Sociology 220 Final Exam

Grounded Theory

Collect and analyze data to derive theory (example of induction)

• Has an idea of what he’s trying to find, but his own observations shape the specifics of his theory

Deduction (deductive reasoning)

theory to (hypothesis to) observation

Induction (inductive reasoning)

observation to (empirical generalizations to) theories

Experiments (experimental - causation between two variables)

social researchers typically select a group of subjects, do something to them, and observe the effect of what was done

1. Taking action

2. Observing consequences of that action

independent and dependent variables, pre-testing and post-testing, and experimental and control groups

Classical experiment 3 major components

Independent variable

the cause, takes the form of a stimulus (present or absent)

Experimental group

Group of subjects to whom an experimental stimulus is administered

Control group

Groups of subjects to whom no experimental stimulus is administered, and who should resemble the experimental group in all other respects - allows the researcher to assess how much effect the actual administration of the stimulus has on the outcome of interest

Double-blind experiment

Experimental design in which neither the subjects now the researchers know which is the experimental group and which is the control group (eliminates bias)

Randomization

Technique for randomly assigning experimental subjects to either the experimental or control group (preferable because the experimenter may not be aware of all the characteristics of the subject that could affect the findings)

Matching

• Pairs of subjects are matched based on their similarities on one or more variables

  • One member of the pair is assigned to the experimental group and the other to the control group so that the two groups are similar to one another

  • What variables should be used to match? These variables cant be specific in any definite way, and depend on the nature and purpose of the experiment 

  • People within a specific variable group (important to the study) are split evenly

Internal validity

The study actually tests what it seeks to test

(the possibility that conclusions drawn from experimental results may not accurately reflect what happened in the experiment itself)

External validity

The study is generic to other situations and contexts - generalizable to the “real world”

(the possibility that conclusions drawn from experimental results may not be generalizable to the “real world”)

Temporal Priority

Principle that causes must occur before the effects

Placebo

A “drug” with no relevant effect

Strengths of experimental

• Isolation of experimental variables impact over time

• Replication

• Scientific rigor.

Weaknesses of experimental

Artificiality of laboratory settings

Non-experimental

cross sectional, correlation, observational

Quasi-experimental

field experiment, natural experiment

Respondents

A person who provides data for analysis by responding to a survey questionnaire

Questionnaire

Document containing questions and other types of items designed to solicit information appropriate for analysis

Open-Ended questions

Questions in which the respondent is asked to select an answer from a list provided by the researcher

Closed-Ended questions

Survey questions in which the respondent is asked to select an answer from a list provided by the researcher

Contingency questions

Survey question intended for only some respondents, determined by their responses to some other question (Questions may not be relevant to all respondents

 Matrix Questions

Instances when a series of items share the same set of responses

- Quite often, you’ll want to ask several question that have the same set of answers, like a Likert Scale (Strongly agree to strongly disagree)

- While efficient, it can produce a response set where respondents answer all the items in the same way

- Advantages - uses space efficiently, respondent will probably find it easier to complete a set of questions presented this way, and allows for respondents to compare to earlier answers

Self-administered questionnaires

Where respondents are asked to complete the questionnaire themselves (most common is the mail survey) - cheaper and faster than face to face interviews, national is the same cost as local mailings, requires small staff, and more willingness to answer controversial items

Follow-Up Mailing

sending either a reminder or another survey to respondents who haven’t already returned the survey

Population

The cluster of people, events, things or other phenomena in which you are most interested - often the “who” or “what” that you want to be able to say something about at the end of your study

Sampling

Process of selecting observations that will be analyzed for research purposes - selecting some subset of one’s group of interest and drawing conclusions from that subset

Probabilistic sampling:

Techniques employed to generate a formal or statistically representative sample - utilized when the researcher has a well-defined population to draw a sample from, as it is often the case in quantitative research, and this fact enables the researcher to generalize back to the broader population (general terms for samples selected in accord with probability theory, typically involving some random-selection mechanism

• Its application involves sophisticated use of statistics, the basic logic isn’t difficult to understand

• If all members of a population were identical in all respects, there would be no need for careful sampling procedures (any single case would suffice  as a sample of the whole population)

• Provide useful descriptions of the total population, a sample of individuals from populations must contain the same variations that exists in the populations

Bias

Those selected are not typical or representative of the larger population

Representativeness

• Quality of a sample of having the same distribution of characteristics as the population from which it was selected\

  • Each member of the population has a known probability of being selected in the sample

Advantages of probability sampling

typically more representative than other types of samples because biases are avoided, and permits researchers to estimate the accuracy or representativeness of the sample

Element:

Unit of which a population is composed and which is selected in a sample

Population:

theoretically specified aggregation of the elements in a study

• Study population:

• Aggregation of elements from which a sample is actually selected

  • Researchers are seldom in a position to guarantee that every element meeting the theoretical definitions laid down actually has a chance of being selected in the sample

Non-probabilistic sampling:

Technique is the method of choice when some participants are more desirable in advancing the research project’s objectives - best approach for a variety of qualitative research (not possible to generalize back to population)

Reliance on available subjects

Uses people (groups, organizations, or social artifacts) that are readily accessible to the researcher

• Convenience sampling

• Doesn’t allow for control over the representativeness of a sample

• ONly justifies if less risky methods are unavailable

• Researchers must be very cautious about generalizing when this method is used

• When would this method be appropriate?

  • Pretesting a questionnaire - the test run might uncover defects in the questionnaire

• However, it will seldom produce data of any general value (studies findings wouldn’t represent any meaningful population)

Purposive or judgmental sampling

• Identifying a small subset of the population the researcher is interested in and then sampling those subjects

  • Small subsets of a population

  • Two-group comparison

  • Deviant cases

    • Ex. You might gain important insights into the nature of school spirit by interviewing people who don’t engage in school spirit activities

Snowball Sampling

• Each person interviewed may be asked to suggest additional people for interviewing - uses subjects as a away to identify other potential subjects to be included in the sample (process of accumulation as each subjects suggests other subjects

  • Especially useful for studying population show members are difficult to locate (sensitive)

    • Ex. homeless individuals, migrant workers, or undocumented immigrants

  • Sometimes “chain referral” is used when the sample unfolds and grows from an initial selection

  • Often used in field research and special populations (more in qualitative)

Quota sampling

• Units are selected into a sample on the basis of pre-specified characteristics, so that the total sample will have the same distribution of characteristics assumed to exist in the population being studied

  • Researcher knows the characteristics of the population they wish to sample. The researcher then selects subjects that represent the population (they try to match them)

    • Ex. I now the population I am studying is 60 percent women and 40 percent men, so when selecting subjects, I will try to match that quota

  • Similar to probability sampling, but has inherent problems -

    • Quota frame must be accurate (proportions of population must be accurate)

    • Selection of sample events may be biased (researcher)

Informant:

Someone who is well versed in the social phenomenon that you wish to study and who is willing to tell you what they know about it

Random Selection

• Select a set of elements from a population in such a way that descriptions of those elements accurately portray the total population from which the elements are selected

  • Each element has an equal chance of selection independent of any other event in the selection process

  • serves as a check on conscious or unconscious bias on part of the researcher and satisfies probability theory, which provides the basis for estimating the characteristics of the population

    • Ex. flipping a coin or rolling a set of dice

      • “Selection” of a head or tail is independent of previous selections of heads or tails

      • No matter how many heads turn up in a row, the chance the next flip will produce heads is exactly 50-50

Sampling unit

Element or set of elements considered for selection in some stage of sampling

Probability theory

Allows researchers to estimate how close to the population their sample is on a given dimension

Parameter

• Summary description of a given variable in a population

  • Ex. Mean income of all families in a city;age distribution of city

Sampling Distribution

Distribution of the dots on the graph and allows the sociologists to calculate the sampling error

Sampling Error

• Amount of error made when trying to estimate a measure of the population using a sample

  • Ex. Want to study percent of students, out of 200, who approve/disapprove of conduct code.

• 1. Random Sampling

• 2. Stratified Sampling (select people random from subgroups)

• 3. Cluster Sampling (random clusters, which aren’t representative of population)

• 4. Systematic Sampling

Probability Sampling Techniques

Interviews

thoughtfully designed, with particular approaches to inquiry and a focus on reflexivity, along with other practices that truly enhance with experience

In depth interviews:

Explore rich personal experiences, guided by a few thoughtfully crafted questions (uses these questions to uncover deeper insights, allowing for a more profound understanding of each individual’s journey)

Descriptive Questions:

Designed to start a conversation about a particular incident/situation

Grand tour Questions:

Designed for the participants to talk about their everyday experience

Specific grand tour questions

Similar to grand tour questions but regarding a particular incident/situation and how they felt about it

Qualitative field research

Type of observational method from methods designed to produce data appropriate for quantitative (statistical) analysis

Practices

various kinds of behavior, such as talking or reading a book

Episodes

variety of events such as a divorce, crime or illness

Encounters

two or more people meeting and interacting

Roles and social types

analysis of the positions people occupy and behavior associated with those positions (occupations, family roles, ethnic groups)

Relationships

behavior appropriate to pairs or set of roles (mother-son relationships, friendships, etc.)

Groups

small groups (friendship cliques, athletic teams, and work groups)

Organizations (formal)

hospitals, schools, social and personal relationships

Settlements and habitats

small-scale “societies” (villages and neighborhoods), as opposed to large societies (nations)

Social Worlds

ambiguous social entities with vague boundaries and populations (“sports world” and “Wall Street”

Full participant

• Goes about ordinary life in a role or set of roles constructed in the social setting they are studying (complete participants or participant-observer)

  • Ex. participants in a campus demonstration or may even pretend to be a genuine participants

  • In any event, you must let people see you only as a participants, not as a researcher

  • Ethical issue- deceiving people you're’ studying and hope they confide in you, consent

Complete observer

• Engages not at all in social interaction and may even shun involvement in the world being studied

  • Could participate fully with the group under study but make it clear that you were also undertaking research (complete observer)?

    • Ex. as a member of a volleyball team, you might use your position to launch a study in the sociology of sports, letting your teammates know what you're doing

  • Dangers - people being studied may shift their attention to the research project, rather than the natural process, or you may come to identity too much with the interests and viewpoints of the participants (you begin to “go naive” and lose much of your scientific detachment

Reactivity

Problem that the subjects of social research may react to the fact of being studied, thus altering their behavior from what it would have been normally (think Hawthorne Effect)

Ethnography

Report on social life that focuses on detailed and accurate descriptions rather than explanations

• White believes to learn fully about social life on the streets, he needed to become more of an insider. His study offered something that surveys couldn't - richly detailed picture of lids among the Italian Immigrants of Cornerville

Ethnomethodology

Approach to the study of social life that focuses on the discovery of implicit, usually unspoken assumptions and agreement

• Involves the intentional breaking of agreements as a way of revealing their existence

• Whereas traditional ethnographers believes in immersing themselves in a particular culture ad reporting the informat’s stories, ethnomethodologists see a need to “make sense” out of informant’s perceptions of the world

Grounded theory

Inductive approach to the study of social life that attempts to generate a theory from the constant comparing of unfolding observation

• Seeks to develop general theories from specific patterns drawn from the data

• Different from deductive, which is theory used to generate hypotheses to be tested through observations

Case Studies

In-depth examination of a single instance of some social phenomenon

• Represent an in-depth qualitative study of a particular case

  • Ex. attitudes of one particular class, in one specific school, city, state, country, time, etc.

• Extended case method - seeks to use the insight form the case study to critique existing theories

• Researcher begging by identifying the major claims made by the theory, then using a case study to extend/modify the theory

Extended case method

Technique in which case study observations are used to discover flaws in ad to improve existing social theories

• Whereas grounded theorists seek to enter the field with no theory, an extended case method is the opposite

Qualitative interview

Based on a set of topics to be discussed in depth rather than based on the use of standardized questions (survey interviewing) - researcher has a general idea of what he or she would like to ask, but the interview is less formal than a face-to-face interview in a survey

• Tone is much more conversational, but the researcher should guide the direction of the interview

• Subject should be allowed to do most of the talking

Focus Group

Group of subjects interviewed together, prompting a discussion

• Similar to qualitative interviewing, but the researcher is questioning several subjects simultaneously

• Researchers usually seek to include certain types of people

• Advantages - real-life data, flexible, high degree of face validity, dast, inexpensive

• Disadvantages - not representative, little interviewer control, difficult analysis, interviewer/moderator skills, difficult logistically

Unobstructive Methods

researcher doesn’t interfere with the subject or study in any way

Content Analysis

Study of recorded (already existing) human communications (ex. social artifacts)

• Ex. books, magazines, websites, newspapers, poems, paintings, laws, songs, speeches, letters, emails, tv shows, bulletin board postings

• Topics appropriate - Useful for analysing human communications, and to answer the basic question of communication research

  • “Who says what, to whom, why, how and with what effect?”

  • Ex. Are romance novels in France more concerned with love than US novels?

  • Early ex. Work of Ida B. Wells who in 1892 examines Southern newspapers to analyze the various reasons for the lynching of Black men

Coding

Process whereby raw data are transformed into a standardized form suitable for machine processing and analysis

Manifest content

• Visible, surface content; concrete terms contained in a communication - observable that is easy to identify

  • Ex. to determine how romantic a novel is you might simply count the number of times the word “love” appears in each novel or the average number on a page (could use other words, like care, hug, and kiss to strengthen your measure)

  • Advantages - ease and reliability

  • Disadvantage - validity

Latent content

• More subtle, underlying meaning

  • Ex, you might read an entire novel and make an overall assessment of how romantic it was

    • Although your assessment might be influenced by the number of times your reach the word “love” and “hug”, it wouldn’t depend fully on their frequency

  • Advantage - better designed for taping the underlying meaning of communications

  • Disadvantage - reliability and specificity (different analysis then others)

Analyzing Existing Statistics

Relies open official statistics usually reported by government officials or organizations (statistics that have already been analyzed)

Ecological fallacy

Erroneously drawing conclusions about individuals solely front the observations of groups

Mixed methods research

Emerging research approach in the social and health sciences that involved combining both statistical trends and stories to study human and social problems

• Around this approach has developed an entire research methodology

• Core assumption is that when an investigator combines both statistical trends and stories, that combination provides a better understanding of the problem than either trends or stories alone

Quantitative Methods

Pre-determined, instrument-based questions, performance, attitude, observational and census data, statistical analysis, and statistical interpretation

• Advantages: draw conclusions for large numbers of people, efficient data analysis, demonstrate relationships, examine probable cause and effect (confirmatory), bias controlled, and people like numbers

• Disadvantages: impersonal, dry, do ont hear the words of the participants, limited understanding of context of participants, and largely researcher driven

Qualitative Methods

Emerging methods, open-ended questions, interview, observation, document and audiovisual data, text and image analysis, and themes, patterns interpretation

• Advantages: detailed perspectives of a few people, can hear voices of participants, understand participants' experiences within context, built from views of participants, not researcher, and people like stories

• Disadvantages: limited generalizability, soft data, not as hard as numbers, few people studied, highly interpreted, and reliance on participant minimizes researcher’s expertise

Quantitative rigorous methods

quantitative design (experiment, correlation, survey) site, permissions, systematic sampling of adequate number of people that we study, recruitment, assignment of participants, types of data, instruments, data cleaning, descriptive, inferential statistics, statistical packages, validity and reliability

Qualitative rigorous methods

qualitative design (ethnography, grounded theory), site, permissions, purposeful sampling, number of people that we study recruitment, reciprocity, types of data, protocols, research questions, data preparation, data analysis steps, software, multiple coders, validity strategy and reflexivity

Convergent design

collect data, analyze it and at the same time, collect qualitative data and analyze it, then gather these two databases, merge the data and compare the results

Explanatory sequential design

Quantitative results are further explained by qualitative data and results (Start by collecting quantitative data, analyzing it, and from those results, build in a second qualitative phase of collecting and then analyzing qualitative data, and then reach interpretation) - interpret quantitative results using the qualitative data

Explanatory sequential design

Reversed to start with qualitative data collection we explore and come up with findings, which we use to then follow up with quantitative phase - qualitative exploration leading to a quantitative test

Key features of mixed methods

1. Collecting and analyzing qualitative and quantitative data (open and closed ended) in response to research questions

2. Using rigorous qualitative and quantitative methods

3. Combining or integrating quantitative and qualitative data using a specific type of mixed methods design

4. Framing the mixed methods design within a broader framework (ex. Experiment, theory, or philosophy)

Convergent (mixed methods)

merging two databases and then make an interpretation

• Intent: Combine two different databases for a more complete understanding of them

• Collect qualitative data and analyze it, and quantitative and analyze it, and then compare the two results

• Use parallel questions (asking about same thing in both)

Steps:

1. Collect the quantitative and qualitative data at roughly the same time and independently (single step approach)

2. Independently analyze the quantitative and qualitative data

3. Compare the results from the quantitative results and the qualitative results

4. Discuss a comparison of those results, and indicate areas of convergence or divergence between the quantitative and qualitative results

5. For areas of divergence, provide explanations for the divergence (like collect more data, reexamine the quantitative and qualitative results) or point out limitations in one of the databases or the other

Approaches to merging data:

1. Side-by-side comparison in discussion

2. Transforming data in results

3. Joint display in result

Side-by-side comparison in discussion

state quantitative and then qualitative results so you can see where they converge/diverge

Transforming data in results

take qualitative results and transform it into numbers, so then this quantitative is merged into other quantitative database

Joint display in result

Come up with a table with arranged columns of topics in the study, quantitative, qualitative and then compassion of results

Explanatory sequential (mixed methods)

sequentially connect the qualitative and quantitative database and have the second database help explain the first

• Intent: Use the qualitative data to help explain the quantitative results

Steps:

1. Collect the quantitative data (phase 1)

2. Analyze the quantitative data

3. Determine what quantitative results need to be further explained, and determine what participants can help with this explanation

4. Collect the qualitative data (phase 2)

5. Analyze the qualitative data

6. Explain how the qualitative data helps to explain the quantitative results

Exploratory sequential (mixed methods)

reverse of explanatory

• Collect qualitative data and analyze it, build something quantitatively, and test out this quantitative instrument/intervention (3 phases)

• Intent: Explore first before building a quantitative phase

Steps:

1. Collect the qualitative data

2. Analyze the qualitative data

3. Design the quantitative strand based on what is learned from the qualitative results

4. Use these results in various ways - develop a new instrument, modify an existing instrument, develop a typology or taxonomy

5. Collect the quantitative data

6. Analyze the quantitative data

7. Explain how quantitative results help to generalize the qualitative data, provide a new instrument, identify new variables, help to form a new typology, etc.

Codebook

• Document used in data processing and analysis that tells the location of different data items in a data file

  • Includes description of variables and attributes (values) the variables can take

  • Identifies the locations of data items and meaning of the codes used

  • Should contain:

    • 1. Variable name - each variable is identified by a abbreviated variable name

      • Ex. variable for measuring individuals’ political view might have POLVIEWS as its variable name

    • 2. Full definition of the variable (question from survey - how we measured it)

    • 3. Attributes of the variable

    • 4. Each attributes numerical code

Variable name, full definition of variable, attributes of variable, and each attributes numerical code

What codebook should contain

Experimental, non-experimental, and quasi-experimental

Data collection strategies

Univariate analysis

Analysis of a single variable, for purposes of description - describing a case in terms of a single variable, specifically, the distribution of attributes that it comprises

describe the units of analysis of a study and allows us to make descriptive inferences about the larger population

More concerned with descriptive statements

• Ex. frequency distribution, averages, measures of dispersion

• Ex. gender - number of me in sample/population, and the number of women in sample/population