Exam 1 Flashcards
inductive reasoning
moves from the particular to the general, from a set of specific observations to the discovery of a pattern that represents some degree of order among all the given events
deductive reasoning
moves from the general to the specific. it moves from a
1) pattern that might be logically or theoretically expected 2) to observations that determine whether the expected pattern actually occurs
theory
a set of statements that renders intelligible some phenomenon or process.
Wheel of Science diagram
Positivist
they seek to explain the cause-effect relationship: to predict and explain variables in a way that maximizes generalization to the largest possible class of phenomenon
positivist research is marked by certain features
1) the belief in an objective reality knowable only through empirical observation
2) the development of theories that enable prediction, explanation, and control
3) the search for generalized laws
4) observations in the form of quantitative data
Requirements of causal explanation
1) cause precede the effect in time
2) two variables be empirically related to each other
3) the observed empirical correlation between two variables cannot be explained in terms of some third variable related to both of them
What are the Sources of knowledge?
i. Tradition ii. Common sense iii. Authority iv. Experiential v. Intuition vi. Logic/Rationalism vii. Science
How do we use science as a source of knowledge?
This method of obtaining objective knowledge about the world through systemic observation
What are the three steps in science that we use through systemic observation?
a. Theory b. Data collection c. Data analysis
What are the errors in inquiry?
a. Inaccurate observations b. Overgeneralization i. The tendency to overgeneralize is greatest when the pressure to arrive at a general understanding is high c. Selective observation i. Overgeneralization may lead to selective observation ii. We all as individuals process things differently. d. Illogical reasoning i. Logical reasoning is a conscious activity for researchers and they have their colleagues to keep them honest
What is the meaning of research?
a. Prefix “re” and verb “search” i. “Re”=again, anew ii. “Search”= to examine closely and carefully to probe b. “What’s really real?” c. The foundations of social science are logic and observation
What are the characteristics of research?
a. Social research is exploratory, descriptive, and explanatory. b. Scientific theory involves the logical aspect of science. It provides systemic explanations. Data collection involves the observational aspect. c. Aggregates, not individuals d. Qualitative and Quantitative data e. Pure and applied research
Attributes of scientific research - Kerlinger (1968)
i. Systematic ii. Controlled iii. Empirical iv. Critical investigation of hypothetical propositions
Attributes of scientific research: Wimmer and Dominick (1994)
i. Public ii. Objective iii. Empirical iv. Systemic v. And cumulative vi. Predictive
What is gravity?
a. The phenomenon by which physical bodies appear to attract each other with force proportional to their masses. It is most commonly experienced as the agent that gives weight to objects with mass and causes them to fall to the ground when dropped.
Knowledge gap
a. “as the infusion of mass media information into a social system increases, segments of the population with higher socioeconomic status tend to acquire this information at a faster rate than the lower status segments, so that the gap in knowledge between these segments tends to increase rather than decrease” b. digital divide i. the digital divide refers to the gap in access to digital and information technology.
digital divide
the digital divide refers to the gap in access to digital and information technology.
Elements of social theory
a. Observation: how you view society b. Fact: something reliable c. Laws: d. Theory: explains how and why something happens e. Concepts: f. Variable:
Types of theories
a. Macrotheory: big, broad b. Microtheory: ex: looks at individual people and their health behavior c. Mesotheory: explain how organization function; how certain support groups function
Axioms or postulates:
what we hold to be true in the context of a theory
Propositions:
what a theory proposes
Hypothesis:
formal proposal
Theory of reasoned action suggests what?
that a person’s behavior is determined by his/her intention to perform the behavior and that this intuition is, in turn, a function of his/her attitude toward the behavior and his/her subjective norm
Deductive theory construction
a. Specify the topic b. Specify the range phenomenon your theory addresses c. Identify and specify your major concepts and variables d. Find out what is known about the relationships among those variables e. Reason logically from those propositions to the specific topic you are examining
Inductive theory construction
a. Observe aspects of social life and seek to discover patterns that may point to relatively universal principles i. Grounded theory ii. Field research
Milgram Study
a. Testing whether people would go to a certain point to obey even when it is hurting an individual b. People would shock the individual with shocks when they got a question wrong c. Paid the individual $50 for participating
Milgram Study: What was the unethical approach did they use?
Making the person being observed thinking they could kill the individual being shocked. - Deception
Milgram Study: How could they have altered the study to make it more ethical?
- They could have made the perceived threat much less. 2. Taught the participants of what a voltage is or let them feel a shock before they do it on someone else.
Tuskegee Syphilis clinical study
a. 1932-1972: penicillin b. sexual transmitted disease that killed people used on black men to kill off the population
Confidentiality:
assuring the person that we know their information but will not use it for any purpose
Criteria for Causality
g. Correlation: h. Time order: i. Nonspurious:
Correlation:
i. Information goes up, then knowledge also goes up ii. Inverse correlation: one variable goes up and the other goes down
Time order:
Independent variable must come first
Nonspurious:
It needs to be genuine
Necessary cause
i. Condition that must be present for effect to follow ii. Ex: must be enrolled in class to pass class
Sufficient cause
i. Condition that, if present, guarantees the effect in question ii. Ex: if you skip the exam (without university-sanctioned excuse), you will get a zero.
To test the hypothesis:
- Specify variables you think are related 2. Specify measurement of variables 3. Hypothesize correlation, strength of relationship, statistical significance 4. Specify tests for spuriousness
Unit of analysis
a. the what or whom being studied (most often individuals in social science research) i. Individuals (gender of gang members) – most common ii. Groups (male or female groups) iii. Organizations iv. Social interactions
Ecological fallacy
i. Something learned about in an ecological unit says something about the individuals making up that unit ii. Ex: Precents with more younger voters were most likely to vote for female candidates. 1. Fallacy: younger voters are most likely to vote for female candidates
Reductionism
i. To explain a particular phenomena in terms of limited and/or lower order concepts 1. Ex: using abilities of individual players to predict winners and losers in NBA play-offs.
Theory:
I. A systemic explanation for the observations that relate to a particular aspect of life. Theories can deal with causal explanation, functional explanation, or understanding.
Concepts
: an abstraction that refers to some feature or aspect of a communication phenomenon (ch. 6)
Variables (independent and dependent
a. ): logical groupings of attributes. i. Ex: The variable gender is made up of the attributes masculine and feminine
Operational definition
- the concrete and specific definition of something in term of the operations b which observations are to be categorized. The operational definition of “earning an A in this course” might be “correctly answering at least 90% of the final exam questions” (ch 6)
- measures of a study’s variables
Deductive Theory Construction (Poindexter & McCombs)
- Monitor environment 2. Identify problem/theory/issue 3. Specific survey topic in research question/hypothesis 4. Design study 5. Specify research method 6. Determine population 7. Establish budget and timeline 8. Determine who will conduct data collection
The links between theory and research
a. Deductive model – from theory to observational testing i. Consistent with Khun’s “normal science” b. Inductive model – from observation to understanding of patterns
No harm to the participants
a. Primum non nocere b. Can all risk be eliminated? c. Informed consent d. You should be able to quit at anytime during the study
Anonymity:
a. a condition in which the researcher does not know the identity of a given participant (ch. 5)
Debriefing:
a. a procedure in which study participants are informed after the study’s completion on the details of the study (ch. 5)
Three purpose of research:
- Exploration (something new) 2. Description (who, what, when, where, how) 3. Explanation (why)
Longitudinal study: and types
takes place over-time i. Trend study (by population) ii. Cohort study (by subpopulation) iii. Panel study (by unique people)
Panel study (by unique people
- It requires multiple assessments 2. The exact same amount of people assessed multiple times a. Ex: freshman can be surveyed all their years in college b. Since we are talking to the same people, we can figure out causation.
How to design a research project
a. Define the purpose of your project – exploratory, descriptive, or explanatory? b. Specify the meanings of each concept you want to study i. Panel study, trend study…etc. c. Select a research method d. Determine how you will measure the results e. Determine whom or what to study i. Population ii. How we are going to sample in that population iii. You need a well represented sample f. Collect empirical data i. Create a random sample of the adults in the US g. Process the data h. Analyze the data i. Report your findings
Elements of a research proposal
i. Problem or objective ii. Literature review iii. Subjects for study iv. Measurement v. Data collection methods vi. Analysis vii. Schedule viii. Budget
attribute
i. is a characteristic or quality of something (ex: female, old, student) 1. Responses to the question
variable
i. variable is a logical set of attributes (ex: gender, age) Questions
Levels of measurement
i. Nominal (e.g. gender, hair color, ethnicity) ii. Original (e.g., SES, conservatisms) iii. Interval (e.g. temperature (f), IQ score) iv. Ratio (e.g., temperature (kelvin), age, GPA)
deception in science
deceiving people is unethical, deception within social scientific research needs to be justified by compelling scientific or administrative concerns (pg. 89 ch. 5)
institutional review boards (IRB)
- chief responsibility of an IRB is to ensure that the risks faced by human participants in research are minimal.
- IRB are able to approve or refuse a study
- researchers are required to provide an “informed consent” tot he IRB describing the risks of the study and participants signing that they understand them.
conceptualization
- the refinement and specification of abstract concepts
- the process through which we specify what we will mean when we use particular terms
operationalization
is the development of specific research procedures (operations) that will result in empirical observations representing those concepts in the real world
conceptions
mental images of what a specific word means in your mind from what you were told it means and your experience
Concept
- The result of coming to an agreement about what the conceptions mean
indicators
an observation that we choose to consider as a reflection of a variable we wish to study. Thus, for example, hugging someone who is crying might be an indicator of social support (ch. 6)
dimension
a specifiable aspect or facet of a concept (ch. 6)
interchangeability of indicators
if several different indicators all represent, to some degree, the same concept, then all of them will behave the same way that the concept would be have if it were real and could be observed
nominal measures
- variables with attributes that have only characteristics of exhaustiveness and mutual exclusiveness are being measured at the nominal level
- nominal measures merely offer names or labels for characteristics
- ex: email-server, birth place, hair color, college major
ordinal level
- a level of measurement describing a variable with attributes you can rank-order along some dimension (ch 6)
- variables with attributes we can logically rank-order are being measured at the ordinal level
- ex: socio-economic status as composed of high, medium, and low
interval level
- a level of measurement describing a varibale whose attributes are rank-ordered and have equal distances between adjacent attributes.
- The Fahrenheit temperature scale is an example of this, since the distance between 17 and 18 is the same as that between 89 and 90. (ch. 6)
- the actual distance separating those attributes matter - such variables are being measured at the interval level
ratio level
- a level of measurement describing a variable the attributes of which have all the qualities of nominal, ordinal, and interval measures and are also based on a “true zero” point. Age is an example of a ratio measure (ch. 6)
Reliability
- measurement reliability is a matter of whether a particular technique, applied repeatedly to the same object, would yield the same results each time.
- consistence
Test-Retest method
- it appropriate make the same measurement more than once; if you don not expect the information to change, then you should expect the same response both times. Such consistency would demonstrate adequate test-retest reliability
Alternate-Form Method
- this technique requires a researcher to develop two different forms or versions of the same measure from the same pool of measurement items.
- the same, or similar, scores will be derived for subgroups measured with each form
Internal Consistency Method: split-half reliability
- a kind of internal consistency measurement of reliability in which the scores from two halves of a given measure are correlated for a group of participants
- for example: odd-numbered items and even-numbered items on a survey measure
Internal Consistency Method
based on the assumption that the various items in a given measure should correlate positively with one another. in other words they should perform consistently.
Internal Consistency Method: item-total reliability
- a kind of internal consistency measurement reliability in which the score on a given item is compared to the total score.
- if all of the items correlate positively with the total score, then the measure is said to have high item-toatl reliability
validity
- refers to the extent to which an empirical measure adequately reflects the real meaning of the concept under consideration
content validity
- refers to how well a measure covers the range of meanings, or the dimensions, included within the concept
- three types: face validity, expert panel validity, criterion validity
face validity
- a form of content validity in which one asks whether a given measure, on its face, appears to tap the full range or scope of a variable, as conceptualized by the researcher
expert panel validity
- a form of content validity in which a group of experts with knowledge of a given variable determine whether a given measure taps the full scope of the variable (ch. 6)
criterion validity
- a way in which measurement validity is determined
- the researcher compares a given measure to a criterion variable in which of the two ways:
- predictive validity (measure must demonstrate that it predicts future behavior) or
- concurrent validity (one measure of a given variable is compared to a second, established measure of the same variable) (ch. 6)
construct validity
- based on the logical relationships among variables
- convergent validity: a researcher demonstrates that the measure converges, or correlates positively, with measures of theoretically related variables
- discriminant construct validity: the measure diverge from, or correlates negatively with, measures of theoretically different variables
• According to Wimmer and Dominick (1994), scientific research can be characterized as which of the following?
• Systemic
• Cumulative
• Predictive
• Public
• All of the above
• Conceptualization can be characterized by which of the following?
- the mental process whereby fuzzy and imprecise notions are made more specific and precise.
- The process that connects theory to operational measurement.
- The process that connects theory to concepts.
- The process articulating the building blocks of theory.
- All of the above are true.
• From theory to testing
o The two xs present what?
o Conceptual level = x → y
o Operational level = x → y
• Independent variable
• Which of the following is most clearly a list of variables?
• Occupation, political party preference, birthrate
• Dr. Leonard did a study in the lab and he severely berated the subjects when they arrived b/c he wanted to examine the effect of berating on performance. Several of the subjects became very upset. Which ethical principle was violated?
• No harm to participants
• Researchers are in what process if they are trying to put concepts in a more functional form?
• Operationalization
• Theories, in contrast to paradigms are general frameworks or viewpoints.
false
• Which of the following is a specified, testable expectation about the empirical reality that follows from a more general proposition?
• Hypothesis
• Longitudinal studies may be either trend or cohort studies, but not panel studies.
false
• Gender has what level of measurement?
nominal
• Social science paradigms o According to the class lecture, the unit od analysis in social scienve research is most consistent with which level on the social ecological model?
• Individual
• We hypothesize that, among low-SES segments of the population, H1N1 will infect more low-news users than high-news users. What concepts will we need to operationalize?
• H1N1 infection
• Low news use
• High news use
• Low SES
• All of the above
• A and B represent which of the following in terms of modeling the link between theory and research?
o Induction/deduction
• A study in which we test three hypotheses that aim to answer “why” is representative of which type of research?
o Explanation
• In terms of the steps to design a research project, which sequencing is correct?
o Collect data/process data/ analyze data
• Dr. Smith observed people in her Sunday school for several months and then determined f there was a pattern in the different responses of men and women. Which of the following approaches is reflected?
• Inductive
• Which of the following would NOT be a suitable variable for a scale to measure the concept of “news use”?
• Hours spent watching TV per week
• As an analogy for measurement, this figure is indicative of which of the following>
• Reliable but not valid
• After noting that there are three aspects to the quality of a relationship, professor miller designed an instrument to measure the quality of the relationship. In looking at her questionnaire, she noticed that there no items tapping solidarity. Her measure lacks which of the following?
• Content validity
• It is always unethical to deceive subjects
false
• Which of the following are Kuhn’s three stages of science?
• Prescience, normal science, crisis
Stages of science (Thomas Kuhn)
a. Prescience:
b. Normal science
c. Crisis
Cross-sectional study
one point in time not across time like longitudinal study
a. To determine inferences of causation, we should use which type of survey?
panel
b. To get a snapshot (a quick look) of social processes, we should use which type of survey?
cross-sectional
c. To determine what percent of Americans prefer various presidential candidates over the months to come, we should use which type of study
i. Trend (over time) – up and down
d. To study the perceptions of TAMU freshmen over the past 30 years, we should use which type of survey?
cohort
ii. Scale
a type of composite measure composed of several items that have a logical or empirical structure among them.
Ordinal Level
1-5 how do you feel?
i. Index
a type of composite measure that summarizes and rank-orders several specific observation and represents some more general dimensions.
Ordinal level
yes/no
i. Bogardus Social Distance Scale
a measurement technique for determining the willingness of people to participate in social relations – of varing degrees…
- Do you feel comfortable living in the same…as a burglar.
a. Country - yes
b. State - yes
c. City - yes
d. Block - no
e. Neighborhood - no
ii. Thurstone Scales
- A type of composite measure constructed in accord with the weights assigned by “judges” to various indicators of some variables
a. Please consider a student’s GPA at TAMU. Please estimate how strong an indicator of a student;s GPA each item is on a scale from 1 – 10…
i. Time spent studying
ii. Class attendant
iii. Getting help during office hours
iv. Student IQ
v. Attendance of aggie football games
iii. Likert Scaling
i. : a type of composite measure, designed to improve the levels of measurement in social scientific research through the use of standardized response categorized in survey questionnaires
1. Likert-type items are those using such response categories as strongly agree, agree, disagree, and strongly disagree
iv. Semantic Scaling:
v. Semantic Differential: a questionnaire format in which the respondent is asked to rate something in terms of two, opposite adjectives
1. Please rate your last firday evening on the following scale…very much – 1, somewhat – 2, neither -3 ,
a. Enjoyable – unenjoyable
b. Expensive – inexpensive
c. Normal - abnormal
Guttman Scaling:
i. a type of composite measure used to summarize several discrete observations and to represent more general variables
1. Example 1:
a. I am willing to be near ice cream.
b. I am willing to smell ice cream.
2. Example 2:
a. Are willing to smell the liver?
b. Are you okay about touching the liver?
c. Are you okay about tasting the liver?
d. Are you okay about eating all of the liver?
I. Steps in scale validation
i. Conceptualize construct
ii. Operationalize
iii. Generate question items related to construct
iv. Administer question items
v. Validate scale
1. Factor analysis – do I keep all of my items?
2. Correlate with related construct
3. Predictive validity
vi. Reliability
a. Handling missing data
i. Analyze the missing data to interpret their meaning.
ii. Exclusion
iii. Treat as one of the available responses
iv. Assign middle value, or the mean value
v. Assign values to the proportion of variables scored
Research Process Map
