Chapter 2 - METHODS Flashcards
What are goals of science?
- Description (accurate portrayal/depiction of phenomenon)
- Explanation (gathering knowledge about “why” phenomenon exists it its causes)
- Prediction (anticipate an event prior to its occurrence)
- Control (manipulation of conditions to affect behavior)
What is science?
A process or method for generating a body of knowledge
(Represents a logic of inquiry - way of doing things to increase understanding of concepts, processes, & relationships)
Interrelated constructs(concepts), definitions, & propositions that present a systematic view of a phenomenon by specifying a relations among variables, with the purpose of explaining & predicting the phenomenon
What is “Theory”?
Statements about the supposed relationships between or among variables
What is hypothesis?
What are 5 things that make a good theory?
- Parsimonious: explains a lot, yet simple
- Precision: specific & accurate in its wording
- Testability: verifiable by experimentation/study
- useful: practical, helpful in describing/explaining/predicting important phenomena
- Generativity: stimulates additional research
What is induction?
Data —> Theory
What is deduction?
Theory —> Data
What is an independent variable & what are some other names we use for it?
Anything that is systematically manipulated
&
Predictor, precursor, & antecedent
What is a dependent variable & what are some other names we use for it?
What we’re measuring/assessing
&
Criteria, outcome, or consequence
What is an extraneous variable?
Any other variable that can contaminate results
What is validity?
Are we measuring what we’re supposed to be measuring?
What is the research process order?
Design the study Analyze data Collect data Formulate hypothesis Report findings
What is internal validity?
Extent to which causal inferences can be drawn about variables
(Relating our alternative explanations)
What is external validity?
Extent to which results generalize to other people, settings, time (student participants & “real world” applicability
Types of Research Designs: Overview
- Experimental Methods
- Lab Experiment
- Field & quasi-experiments
- observational methods
What are field experiments?
Random assignment & manipulation of IV in a naturally occurring, real-world setting
What are quasi-experiments?
Field experiment without random assignment and not always practical to randomly assign participants; use of intact groups
What is manipulation in experimental methods?
Systematic control of one or more independent variables
What is Random Assignment in experimental methods?
Each participant has an equally likely chance of being assigned to each condition
What are observational methods in research designs?
Also called, correlations designs, descriptive research
- do not involve random assignment or manipulation of IVs
- make use of available resources
- can draw conclusions about relationships but NOT casualty
- common in field settings
Examinations of a single individual, group, company, or society
—> interviews, historical analysis, research into the writings of policies of an individual/organization
—> main purpose: is to describe &/or explain
Case studies
What type of research relies on “secondary” data sets?
Archival research
What type of data is collected at one point in time from a single group of respondents?
Cross-sectional data
What type of data is collected over multiple time periods so that changes in attitudes & behaviors can be examined
Longitudinal data
What are self-administered questionnaires & where are they used?
Used in both lab & field settings
- Surveys that are completed by respondents in the absence of an investigator
- can be given to large groups at once
- easy to administer
- give respondents anonymity
What are the two approaches to using method of data collection?
- self-administered
- interviews
What are the two major concerns of accuracy of measurement?
- reliability
- validity
What is reliability?
Consistently/stability of a measure
What is test-retest reliability?
Give an example of it
The stability of a test over time
Also called coefficient of stability
Example: participants are given a test at Time 1 & then given the exact same test at Time 2
What is parallel forms reliability? Give an example of it
The two tests are measuring the same thing
Ex: Two different forms of a final, survey on paper & computer, test for disabled applicants
What is interrater reliability?
Extent to which multiple judges/raters agree on ratings of a particular thing or person
What is internal consistency reliability?
Extent to which individual test items seem to be measuring the same thing
What type of reliability is split the test in half to see if one half is equivalent to the other?
Split-half reliability
What type of reliability is examining the correlations among all test items to determine consistency.
Inter-item reliability (Cronbach’s coefficient alpha)?
What is the rule of thumb for reliability?
.70
Extent to which a test measures the underlying construct that it was intended to measure
Ex: self-esteem, intelligence, motivation, cognitive ability
Construct Validity
Degree to which a test/predictor covers a representative sample of the quality being assessed
Content Validity
Degree to which a test is a good predictor of attitudes, behavior, or performance
Criterion-related Validity
Extent to which test scores obtained at one point in time predict criteria obtained at some later time
Ex’s: GREs, GPAs, research experience, predicting later success in graduate school
Predictive Validity
How well a test predicts a criterion that is measured at the same time test is administered
Ex: want to see if newly developed selection tests predict performance of current employees
Concurrent Validity
Degree to which a measure of the construct is related to measures of other, similar constructs
Convergent Validity
Degree to which a measure of the construct is related to measures of other, dissimilar products
Divergent Validity
What are the two approaches to construct validity?
- content validity
- criterion-related Validity
What are the two approaches to criterion-related Validity?
- predictive validity
- concurrent validity
Summarized in a single # the values, characteristics, or scores describing a series of cases
Statistics
What are the measures of Central Tendency?
- Mode
- Median
- Mean
Score in the middle of a distribution
- extreme scores do not affect this
- mostly use this for skewed data
Median
Most frequent single score in a distribution
- useful with categorical data
Mode
Arithmetic average of a group of scores
- sensitive to extreme scores
Mean
Characterize a typical member of the group
Measures of Central Tendency
Inform us how closely scores are grouped around the measure of Central Tendency; “spread-outedness” of the data
Measures of Dispersion
What are the three measures of dispersion?
- range
- variance
- standard deviation
Spread of scores from the lowest to the highest
Range
Most useful measure of dispersion
- sum of squared differences between each score & the mean
Variance
Square root of the variance; retains original metric of scores
Standard deviation
This distribution is
- symmetrical
- bell shaped curve
- proportions will be same for (+) & (-) scores
Ex: job attitudes, intelligence, performance
Normal Distribution
What does correlation coefficient (r) indicate?
- indicates direction of the relationship
- indicates the strength/sign of the relationship between two variables
Magnitude —> 0 - 1.00
What is coefficient of determination (r2)?
Coefficient of determination (r2): percentage of variance accounted for by the predictor
Allows us to predict one variable from another
- how much variance in a criterion variable is accounted for by a predictor variable
(The higher the overlapping is, the better the predictor is)
Regression
- methodology used to conduct quantitative literature reviews
- used to combine the results of multiple studies to arrive at the best estimate of the true relationship
Meta-Analysis