SOC 380 Final Exam Study Guide
SOC 380 Final Exam Study Guide SOC 380 001
Popular in Introduction to Research Methods
SOC 380 001
verified elite notetaker
Popular in Sociology
This 17 page Study Guide was uploaded by Maddie Butkus on Friday April 29, 2016. The Study Guide belongs to SOC 380 001 at Ball State University taught by Dr. Rachel Kraus in Winter 2016. Since its upload, it has received 20 views. For similar materials see Introduction to Research Methods in Sociology at Ball State University.
Reviews for SOC 380 Final Exam Study Guide
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 04/29/16
Final Exam Study Guide Material from Exam 1 •Wheel of science Theory Empirical Generalization Hypotheses Observation Inductive, qualitative, interviews (goes from more specific to very general - bottom to top) vs. deductive quantitative (general to more specific – top to down) scientific knowledge logical system bases knowledge on direct, systematic, empirical observation and evidence (not value judgments) vs. other types of knowledge (common sense, intuition or personal experiences) •Types of research: Exploratory- 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. Descriptive- research in which social phenomena are defined and described Explanatory- seeks to identify causes and effects of social phenomena and to predict how one phenomenon will change or vary in response to variation in another phenomenon. •Generalizability- exists when a conclusion holds true for the population that are summarized into conceptual categories, reevaluated in the research setting and gradually refined and linked to other conceptual categories. Replication- to repeat multiple times •Errors of Inquiry: o Inaccurate observations: wrong about what you think you saw o Overgeneralization: correct about what you saw, but apply it too broadly o Selective Observation: notice only what support your view •Cross sectional and types of longitudinal research design (in book): Trend: a longitudinal study in which data are collected at two or more points in time from different samples of the same population For example: Before an election a sample of adults is drawn. A year later, a different sample drawn from the same population shows a change. Cohort: a longitudinal study in which data are collected at two or more points in time from individuals in a cohort. A group of graduates that are the same age from different colleges with the same degree are studied every 5 years on how they have progressed. Panel: longitudinal study in which data are collected from the same individuals – the panel – at two or more points in time. Example: a study of 1,000 high school seniors who are then contacted every two years for a ten-year period to participate in a follow-up survey Be sure you know definitions AND be able to provide an example of each. •IRB: Institutional Review Board Human subjects: a living individual about whom an investigator conducting research obtains data from Research: a systematic investigation including research development, testing and evaluation, designed to develop or contribute to generalizable knowledge. Research ethics: •Protected populations in research o Criminals, children, pregnant women (biomedical research), mentally or physically challenged, people with incapacity to give consent. •Literature reviews o Collection of writings on a topic – usually scholarly o Summary (recap of what people say) AND synthesis (organize in a particular way for your purpose) o Different ways to synthesize: chronology, theme and methodology o Do not write a paragraph per article – write in themes o Evaluate/critique to determine contribution o Sound methodology, limitations of studies o Illustrate your contributions to some gap in the literature • Theory: logically interrelated set of propositions about empirical reality Hypotheses: tentative statement about empirical reality involving a relationship between two or more variables IV: variable that is hypothesized to cause or to lead to variation in another variable DV: variable that is hypothesized to vary depending on or under the influence of the IV. •Units of analysis: level of social life we are studying, who or what is being measured o Individuals- attitudes and behaviors, students, gays, voters, etc. o Groups- (informal)/organizations (formal): size and social structure o Geographical Location: population – gangs, classes, friendships, etc. ex: regions power, crime rates, etc. o Social Artifacts: books, poetry, jokes, ex: content cats, etc. Ecological fallacy: An error in reasoning in which incorrect conclusions about individuals level processes are drawn from group- level data. Reductionism Fallacy: An error in reasoning that occurs when incorrect conclusions about group-level processes are based on individual- level data. • Positive Correlation: IV & DV move in the same direction Negative Correlation: IV & DV move in opposite directions Material from Exam 2 Highlighted = Book Material Conceptualization: o Process of specifying what we mean by a term. Helps translate portions of an abstract theory into testable hypotheses involving specific variables. In inductive research, conceptualization is an important part of the process used to make sense of related observations. EX: workshop from class – defining simple words with partners Operationalization: o Occurs after conceptualization. Process of specifying the way that you will measure each concept. Operational concepts in one or more variables (IV & DV) o Variable Criteria: Categories must cover all possible answers Answers cannot fit into more than one response category o Categorical Variables: Nominal Variables: Place case into categories with out natural ordering Assigned numerical value, number means NOTHING. EX: race, sex, region (no more or less, no bigger or smaller than each other) Ordinal Variables: Allow us to determine order of categories, but there is no quantifiable distance between the categories EX: agreement scales; strongly agree, agree, neutral, disagree, strongly disagree (distance between categories is not measureable) Ratio Variables: Variable we have fixed, absolute zero point We can rank cases, we can say how far apart cases are and we can say that one value “X” time as large as another value EX: age, height, weight, length of residency, # of clubs belong to, income Example of Religion for all three types of variables: Nominal: Religious Affiliation (catholic, Methodist, Baptist, Jewish, etc.) Ordinal: Religiosity, how often you attend service (never, occasionally, sometimes, etc) Ratio: how many times have you attended service in the last month? Levels of measurement: o Validity: extent to which a measure actually measures what we think it does. Face Validity: does the measurement make common sense? Criterion (Predictive) Validity: does our measure of a concept agree with a more direct or already validated measure of the same concept? EX: Standardized test scores & college success. Construct Validity: the degree to which a measure relates to other variable as expected within a system of theoretical relationship. EX: if measure of marital satisfaction relates to measure of marital infidelity (as 1 goes up, the other decreases) the way you think they should construct validity Content Validity: degree to which a measure covers the range of meanings/dimension with a concept Does measuring someone’s intelligence based only on standardized test scores pass content validity? Is only addition a good measure of someone’s math ability? o Reliability: extent to which a measure yields consistent responses on different occasions. 4 Empirical Ways of Assessing Measurement & Reliability 1. Test Re-take method: a. Take the same measurement at two or more points in time 2. Split-Half Method: a. Make more than one measurement of a concept 3. Inter-Item Method: a. Using a series of questions to measure the same concept 4. Inter-Observer Method: a. Using 2 different observers to measure the same concept. 5. Alternate-Forms Reliability: (FROM THE BOOK) 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 question Triangulation: o The use of multiple methods to study one research question. Population: Whatever group you want to learn something about. o The entire set of individuals or other entities to which study findings are to be generalized. EX: ALL the countries in the world Sample: o A subset of a population used to study it. EX: a subset of countries It is impossible to study every country- this narrows down a sample to testable measures. Sampling frame: o A list of all elements or other units containing the elements in a population. EX: a list of all countries Each country is an element on the list of countries in the population Bias: o Means someone who has more or less of a chance to be chosen for a sample. o Occurs when some population characteristics are over or underrepresented in the sample because of particular features of the method of selecting the sample. Census: Research in which information is obtained through responses from or information about all available members of an entire population. Probability sampling: Sampling methods that allow us to know in advance how likely it is that any element of a population will be selected for the sample. o Probability of selection is known and is not zero (so there is some change of selecting each element o These methods randomly select elements & therefore have no systematic bias (nothing but chance determines which elements are included in the sample). o This feature of probability samples makes them much more desirable than nonprobability samples when the goal is to generalize to a larger population. Random samples (simple, stratified (2 types), cluster) o Simple Random Sampling: Identifies cases strictly on the basis of chance Flipping a coin and rolling a die both can be used to identify cases strictly on the basis of change, but these procedures are not very efficient tools for drawing a sample. o Stratified Random Sampling: Ensures that various groups will be included First, all elements in the population (that is, in the same sampling frame) are distinguished according to their value on some relevant characteristics o EX: army rank; for instance generals, captains, privates o Proportionate Stratified Sampling: You plan to draw a sample of 500 from an ethnically diverse neighborhood. Neighborhood population is 15% black, 10% Hispanic, 5% Asian & 70% white. If you drew a random sample, you might end up with somewhat different percentages of each group BUT, if you created sampling strat based on race and ethnicity, you could randomly select cases from each stratum, in exactly the same proportions as in the neighborhood population This is termed proportionate stratified sampling because the percentages are proportional to the population o Disproportionate Stratified Sampling The proportion of each stratum that is included in the sample is intentionally varied from what is in the population. In the case of the sample stratified by ethnicity, you might select equal numbers of cases from each racial or ethnic group NOT proportional to percentages in population o Cluster Sampling Broad to more narrow Creating clusters then sampling within the clusters Naturally occurring mixed aggregated of elements of the population. Sampling error: o Sampling error is an error that occurs when using samples to make inferences about the populations from which they are drawn. There are two kinds of sampling error: random error and bias. o Random error is a pattern of errors that tend to cancel one another out so that the overall result still accurately reflects the true value. Every sample design will generate a certain amount of random error. o Bias, on the other hand, is more serious because the pattern of errors is loaded in one direction or another and therefore do not balance each other out, producing a true distortion. o Observing a sample instead of a population Non-probability samples (snowball, convenience, quota, purposive) o Often used in qualitative studies when researchers are unable to use probability selection methods. o Sometimes a probability sample is not feasible or generalizability isn’t possible… such as? EX: Internet data – no way you can get a list of all FaceBook users or Non-Mainstream groups – hard to track down o Availability Sampling (convenience sample): Elements are selected for availability sampling because they’re available or easy to find. Thus, this sampling method is also known as haphazard, accidental or convenience sample. EX: People on the street, internet posts, magazine surveys – all at your convenience o Quota Sampling: Intended to overcome flaw of availability sampling – whoever of whatever is available, without any concern for its similarity to the population of interest. Quotas are set to ensure that the sample represents certain characteristics in proportion to their prevalence in the population Similar to stratified sampling, but quota sampling is not representative on any other characteristic & people chosen by first come first serve basis NOT random sample. EX: 2 men, 2 women but 1 black man & 1 white man and 1 black woman & 1 white woman. o Purposive Sampling: Each sample element is selected for a purpose because of the unique position of the sample elements EX: Studying the entire population of some limited group (directors of shelters for homeless adults) or a subset of a population (sociology majors at ball state) Purposive sample can also be “key informant survey” which targets individuals who are knowledgeable about issue in research o Snowball Sampling: Hard to reach or identify populations, not sampling frame, but the members of which are somewhat interconnected EX: belly dancers know other belly dancers o Underground populations Critique of Snowball Sampling: relying on your one person to give you names of others and they’re all most likely going to have similar answers Benefits and limitations of different survey distribution methods o Mailed, Self- Administered survey: conducted by mailing a questionnaire to respondents, who then take the survey by themselves Limitations: Central problem is maximizing the response rate – probably only a 30% return rate, women often respond more. Benefits: low cost, available population o Group- Administered Survey: completed by an individual respondent who are assembled in a group. Limitations: seldom feasible because it requires captive audience, feel coerced to participate – less honesty Benefits: high response rate o Telephone Survey: Interviewers question respondents over the phone and record their answers Limitations: not being able to reach proper sampling units, not getting enough successfully completed responses Benefits: Available population- basically everyone has a phone o In-Person Surveys: interviewer questions respondents face to face and records their answers. Limitations: should always conduct the survey exactly the same with each participant, presence of interviewer can make it hard for participant to answer questions Benefits: high response rates, survey control, solid responses o Electronic Surveys: sent and answered through e-mail or on the web Limitations: coverage issue, cannot reach people without computers/internet Benefits: cover large population, more comfortable to disclose information, get more honest answers, easy to conduct. Experiments: o A test under controlled conditions in which the IV is manipulated by the experimenter in order to study the effects of that variable on the dependent variable. o True Experiment: 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 measure in a posttest. o Comparison Group: groups that have been exposed to different treatments or values of the IV o Experiments share 2 important features: 1. Treatment (experimental group): group of subjects that receives the treatment or experimental manipulation 2. Control Groups: a comparison group that receives no treatment Groups must be similar before IV is manipulated Experiment limitations o IV needs to be manipulated – many social variables can’t be manipulated such as age, rage or sex etc. o Random assignment might be unfair or bias o Weak on external validity: artificially constructed circumstances may not hold in “real-world” o Threats to internal validity: History: other events effect DV (confounding variables) Study subject changes (endogenous change) Differential attrition (mortality): problem that occurs in experiments when comparison groups become different because subjects in one group are more likely to drop out for various reasons compared with subjects in the other groups. Selection Bias: no random assignment, groups not truly equal. Instrumental decay: deterioration over time of a measurement instrument, resulting in increasingly inaccurate results. Regression effect: source of cause invalidity that occurs when subjects chosen because of their extreme scores on a dependent variable become less extreme on a posttest as a result of mathematical necessity rather than treatment. Contamination: experimental group or the comparison group is aware of the other group and it influences the posttest result Double blind procedure: an experimental method in which neither the subject nor the staff know which subjects are getting the treatment Placebo effect: subjects receive treatment that they consider to be beneficial and improve as a result of that expectation The Hawthorne effect: a. A type of contamination in experimental and quasi-experimental 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. Material from Exam 3 Descriptive Statistics: stats used to describe the distribution of and relationship among variables Inferential Statistics: stats used to estimate how likely it is that a statistical result based on data from a random sample is representative of the population from which the sample is assumed to have been selected. Correlation coefficient: The correlation coefficient is a measure that determines the degree to which two variable's movements are associated Meaning of statistical significance: mathematical likelihood that an association is not the result of chance, judged by a criterion the analyst sets (probability is less than .05) Measures of central tendency: Mode: frequency that occurs most often Median: position average or divides the distribution in half (50 th percentile) Mean: arithmetic average; = sum of values/# of values Measures of variance: capture how widely and densely spread Range: simplest measure of variance; = highest value – lowest value +1 Variance: statistic that measure the variability of a distribution as the average squared deviation of each case from the mean. Standard deviation: distance from the mean that covers a clear majority of cases (2/3) Coding: process of transforming raw data into a “standardized” form - Type of content analysis involving logic of conceptualization and operationalization - Coding in Content Analysis o Content analysis is essentially a coding operation o Coding in content analysis involves the logic of conceptualization and operationalization. o Define set of coding categories Deductive: pre-established codes (from theory, past research, what you look for) “decision rules” to apply codes (when X occurs in data, it receives y code) applying codes to body of text: place data into codes Content analysis: - Unit of analysis: tangible “thing” we examine, want to learn about, understand, (artifact we are examining; commercial, books, movies) - Unit of observation: what we look at to understand the “thing,” path we use to get to understanding o EX: learn about a novelist (unit of analysis = individuals) by examining the novels they write (unit of observation) o EX: learn about commercials by watching commercials; Unit of analysis and unit of observation are the same thing Manifest vs. latent coding: - Manifest: right up front, noticeable. - Latent: hidden message Inter-coder reliability: Inter-coder reliability refers to the extent to which two or more independent coders agree on the coding of the content of interest with an application of the same coding scheme. In surveys, such coding is most often applied to respondents' answers to open-ended questions, but in other types of research, coding can also be used to analyze other types of written or visual content. Inter-coder reliability is a critical component in the content analysis of open-ended survey responses Archival research: written or visual records, not produced by the researcher Writing tips: -Don’t expect to write a polished draft the first time around - Leave time for revision and accept much of your writing will be discarded - Write as fast as you can and spell/grammar check later - Ask for reactions from other people you trust - Draft segments as you go; don’t write at once - Shorten and clarify statements - Make sure each paragraph only concerns 1 topic Applied research reports: The goal of research is not just to discover something, but to communicate that discovery to a larger audience. A successful report must be well organized and clearly written Characteristics of a good literature review: - identify gaps in current knowledge - integrated literature review should: o be directly tied to the research question o summarize prior research be selective; not just the first articles be up to date use direct quotes sparingly o Critique prior research o Inform hypotheses o Present pertinent conclusions (relevant to our study) Distinguish your opinion clearly from research conclusions Don’t emphasize problems that you can’t avoid either. Field research: (P. 206) - Complete observation: role in participant observation in which the researcher does not participate in group activities and is publicly defined as a researcher - Reactive effects: changes in an individual that result from being observed or otherwise studied. - Complete participation: role in field research in which the researcher does not reveal his or her identity as a researcher to those who are observed. - get approval to observe - must be sensitive to the impression they make and ties established when entering the field - collects data from people who have different perspectives and for developing relationships that the research can use to surmount the problems in data collection that arise in the field - researcher needs to be ready to explain to participants - Gatekeeper: a person in a field setting who can grant researchers access to the setting. - Key Informant: an insider who is willing and able to provide a field researcher with superior access and information including answers to questions that arise during the research. - Develop a plausible explanation for yourself and your study and keeping the support of key individuals to maintain relationships in the field. Participant observer: a qualitative method for gathering data that involves developing a sustained relationship with people while they go about their normal activities. Reflexivity: (P. 240) - Reflexivity entails the researcher being aware of his effect on the process and outcomes of research - Honest and informative account about how the researcher interacted with subjects in the field, what problems they encountered and how these problems were or were not resolved. Conversation analysis: (P. 243) - qualitative method for analyzing ordinary conversations. Unlike narrative analysis conversation analysis focused on the sequence and details of conversational interaction rather than on the “stories” people are telling. Like ethnomethodology, from which it developed, conversation analysis focuses on how reality is constructed rather than on what it is. - Three Premises: o Interaction is sequentially organized and talk can be analyzed in terms of the process of social interaction rather than in terms of social interactions rather than in terms of motives or social status. o Talk as a process of social interaction, is contextually oriented – it both is shaped by interaction and creates the social context of that interaction o These processes are involved in all social interaction, so no interactive details are irrelevant to understanding it Grounded theory: systematic theory developed inductively, based on observations that are summarized into conceptual categories, reevaluated in the research setting and gradually refined and linked to other conceptual categories. Ethnomethodology: qualitative research method focused on the way that participants in a social setting create and sustain a sense of reality Netnography: use of ethnographic methods to study online communities Nomothetic and idiographic explanations: Represent an understanding to social life - An idiographic method focuses on individual cases or events. Ethnographers, for example, observe the minute details of everyday life to construct an overall portrait of a specific group of people or community - A nomothetic method, on the other hand, seeks to produce general statements that account for larger social patterns, which form the context of single events, individual behaviors, and experience. Qualitative data analysis Steps in qualitative Data Analysis: 1. Documentation of the data (interview transcripts) 2. Coding 3. Examining relationships in the data to show how one concept may influence another 4. Authenticating conclusions by evaluations of alternative explanations; credibility based on data (offers questions from the data to illustrate concepts, patters of ideas) Analyzing Qualitative Data - initial or “open” coding stage: line by line coding using phrases explicitly found in the data - Codes combined into broader themes - Constant comparative method: data are constantly checked and re-checked against the broader theme o New data constant re-examined whether or not the examples really “fit” that theme of if they are demonstration something else, If not…. They are reexamined for possible new themes Themes/patterns may be discarded if found the aren’t “really” relevant Numerous readings and re-readings of data Importance of examining relationships between concepts - There are no variables or numbers; we need thick descriptions to find relationships & explanations - Examining relationships in the data to show how one concept may influence another - Authenticating conclusions by evaluating alternative explanations; credibility based on data (offers quotes from the data to illustrate concepts, patterns, or ideas.) o Use quotes to identify findings, patterns from data Interviewing and saturation: point at which subject selection is ended in intensive interviewing because new interviews seem to yield little additional information. Focus groups: A qualitative method that involves unstructured group interviews in which the focus group leader actively encourages discussion among participants on the topics of interest. Ethics involved in qualitative data ANALYSIS (P. 254) - Research integrity and quality: study is conducted carefully, thoughtfully and correctly in terms of some reasonable set of standards. Produce authentic and valid conclusions. - Ownership of data and conclusions: conflicts of interest between different stakeholders much more difficult to resolve. Working though the issues as they arise is essential. - Use and misuse of results: it is prudent to develop understandings early in the project with all major stakeholders that specify what actions will be taken to encourage the appropriate use of project results and to respond to what is considered misuse of these results Criteria for assessing the quality of a research article (cannot find much information on this) - peer reviewed - methods - sample population - findings Your preferred research method: qualitative, quantitative or content analysis. It’s strengths and weaknesses (this is my own answer) Surveys: excellent for generalizable studies of large populations o Multiple variables o Allow for statistical testing of hypothesis o May be inaccurate and low on nuance, context
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'