. Some degree of deception may be justified in exchange for the knowledge gained. • Participate Observation requires researcher to be publicly acknowledged, while also participating in group activities. • In the union recruits setting a participate observer would be publicly acknowledged as a researcher and would still participate in group activities. Advantages and Disadvantages: Because they know the researchers role they can choose to keep things to themselves. Although the researcher can also decline to participate in unethical or dangerous activities without fear of exposing his/her identity. However, it is difficult to maintain a fully open research role in setting in which new people come and go. • They can be ethical about identity and still observe the natural social world.
6. Outline the two causal fallacies commonly associated with units of analysis. Give an example that demonstrates each, describing the problem with each fallacy in terms of examples.
• Ecological Fallacy: an error in reasoning in which incorrect conclusions about individuals-level processes are drawn from group level data • Conclusion may or may not be correct, but we must recognize the fat that group-level data do not necessarily reflect solely individual-level processes. • Example: A research may examine factory records and find that the higher the percentage of unskilled workers in factories, the higher the rate of employee sabotage in those factories. But the researcher would commit an ecological fallacy if he/she then concluded that individuals unskilled factory workers are more likely to engage in sabotage. • Reductionist Fallacy: an error in resigning that occurs when incorrect conclusions about group-level processes are based on individual-level data; also known as an individualist fallacy. • Data about individuals are used to make inferences about group-level processes, a problem occurs that can be thought of as the mirror image of ecological fallacy. • Example: Individual violence would focus on biological factors, such as genes or hormones, math than on the community's level of social control. Reductionist explanation of behavior problems in grade school classrooms would focus on the children personalities, rather than on classroom structure, teacher behavior, or
11. What is e-survey? List and discuss the major advantages and disadvantages of electronic (or web) surveys?
• Electronic Survey: A survey that is sent and answered by computer, either through e-mail or on the web. Most popular form is the web survey • Advantages: Low in cost, mostly structured — Used to reach large amounts of people, international connection because of internet capabilities. • Disadvantages: About one quarter of US households are not connected to internet, so it is not possible to survey directly a representative sample of the US population on the web— Rates of internet usages decreases across the world. Households without internet tend to be older, poorer, and less educated than do those that are connected, so web surveys of the general population can result in seriously biased estimates. Lower rates of survey completion— easy to just stop working on a web survey and get distracted.
13. What are the major advantages and disadvantages of using cross-sectional versus longitudinal research design? What are the advantages and disadvantages of using panel, trend, and cohort longitudinal designs?
• In a cross-sectional research design, all data are collected at one point in time. Identifying the time order of effects—what happened first, and so on—it critical for developing a causal analysis, but can be an insurmountable problem with a cross-sectional design. Ability to pull data together and compare across the spectrum • advantage: relativity inexpensive and cost effective, easy to administer • cause proceeds the effect, critical factor for developing the cause of analysis • In longitudinal research designs, data are collected at two or more points in time, and so identification of the time order of effects can be quite straightforward. — observations collected over time • disadvantages: expensive and errors at multiple points in time, depending on type could encounter subject mortality (people die and move, subject error) maturation effect • using a cohort analysis you would not have to worry because anyone who fits the description can be used- would be easy to replace a subject that dropped out. Three Major Types of Longitudinal Designs • Repeated cross-sectional design (trend study): type of longitudinal study in which data are collected at two or more points in time from different samples of the same population — cover a wide variety of topics and put into a visualizable graph • Ideally you want to collect the same samples over the same population over the same period of time — ability to draw causality over time and see causes of changes in behavior over time • GSS data, survey of random sample of the US population—subjects are not always the same, making it a cross-sectional data design but because the population is the same it is longitudinal (NORC made this available) • Fixed-sample panel design (panel study): a type of longitudinal study in which data are collected from the same individuals—the panel—at two or more points in time. In another type of panel design, panel members who leave are replaced with new members. • problematic that you may not be able to get the same sampling unit — also the cost of this type of study is higher • comparisons between time 1 and time 2 with making conclusions between the two • subject to "subject fatigue" this can be counter acted with motivation/incentive • Event-based design (cohort study): a type of longitudinal study in which data are collected at two or more points in time from individuals in cohort. • these are for people born within the same cohort — do not need to worry about subject mortality because it doesn't need to be the same individuals just those who fit the profile.
8. Describe four different ways that surveys can be administered? What are the advantages and disadvantages of each?
• Mail Survey: set through the mail, draw a random address sample— stamp and self-address return envelope must be included w/ instruction • central concern is maximizing return rate — main disadvantage is low response rate and cross-representativeness • increase response rate by doing multiple mailings — two weeks apart, friendly reminder • suggested that you have a preliminary introductory letters that introduces you and your questionary— suggested that you include some token / incentive (gift card) — personalize the letter and this establishes credibility of you as a researcher/ university and the research that you are conducting — consent must also be met for code of conduct • 6/8 weeks mail a new letter and new questionary, by this repeated sending this is going to be expensive and time consuming. • Group Administered Survey: captive audience — auditorium that allows you to explain purpose of survey, do not worry about sending out reminders and typically called self administered questionaries • high response rate— typically used to survey students • Telephone Survey: basically have the questionary in-front of staff conducting interviews— hopefully you have random digit dial— ask if the fit the profile of what you are looking for and read, and record response • high response rate— only problem is that you can run into numbers that are dead / not working, result of technological advances as well as: screening, answering machine • Computer Assisted Telephone Interviewing: CATI— survey over phone should not take longer than 20 minutes, longer than this you are reaching the possibility of interview being lost • higher than mail survey but decreasing become of technological changes • telemarketing causes people to hang up on you— though it is cost affective • Electronic/ Internet Survey/ Web-surveys: most effective of todays society — problem is people / demographic with little/no internet access • In-Person Interview: survey in which an interviewer questions respondents face-to-face and records their answers.
3. Overall, what are the advantages and disadvantages of qualitative research when compared to experimental or survey research?
• Qualitative research tends to develop ideas inductively, try to understand the social context and sequential nature of attitudes and actions, and explore the subjective meanings that participants attach to events. These researchers rely primarily on participant observation, intensive interviews, and in recent years, focus groups. However, the research gives many details it is usually hard to generalize to other people who may not directly identify with research subjects, also qualitative methods are not quantitative in research— no formula or mathematically calculations to be collected. • When conducting experiments and survey research you do not know much about the individual except for the questions in which you asked them. With qualitative research you get to know each individual on a personal level, which adds greatly to all research no matter the categories. Although with experimental or survey methods knowing to much about a participant be fatal to the research as well.
How does quantitative research differ from qualitative research? In what circumstances is qualitative research the most appropriate?
• Quantitative research involves surveys and experiments that record variation in social life in terms of categories that vary in amount. Research conducted under quantitative methods are either numbers or attributes that can be ordered by magnitude. Qualitative research in clues participant observation, intensive interviewing, and focus groups that are designed to capture social life. Qualitative research is not mathematical and release on written or spoken words or observation that do not often have a direct numerical interpretation and typically involve exploratory research questions. • Qualitative research is most appropriate when a researcher chooses to study a subject in their natural environment, study social processes that defy quantification, but are most useful for styling disaster events.
7. Outline and describe the three types of longitudinal research designs. What are the strengths and potential weaknesses of each?
• Repeated cross-sectional design (trend study): type of longitudinal study in which data are collected at two or more points in time from different samples of the same population — cover a wide variety of topics and put into a visualizable graph • Ideally you want to collect the same samples over the same population over the same period of time — ability to draw causality over time and see causes of changes in behavior over time • GSS data, survey of random sample of the US population—subjects are not always the same, making it a cross-sectional data design but because the population is the same it is longitudinal (NORC made this available) • weakness: using different people between test one and test two • Fixed-sample panel design (panel study): a type of longitudinal study in which data are collected from the same individuals—the panel—at two or more points in time. In another type of panel design, panel members who leave are replaced with new members. • problematic that you may not be able to get the same sampling unit — also the cost of this type of study is higher • comparisons between time 1 and time 2 with making conclusions between the two • weakness: subject to "subject fatigue" this can be counter acted with motivation/incentive • Event-based design (cohort study): a type of longitudinal study in which data are collected at two or more points in time from individuals in cohort. • These are for people born within the same cohort — do not need to worry about subject mortality because it doesn't need to be the same individuals just those who fit the profile. • weakness: can not repeat the specific even ever again, somewhat time sensitive.
12. Why are surveys so popular in the social sciences? Describe the key features that make surveys so attractive to scale scientists.
• Surveys research owes its popularity to three features: versatility, efficiency, and generalizability Versatility • First and foremost, survey methods are versatile (flexible) • Although a survey is not the ideal method for testing all hypothesis or learning about every social process, a well-designed survey can enhance our understanding of just about any social issue. • Computer technology has made surveys even more versatile. computers can be programmed s that different types of respondents are asked different questions. Short videos or pictures can be presented to respondents on a computer screen. Efficiency • Surveys also are popular because data can be collected from many people at relatively low cost and, depending on the survey design, relatively quickly. • Surveys are efficient because many variables can be measured without substantially increasing the time or cost. • Modern information technology has been a mixed blessing for survey efficiency. The internet makes it easier to survey some populations, but it leaves out important segments of the population. • these left out include: people of low income without internet / without smartphones • people who do have these cellphones or smartphones are no longer out of reach Generalizability • Survey methods lend themselves to probability sampling from large populations • Thus, Survey research is very appealing when sample generalizability is a central goal for research. Equal Probability of Selection Method (EPSM)- able to use in survey method In fact, survey research is often the only means available for developing a representative picture of the attitudes and characteristics of a large population. Surveys also are the method of choice when cross-population generalization is a key concern, because they allow a range of social contexts and subgroups to e sampled. The consistency of relationships can then be examined across the various subgroups. Unfortunately (for survey researchers), the new technologies that are lowering the overall rate of response to surveys are also making it more difficult to obtain generalizability samples. (caller ID/ answering-machine/ call forwarding)
