Research Methods
What are the 4 levels of measurement - what is an example of each?
- Nominal scale: the forming of classes which contain equivalent objects or events (Color, race, ethnicity, marital status) -- it's just taking groups and giving them a label. - Ordinal scale: in addition to property of equivalence, the objects on the scale can be arranged in a ranking of greater or less than -- (agree, somehwat agree disagree, strongly disagree) (bachelors, masters, doctorates - catagories can be ranked. Middle class, upper class, etc.) -- - Interval scale: in addition to equivalence and rank order, the distance between the ordered locations is equal (catagories can be ranked, but now the gap between them is equal)-- degrees farenheit or celcius - only acceptable answer. - Ratio Scale: in addition to equivalence, rank order, and distance, zero has meaning. There are equal distances in catagories, and catagories can be rank ordered. Does zero have meaning? yes. It's on your birth certificate. 'All properties of interval, PLUS'-- Ratio level: age, income, height weight - when 0 means 0.
What are the two main goals of science and what questions do they ask? -- Science is DE best!
1. Description - What is out there? what is it? 2. Explanation - Why? (brings meaning to description)
What makes a good research question?
1. Scientific relevance - where does it fit in literature and theory? have other people asked the question before? what are the discussions? Does it solve a contradictory finding or puzzling issue in social theory? if so, your question is scientifically relevant. 2.Social Importance (alience) - will this question make a difference -- most important bullet point. 3. Feasability - is it possible with available resources and time?
What are the 4 steps you should take when selecting a variable? ERCL (UNCLE URKLE!)
4 Steps you should take when selecting variables: Examine the theories that are relevant to our research question to identify those concepts that would be expected to have some bearing on the phenomenon we are investigating Review the revevant research literature and asses the utility of variables used in prior research Consider the constraints and opportunities for measurement that are associated with the spesific settings we will stidy. Distinguish constants from variables in this setting Look ahead to our analysis of the dara. What role will each variable play in our analysis?
What is a trend study special case?
A cohort study
What is a construct?
A construct - something we create to represent a particular phenominon. (i.e. school achievement is a function of intelligence and motivation) CONSTRUCT: school achievement
What is a scientific knowledge claim?
A scientific claim asks, "Is it repeatable? Can it be replicated?"
What is social theory? (p.23) What is the role of theory in the research process? (explain concepts!)
A set of interrelated constructs (concepts), definitions, and propositions that present a systematic view of phenomena by specifying relations among variables with the purpose of explaining and predicting constructs. Concepts: Concept - Operational definition: a definition that assigns meaning to a construct or variable by specifying the activities or operations necessary to measure the construct - -- it's telling the world about your idea. Effects on social theory: Social theories suggest areas on which we should focus and the propositions that we should consider testing. In the case in the book, theories about domestic violence lead to research that further confirmed the truthfulness of the theories and their predictions.
What is causal validity? (internal validity)
Also known as 'intenral validity'. it exists when a conclusion that A leads to, or results in, B is correct. It refers to the truthfulnes of an assertion that A causes B.
Briefly describe the four ways researchers can protect research participants.-- MHOD
Avoid harming research participants : In the millgram experiment, he was emotionally harming his participants - they shook, had seizures, sweat, etc. -- It was harmful because it could have affected the subject's self image, as well as their ability to trust authorities in the future. Obtain informed consent: To be informed, consent must be given by persons who are competent to consent, have consented voluntarily, are fully informed about the research, and have comprehended what they have been told. Avoid deception in research: Deception occurs when subjects are mislead about research procedures. In Millgram's tests, he mislead participants into thinking they were actually shocking a real person. Maintain privacy and confidentiality: The researcher's commitment to this standard should be included in the informed consent agreement. In the tearoom experiment, the subjects had no idea they were being observed, their privacy was violated.
How are deductive and inductive research linked to theory?
By starting with social theory and then testing some of its implications with data (deductive research); it is most often the strategy used in quantitative methods. By collecting the data and then developing a theory that explains it, this inductive research process is typically used with qualitative methods. A research project can use both inductive and deductive methods. ---we start with a social theory and then testing some of its implications with data (deductive) or we collect data and then develop a theory that explains it (inductive)- both use theories)
What is inaccurate observation?
Choosing to only look at things that are in line with our preferences or beliefs
What is selective (inacurate) info?
Choosing to only look at things that are in line with our preferences or beliefs.
define Cohort design :
Cohort design : a longitudinal study in which data are collected at two or more points in time from individuals in a cohort.
What is a concept? What is a construct?
Concept: a word that expresses an idea or abstraction " a mental image that summarizes a set of similar OBSERVATIONS, FEELINGS, OR IDEAS" A construct: A concept that has been deliberately invented for a special purpose - Example: religiosity, Rurality
Define confidentiality
Confidentiality : provided by research in which identifying information that could be used to link respondents to their responses is availible only to designated personnel for spesific research needs.
What is a constant?
Constant: A number that has fixed value in a givven situation; a characteristic or value that does NOT CHANGE.
What is "content analysis"? What are the strengths and weaknesses of content analysis? (book and lecture)
Content analysis is the study of communications (text) to describe social behavior or test hypotheses about it. It is generally used to DESCRIBE. It can be used to TEST HYPOTHESIS. Advantages: Does not involve human research subjects, inexpensive, can be used when researcher is prevented from surveying or observing the population being studied, computer assisted content analysis. Disadvantages: Locating messages relavent to the research question, some topics do not appear regularly on the availlable media, it can't bs used to test causal relationships betwween variables, selectivity - Gatekeepers of media.
What is cross-sectional research? (p.31) What is longitudinal research? (p.31) What are their major advantages and disadvantages? (p.32-33) How are they different? (p.31-33)
Cross-Sectional Research: Measures characteristics of a population at one point in time - like a snapshot Advantages: inexpensive, describes population at one point in time Disadvantages: Can't study social processes or change, don't know who or what changed, what happened just before or next? Longitudinal research design: Measured characteristics of a population at two or more points in time. Like a movie picture - the more frames you take in a longitudinal study, the closer you aproximate people's actual behavior over time. What changed, who changed, why they changed.. advantages: can study cause and effect, change over time disadvantage: panel attrition possible, expensive The different frames help us to see change prospectively - what changed, who changed, why they changed (s0metimes)
What is a dependent variable? What is an independent variable? What is an intervening variable?
Dependent variable: A variable that is hypothesized to vary depending on or under the influence of another vairble. Independent variable; a variable hypothesized to cause, or lead to variation in another variable. Example: poverty rate. The hypothesis cause. Variable: a characteristic or property that can vary (take on different characteristics or attributes) INTERVENING VARIABLE -- The Intervening variable is your major explanatory reason for looking at the dependent variable. A variable that comes inbetween two variables - An example is durkheim believing married people are happier - really, have greater social intergration. Males test better than females- but it has nothing to do with sex, it has to do with parental involvement.
Descriptive research:
Description: Research in which a social phenomena are defined and described.
What are the 4 main goals of social research? - DEEE
Description: Research in which a social phenomena are defined and described. Exploration: Exploratory research seeks to find out how people get along in the setting under question, what meanings they give to their actions, and what issues concern them. It's often qualitative, rather than number-based. Explanation: Seeks to identify causes and effects of social phenomena and to predict how one phenomenon will wil change or vary in response to variation in another phenomenon. Evaluation: Research that describes or identifies the impact of social policies or programs.
Under what circumstance, do we use descriptive research, exploratory research, explanatory research, and evaluation research?
Description: Research in which a social phenomena are defined and described. Exploration: Exploratory research seeks to find out how people get along in the setting under question, what meanings they give to their actions, and what issues concern them. It's often qualitative, rather than number-based. Explanation: Seeks to identify causes and effects of social phenomena and to predict how one phenomenon will wil change or vary in response to variation in another phenomenon. Evaluation: Research that describes or identifies the impact of social policies or programs.
What is the ecological fallacy? (p.38) The reductionist fallacy?
Ecological fallacy: Because you see tons of examples, you assume EVERYONE is that way. Reductionist: You only see one example, therefore, everyone is like that person. Give an example! On exams! All the time!
Evaluation research:
Evaluation: Research taht describes or identifies the impact of social policies or programs.
What is Generizability?
Exists when a conclusion holds true for the population, group, setting or event that we say it does, given conditions that we specify.
What is Cross population generalizability (external validity)
Exists when findings about one group, population, or setting hold true for other groups, populations, or settings
What are the six ways of knowing? God tensely experienced science ingloos
Experience—trial and error Tenacity—tradition Authority—established beliefs Intuition—agrees with reason Science—Scientific Method Theology—revelation and inspiration
Explanatory research:
Explanation: Seeks to identify causes and effects of social phenomena and to predict how one phenomenon will wil change or vary in response to variation in another phenomenon.
Exploratory research:
Exploration: Exploratory research seeks to find out how people get along in the setting under question, what meanings they give to their actions, and what issues concern them. It's often qualitative, rather than number-based.
Define 'group unit of analysis'
Group unit of analysis: a unit of analysis in which groups are the source of data and the focus of conclusions
List the steps of the research process! Draw the chart!
Identify topic/issue Develop a research question Theory deduction Hypothesis Observations Analysis (Here can continue or go to INDUCTION) Interpret data Inform others
Define individual unit of analysis
Individual unit of analysis: a unit of analysis in which individuals are the source of data and the focus of conclusions
What role does inductive reasoning play in deductive research?
Inductive reasoning enters deductive reseach when we find unexpected patterns in data collected for testing a hypothesis. Inductive explanations are more than trustworthy if they are tested subsequently with deductive research. GREAT INSIGHTS CAN COME FROM INDUCTIVE STUDIES< BUT VERIFIABLE PROOF COMES FROM DEDUCTIVE RESEARCH.
What is deductive research? Inductive research?
Inductive research: Inductive research begins with spesific data, which are used to develop or 'induce' a theory to account for the data - when you start IN the data, you're doing INDUCTIVE research. General conclsions are drawn from spesific data - compare to deductive research.--- Start IN THE DATA. Durkheim took a ton of facts and created a theory of suicide. Deductive Research: In deductive research, we start with a theory and try to find data that will confirm or deny it. You start with a premise, and DEDUCE an answer.
When we say a relationship exists between two variables, what do we mean
It means there's something statistically significant between the two variables.
What is cross-sectional research? Advantages and disadvantages.
Measures characteristics of a population at one point in time. Measuring at one time to take a snapchot of society at that point in time. But you don't know what happens next, or what happened before. That's the limitations - you can't study change. Advantages of this method: relatively inexpensive, describes a population at that point in time very well if done right Disadvantages: can't study social processes or change, and don't know who or what changed. What happened before? what happened next? we don't know.
What does it mean when response values are mutually exclusive? Exhaustive?
Mutually exclusive: A varibale's attributes (or values) are mutually exclusive when every case can be classified as having only one attribute (or value) Exhaustive: Every case can be classified as having at least one attrubute (or value) for the variable.
List and briefly describe each of the four "everyday errors" that often occur when we rely on personal experience for our knowledge.-- SOIR
Overgeneralization - occurs when we unjustly conclude that what is true for SOME cases is true for ALL cases. - When you have some evidence that applies to some cases but you apply it to all cases. Our experiences are limited, and the world is a complex place. If you had a boring chem teacher, it doesn't mean all chem teachers are boring. --- THe way we make sure it is not ovegeneralized is by doing random sampling. Selective or inacurate observation: Choosing to look only at things that are in line with our preferences or beliefs. We dislike beliefs different than our own. We only acknowlege things that agree with our predispositions.--- How does social scice address this? We have proceedures we need to follow. Illogical reasoning: The premature jumping to conclusions or arguing on the basis of invalid assumptions. Resistance to change: The reluctance to change our ideas in light of new information. When you think you have all the answers and you do not need to listen, seek information or raise questions any longer.
List and briefly describe the three major criteria for evaluating the adequacy of a measure.
PRECISION: How accurate is the measure? How large is the measurement error? RELIABILITY: If we measure the same objects again and again with the same instrument, will we get the same or similar results? VALIDITY: Are we measuring what we think we are measuring?
What is panel Attrition?
Panel attrition: panel's lack of participation.
What are the quantitative and qualitative purposes of sampling? (lecture)
Quantitative: we get a representitive sample from a larger population - looking for subjects spesific to our objective. Qualitative research: collect spesific cases, events, or actions that can clarify or deepend understanding on a relavent subject.
When we say a measure is reliable, what do we mean?
RELIABILITY means that a measure produces yeilds consistent scores (or scores that change only to reflect actual changes in phenomenon). If a measure is RELIABLE, it is affected less by random error or chance variation than if it is unreliable.
Define repeated cross-sectional design
Repeated cross-sectional design: a longitudinal study in which data are collected at two or more points in time from different samples of the same population.
What are the 6 Reasons' for panel attrition?-- Actually, Rufus Located Dead and ill Interviews
Respondent's refusal to participate - angry. Inability to participate - people in the process of dying. too ill to respond - in a car accident. Mortality - people die. we can even guess how many people will die in your panel. Researcher's failure to locate respondent (researcher incompetence) - we can't find them, all addresses or numbers are wrong. Researcher's failure to keep accurate records - we got info, byt didn't write it down. We can't find them. Researcher's failure to interview respondent- it happens. Missing people becayse of 1 or all 6 of these.
What is retrospective memory? What are the limitations of retrospective memory in surveys? (lecture)
Retrospective memory - is it accurate? no. people can sometimes remember past factual information - when they graduated (the date and time). But when remembering how they felt then, they'll often just tell you how they're feeling now. Never ask about retrospective attitudes, it won't be accurate at all. But events? It's okay to ask about events. You can help respondents (i.e.' you got married in this year.. so when did you start your job?) However, especially with older people, it can be difficult to get people to recall important dates. Sometimes, the history you're asking them to remember is too complex. TA review: You can only remeber IMPOTANT THINGS and it's hard to remember PAST ATTITUDES. How you feel now can color how you actually felt then. For example, voting for Obama, but then being dissapointed with him. Older people will have a harder time remembering - younger people will remember more. A retrpsoective question is something that happened in the past.
What is science? What is the scientific method?
Science is an objective, accurate, systematic analysis of a determinant body of empirical data, in order to discover recurring relationships among phenomena. The ideas, rules, norms, techniques, and approaches that the scientific community values.
What is the scientific method?
Scientific Method: The ideas, rules, norms. techniques, and approaches that the scientific community values
what is Subject fatigue?
Subject fatigue: respondents are tired of getting interviews, or they get used to what you're asking them and give the same answers over and over again even if they've personally changed.
Draw the triangles that describe inductive and deductive research
TA defintion of deductive research BEings with abstract ideas and principles or theory, and works towards concrete empirical evidence or ideas - deductive means to move from something general from spmething more spesific. You can even draw the triange! Induscive - Start IN THE DATA. Durkheim took a ton of facts and created a theory of suicide.
Why do researchers avoid using the term "proved" or "true" when testing a hypothesis? Why is proving a hypothesis correct hard to do?
THey avoid it because we never actually know something is true - like the black swan example. You can't know that something is true becase you don't see everything. If you've only ever seen white swans, you can't say 'all swans are right' -- you just haven't seen a black swan yet. You'd have to know ALL THE SWANS THAT EVER EXISTED to know that. and social sicnece is only ever focused on a sample.
Why do researchers avoid using the term "proved" or "true" when testing a hypothesis? Why is proving a hypothesis correct hard to do? (lecture)
THey avoid it because we never actually know something is true - like the black swan example. You can't know that something is true becase you don't see everything. If you've only ever seen white swans, you can't say 'all swans are right' -- you just haven't seen a black swan yet. You'd have to know ALL THE SWANS THAT EVER EXISTED to know that. and social sicnece is only ever focused on a sample.
Discuss the ethical issues in the Millgram experiment, the Tearoom Trade study, and the Tuskegee syphilis study. Contrast and compare each. (book and lecture)
Tea room - this guy was watched them int he bathroom, and then followed them home - all without them knowing. this is NOT ethical in ANYWAY. He wrote down their drivers liscence. A man told gay men he was observing them, and he then went to their homes to interview them — he went to their houses without telling them that he knew about their homosexual behavior. ---- Talk about how they're violating privacy, there is no review board. MILLGRAM: It creates a strong reaction to for the person listening to the screen. They wanted to prove that people inflicting pain would continue to do so if told to. The experiment showed that when you put people in social roles with social expectations, they'll hurt others to fulfill that role. Milgrim deieved them into thinking they were receiving physical shocks. THe ones hurt were the ones watching the people being 'hurt'. Tuskeegee experiment: infected black men with syphilis to see how it works. 100 men died. Researches didn't tell them about suflfer drugs that treated syphilis. This is NOT ethical. The men died. They literally let people die. It's unethical because you deliberately didn't tell people they were going to die. Because of this, they passed the national research act requiring Institutional Review Board to approve ALL studies involving human subjects.
List and briefly describe the four indicators of reliability. - TIIA
Test-retest reliability: A measure showing that masures of a phenomenon at two points in time are highly correlated, if the phenomenon has not chaned or has changed only as much as the phenomenon itself. Interitem reliability - an approach that calculates reliability based on the correlation among multiple items used to measure a single concept. Also known as INTERNAL CONSISTENCY. Alternate forms reliability - A procedure for testing the reliability of responses to survey questions in which subjects' answers are compared after the subjects have been asked slightly different versions of the questions or when randomly selected halves of the sample have been administered slightly different versions of the questions. Intro-observer reliability - when similar measures are obtained by different observers rating the same persons, events, or places
What is a Unit of Analysis? (p.37) Why is this choice important?
The level of social life on which a research question is focused - such as individuals, groups, towns or natuons. Nations, towns, and people exist at DIFFEENT LEVELS of society. Sometimes researchers confuse levels of analysis, mistakeingly using data from one to draw conclusions about another.
What is the purpose of triangulation?
The use of multiple methods to study one research question. It can strengthen measurement. When we achieve similar results with different measured of the same vairbale, we can be more confident in the validity of each measure.
Explain - What is an IRB? (p.43) What is the major purpose of an IRB? What is research risk? (book and lecture)
They set protection standards for human subjects used in research experiments. - Because of the Tuskegee project, we passed the national research act requiring Institutional Review Board to approve ALL studies involving human subjects. Institutional review board (IRB): A group of organizations and community representatives required by federal law to receive ethical issues in all proposed research that is federally funded, involves human subjects, or has any potential for harm to subjects Special 'protected' populations that MUST go through the IRB: - Children (younger than 18, with parental permission) - Mentally disabled - Prisoners - pregnant women - Human fetuses - institutionalized.
What are missing values? What are the best ways to deal with missing data (five ways)? (lecture)
They skew data and cause issuies. Delete all missing cases Substitute average score insert data based on non quantitative information - Insert a random value eliminate cases only of variable only being analyzed or missing
Define 'Serendipitous'
Unexpected patters in data thich stimulate new ideas or theorhetical approaches
What are the 5 norms of the scientific community? Uni communists skeptisised disinterestedly - honestly!
Universalism - Irrespective of who conducts the research, the research is to be judged only on the basis of scientific merit. Organized Skepticism - Scientists should challenge and question all evidence and subject each study to intense scrutiny. Disinterestedness - Scientists must be neutral. Communalism- Scientific knowledge must be shared with others. Honesty- Scientists demand honesty in all research.
7. What are unobtrusive measures (nonreactive research)? Give examples.
Unobtrusive measures: a measurement based on physical traces or other data that are collected without the knowlege or participation or groups that generated the data Examples: Since all drug users urinate, and all the urine ends up in the sewer, we can test the urine and find out what drugs are most prominent. By looking through phonebooks, we can see which places have the most hospitals and nursing homes.
Define 'anomalous'
Unxpected patterns in data that don't fit the theory being proposed
Define 'debriefing'
a researcher's informing subjects after an experiment about the experiment's purposes and methods and evaluating subject's personal reastions to the experiment
What is a variable?
a symbol to which numerals or values are assigned (grade point average, IQ scores)
What is a hypothesis?
a tentative statement about empirical reality involving a relationship between two or more variables. For example, the higher the poverty rate in a community, the higher the percentage of community residents who are homeless. In a hypothesis, you're suggesting that one variable influences another - or that the second in some way depends on the first.
sample generalizatbility:
exists when a conclusion based on a sample, or subset, of a larger population holds true for that population.
What is Measurement validity:
exists when an indicator measures what we think it measures.
define cohort
individuals or groups with a common starting point - a college graduating class, employees, etc.
What is theory?
is a logically interrelated set of proposition about empirical reality.
Overgeneralization:
occurs when we unjustly conclude that what is true for SOME cases is true for ALL cases. Our experiences are limited, and the world is a complex place. If you had a boring chem teacher, it doesn't mean all chem teachers are boring.
Describe the classic experiment
researcher know who changed, what changed, how much changed, and why they changed.
What is illogical reasoning?
the premature jumping to conclusions or arguing on the basis of invalid assumptions.
Validity:
the state that exists when statements or conclusions about empirical reality are correct
What is social science?
the use of scientific knowlege to investigate individuals, societies, and social processes; the knowlege produced in these investigations
