URBS 260 FINAL (2nd half)

data collected by or for researchers at an event that is observed or recorded

Written sources that make sense of summarized primary data

Observation: records, usually of events, situations or things, of what you have experienced with your own eyes
Participants: data gained ny experiences that can perhaps be seen as an intensified form of observation
Measurements: records of amounts or numbers
Interrogation: data gained by asking and probing

Academic journals, news broadcast, magazines, newspapers, documentaries, advertising, internet

the abstract statements that make claims about the world and how it works. Research problems are usually stated at a theoretical level

the building blocks of the theory which are usually abstract and cannot be directly measured

the ideas or mental representations of things

nominal: describes the concepts in rods, much like a dictionary definition

the phenomena which point to the existence of the concepts

Tell us that there may be a link and indicate how strong that link may be

Usually, one indicator for each concept is adequate
It is advantageous to use more than one indicator of a concept

Ensures the definition of the underlying concept is understood correctly

Gets access to a wider range of issues related to the concept, allows the researcher to make finer distinctions

Allows for factor analysis and cluster analysis

Helps to weed out response sets

Variables can be measured indicators by specific questions in a questionnaire

Independent variables are manipulated to see if they have an impact on dependent variables

the actual units or methods of measurements of the variables. These are data in their most concrete form

Coding unstructured data

Derive codes: labels or title given to the themes or categories

Assign numbers to the codes

Basic principles to observe
Categories must not overlap
Categories must be exhaustive
There must be clear rules for how codes are applied

Stability over time
Internal reliability- Are you doing the same thing every time
Inter-observer consistency

concerned with whether one is measuring what one wants to measure

Established if, at first glance, the measure appears to be valid

Established if the measure correlates with some criterion thought to be relevant to the concept

A lack of correlation brings some doubt onto the validity (correctness) of the original measure

established if the concepts relate to each other in a way that is consistent with the researcher’s theory

This is confirmed by seeing that the results match what would be predicted given the theory

Established if a measure of a concept correlates with a second measure of the concept that uses a different measurement technique

people and social institutions are treated as if they are part of the world of nature

The measurement process produces an artificial and false sense of precision and accuracy

The reliance on instruments and procedure produces a disjuncture between research and every day life

An analysis of relationships between variable ignores peoples everyday experiences and how they are defined and interpreted

Explanations for findings may not address the perceptions of the people to who the findings purportedly pertain

Quantitative researches tend to assume an objectivist ontology

Where each element has the same probability of being selected & each combination of elements has the same probability of being selected

Sampling ration: n/N (sample size:n, total population: N)

For every ith case in the sampling frame is selected

i= size of sampling interval
Eg: you want to select every 30th case, i=30

This type of sampling ensures that subgroups in the population are proportionally represented in the sample

Select a simple random sample or a systematic sample from each stratum

Used for large populations

It involves 2 or more stages
Selecting clusters (groups of elements)
Then selecting subunits within clusters

accidental (convenience)

quota- a specified number of cases in particular categories to match the proportion of cases in that category in the population

Theoretical- Is a useful method of getting information from a sample of the population that you think knows most about a subject. A study on homelesslness could concentrate on questioning people on the street. T

purposive- selects what they think is a ‘typical’ sample based on specialist knowledge

systematic matching- when 2 groups of very different size are compared by selecting a number from the larger group to match the number and characteristics of the smaller one

snowball- The researcher makes contact with some individuals, who in turn provide contacts for other participants

no sampling frame, involve time sampling, place sampling, behaviour sampling

definition matters

About 95% of all sample means lie within 1.96 standard errors of the mean

sampling- related error

data collection error

data processing error

As a sample size increases, sampling error tends to decrease

Common sample sizes: 100, 400, 900, 1600, 2500
Each size increase cuts the sampling error by ½, then ⅓, then ¼, and then ⅕ respectively
The biggest change occurs between 100 and 400

authenticity

credibility

representation

meaning

Low cost
Less-time consuming
Opportunity for longitudinal analysis
Subgroup analysis often possible
Opportunity for cross-cultural (international) analysis
More time for data analysis, since no time is spent gathering data
The data can be reanalyzed
Fulfills wider obligations of the social researcher

Lack of familiarity with the data
Complexity of the data
No control over data quality
Absence of key variables
The ecological fallacy may become part of the analysis- This occurs if the unit of analysis for a statement or hypothesis is not the same as that for the data

Advantages:
Allows for replies that the survey researcher might not have contemplated
tap the participants unprompted knowledge

Disadvantages:
More time consuming
Answers must be coded
Face inter-interviewver variability

Advantages:
Minimizes intra-interviewer variability
May make it easier to understand question because the answers are provided

Disadvantages
Loss of spontaneity and authenticity
differ in their interpretation of wording of fixed questions

data are gathered, and then themes or categories of behaviour are discerned

Eg an open questin on the legalization of marijuana might have codes ‘very hostile opposition’, ‘indifferent’, etc

Themes or categories of behaviour are decided upon before the data are gathered

Eg “what is your view on the legalization of marijuana? Are you strongly opposed, neither opposed or in favour, in favour or strongly in favour?

It involves making themes of categories of behaviour to form the basis for codes (labels or titles given to the themes or categories)

These themes are derived from the collected data

1. The categories must not overlap
2. All possibilities that exist in the data must be exhausted
3. There should be clear rules for what is included in categories and what types of answers relate to each categories

Personal factual questions
Factual questions about others
Factual questions about entity or event
Questions about belief
Questions about knowledge

presenting people with one or more scenarios and asking them how they would respond

Anchor the choices in a realistic situation

Creates distance between question and respondent

Used to test whether individual items or the instrument as a whole operates well

open questions to generate closed questions

interviewers with experience in administering the instrument

ensure that there is variability in the answers given

a formal list of questions that the interviewer must follow in detail

The questions must be asked in the order given

produce standardization

an interviewer is not consistent in asking questions or recording answer

lack of consistency in asking questions or recording answers between different interviewers

The researcher has a list of questions or topics to be covered
interviewee s are free to reply in any way
Can ask questions out of order
New questions may be devised and asked on the spot
useful when more than one interviewer or interviewee

The researcher uses only a brief set of points to introduce topics
The only thing defined is the broad topic of interest
Conversational

Introducing questions

Follow-up questions

Probing questions
Follow up what has been said through direct questioning.

Specifying questions
‘What did you do then?’

direct: ‘Do you find it easy to eep smiling when serving customers”
Best left until later in the interview,

indirect: (how do you feel about…?) and then “what do most people around here think of the ways that management treats its staff?”

Strengths
Cheaper and quicker to administer,
Reduced issue with confidentiality
Reduced bias arising from ‘interviewer effect’.

Weaknesses
Hard to sustain for long periods of time (20–25 minutes).
Personal interviews tend to be more effective with sensitive issues.

the observer takes a detached stance by not getting involved in the events and uses unobtrusive observation techniques and remains ‘invisible’ either in fact or in effect (ignored)
No bias

the researcher is mainly an interviewer doing some degree of observation but very little participation

the researcher engages fully in the life and activities of the observed, who are aware of their role

the researcher takes a full part in the social events but is not recognized as an observer by the observed- cohort observer
Full biases

the study of people and their culture in naturally occurring settings

Behaviour is observed in an unstructured way by carrying out in-depth discussions and interviews with the people studied

The process that aggregates data at the current or lower level of measurement in order to reduce the data amount and achieve satisfactory analytical quality
Age→ age cohorts

Sectorial aggregation
Grouping variables values based on the values of another variable

Spatial aggregation
Census tracts make up neighbourhood
Boroughs figured summed or averaged by census tracts

Allow for simultaneous analysis of 2 variables
Identify patterns of association
Normally used for nominal or ordinal data

the difference that exists between participants is being in one category or another
Categories can not be ordered by rank
ex gender

the categories of the variable can be rank ordered
Distance or amount of difference between categories may not be equal
Cannot do arithmetic or mathematical operations with the categories
Eg high enthusiasm, moderate enthusiasm and low

distance or amount of difference between categories is uniform

Can do arithmetic and mathematical operations with the categories

Ratio variable have a “0” start position

Analysis of 1 variable at a time
Combining categories makes the data more manageable
Diagrams can be used to illustrate frequency distributions
Use bar charts and pie charts for displaying a nominal or ordinal variable
Use histograms for interval/ ratio variable

Allow simultaneous analysis of 2 variables
Identify patterns of association
Normally used for nominal or ordinal data

Normally used with interval/ ratio
Values from 0 (indicates no relationship)
To +1 (perfect positive relationship)
Or -1 (indicates perfect negative relationship)

Shows correlation between pairs ordinal variables or with one ordinal and one interval/ ratio
Like Pearson’s R, values range from o to +-1

Shows correlation between pairs of ordinal variables
Like Pearson’s R, values range from o to +-1
Will predict a rank position from one variable to another

Shows the strength for the relationship between 2 nominal
Range 0 to 1
Nominal categories cannot be rank ordered
Usually reported with a contingency table and a chi-squared test

Eta, Kedalls’s tau-b, Spearman’s rho, Pearson’s R
Squaring sows how much the variation in 1 variable will explain variation in the other variable
Allows prediction of the 2nd variable based on the score from the 1st

Can a sample finding be sued to estimate a characteristic of the whole population
Stated as probability level
The probability that the results are not due to change
A null hypotheses tets the significance of the bivariate association

all of these prove relationship and not causality

rejecting a true null hypothesis
The results are a chance association

not rejecting a false null hypothesis

Used with contingency tables
Measure the likelihood that a relationship between the 2 variable exists in the population
Calculated by comparing the observed frequency in each cell with what would be expected by chance
The x^2 value is affected by the sample size

Analysis of variance (F statistic)
Total amount of variation in the dependent variable
Indicates there is a reduced likelihood of no relationship between the set of independent variables and the dependent variable
Reported as a statistical significant probability (p)

Analysis of variance (F statistic)
Total amount of variation in the dependent variable
there is a reduced likelihood of no relationship between the set of ind
Reported as a statistically significant probability (p)
the mean of the explained variation
in relation to means of the error variance

A general research question is devised.
Some data are gathered.
An hypothesis is proposed.

Difficulties with analytic induction
Because all cases must be explained, the hypotheses generated may be too broad to be useful.
no guidelines on how many cases must be reviewed

Open
Identifies initial concepts that will be categorized together later.

Axial
Data are reviewed for linkages and re-organized according to those connections.

Selective
Selection of the core category / categories
Validating the relationships
Identifying gaps that need to be filled in

Observed patterns are related to each other and a theory is developed to explain the connections in that setting.

Theory applied at a higher level
Requires data collection in different settings
Applicable to a variety of settings

Differences between concepts and categories may be vague.
Observation and data gathering may not be as 'theory neutral' as claimed
Practical difficulties, e.g., time constraints on transcription
It may not result in theory

Ethnography and participant observation
Qualitative interviewing
Focus groups
Discourse and conversation analysis
Analysis of texts and documents

Acts
Activities
Meanings
Participation
Relationships
Settings

Risk of losing the context
By selecting parts of the text, qualitative coding weakens the connection between description and social setting in which the events occur

Fragmentation of data
Breaking the data into codes and small chunks of text results in a loss of narrative

Will sort data once the codes are defined
They don’t interpret the data

Advantages of using software:
new visual ways of looking at data

Criticisms of using software:
quantify coded text and negates the qualitative, thematic interpretation of meaning important in qualitative analysis
It fragments textual material into very small pieces of data where the natural flow of the story is broken

Researching the stories people tell to understand their life and the world

Criticism
Stories may be accepted at face value by the researcher.

1. Thematic
2. Structural
3. Interactional- Examines the dialogue (construction) between the teller and the listener
4. Performance

The examination and coding of docs and texts: printed visual, aural or virtual
Words, including the pairing of certain words
Subjects and themes
Value positions
What is the presentation front

the ‘science of sign’

expose hidden meanings in text

Signifier- Thing that indicates an underlying meaning

Signified- The meaning that is pointed to

Denotative meaning- The obvious meaning of a signifier

Connotative meaning- Secondary ,eaning that arises with the denotative meaning

Polysemy- Recognizes that signs ma be interpreted differently

The meaning of a text involve the author’s circumstances and the context in which the text was constructed
Eg history- the perspective of winners vs losers in war

Examines how social order is created through convo

Social order is an achievement not an objective pre-existing phenomenon we uncover

Focuses on reflectivity (responds to context)

Data from naturally occurring situations (naturalist)

Characteristics of how talk is organized:
Adjacency pairs- How the talk moves between praties (eg question-answer)
Preference organization- Preferred responses and non-preferred responses
Cultural contexts are not permitted- Focus is limited to words themselves

Includes elements of conversation analysis
Broader and more flexible
Cover communication other than talk
Tends toward a constructionist orientation
Discourse is a topic itself
Language is constructive
Discourse is a form of action
Discourse is rhetorically organized

Advantages
In its quantitative form it is very transparent, and therefore easily replicated
longitudinal analysis
unintrusive

Disadvantages
Limitations due to the texts analyzed
It is difficult to answer ‘why?’ questions

Interest in the uses of meaning, eg those who study attitudes using surveys

Qualitative claim access to participants’ world view
Rarely proved through respondent validation

Quantitative methods (such as quantitative approaches to content analysis) can be used to establish how people create their sense of reality
Eg one could study the content of TV shows quantitatively to illustrate one way in which gender socialization takes places

Epistemological and ontological considerations
People using a particular research strategy do not always share the same epistemological and ontological assumptons

Triangulation:
The use of quantitative research to collaborate qualitative findings and vice versa
2 methods to come to a conclusion

Facilitation
The use of one research strategy to assist with research that uses a different strategy

Complementarity
Using 2 or more approaches where a single approach would not be sufficient

Becoming more common
Multiple methods likely take more time and money
Different skills and training required