Chapter 2 Flashcards
Research Methods
Hypothesis
The researcher’s best guess about what the results of a study will be.
Variable
An attribute or characteristic of people or things that can vary (take on different values).
Independent Variable
Variable manipulated by the researcher.
Dependent Variable
Variable measured or assessed in response to the IV.
Field Setting
Setting in which the phenomenon of interest naturally occurs.
Laboratory Setting
Artificial setting in which phenomena of interest do not normally occur.
Generalizability
The conclusions of a study can be extended to other groups of people, organizations, settings, or situations.
Control
Procedures that allow researchers to rule out explanations for results other than the hypothesis they wish to test.
Control Group
Collection of people who receive a condition or manipulation different from the one of interest.
Random
Process that eliminates systematic influences on how subjects are treated in a study.
Random Assignment
When we assign people to various treatment conditions or levels of an independent variable in a nonsystematic way.
Random Selection
We choose the subjects of our investigation by a nonsystematic method.
Sample
Group of individuals selected randomly from a population.
Confounding
When two or more variables are intertwined in such a way that conclusions cannot be drawn about either one.
Research Design
Basic structure of a scientific study.
Experiment
Design in which there are one or more independent variables and one or more dependent variables, as well as a random assignment of subjects.
Field Experiment
Experiment conducted within an organization rather than a laboratory.
Quasi-Experimental Design
One or more of the features of a true experiment have been compromised.
Survey Design
Series of questions chosen to study one or more variables of interest.
Quesstionaire
Set of assessments either on paper or electronically used in a survey design.
Cross-Sectional Design
All data were collected at a single point in time.
Longitudinal Design
Collects data at more than one point in time.
Response Rate
Percentage of those surveyed who agree to participate.
Experience Sampling
Take repeated measurements over short time intervals.
Observational Design
Researcher observes employees in their organizational settings.
Obtrusive Methods
Researcher might watch individual employees conducting their jobs for a period of time.
Unobtrusive Methods
Subjects of study might be aware that the researcher was present, bu they would not know that they were being studied.
Quantitative Methods
Researchers define variables, take quantitative measurements of those variables, and use statistical analysis to draw inferences.
Qualitative Methods
Observing behavior in an organization, and then recording those observations in a narrative form.
Measurement
Process of assigning numbers to characteristics of people or things.
Categorical Measurement
Values of the variable represent discrete categories and not the amount of the characteristic of interest.
Continuous Measurement
Used when the numbers represent the amount of the characteristic in question.
Classical Measurement Theory
Every observation of a variable can be divided into two components: true score and error.
True Score
To represent the variable of interest.
Error
Comprised of random influences on the observed score that are independent of the true score.
Reliability
Consistency of measurement across repeated observations of a variable for the same subject.
Internal Consistency Reliability
How well the multiple measures for the same subject agree.
Inter-Rater Reliability
Extent to which ratings by two or more raters are related to one another.
Test-Retest Reliability
Consistency of measurement when it is repeated over time.
Validity
The inferences that are made about what an observed score measures or represents.
Construct Validity
We are able to give an interpretation to scores on a measure.
Face Validity
A measure appears to assess what it was designed to assess.
Content Validity
A multiple item measure of a variable does an adequate job of covering the entire domain of the variable.
Criterion-Related Validity
Scores on a measure on interest relate to other measures that they should relate to in theory.
Descriptive Statistics
Provide ways of reducing large amounts of data to summary statistics, such as means or variances.
Arithmetic Mean
The sum of the observations divided by the number of observations.
Median
Middle number when the observations are rank ordered from lowest to highest.
Variance
A dispersion measure that is the arithmetic mean of the squared differences between each observation and the arithmetic mean of the same observations.
Standard Deviation
Square root of the variance.
Correlation
Statistic used to indicate the degree to which two continuous variables are related and the direction of the relation.
Pearson Product-Moment Correlation Coefficient
S
Regression Equation
Provides a mathematical formula that allows for the prediction of one variable from another.
Predictor
S
Criterion
S
Inferential Statistics
Allow us to draw conclusions that generalize from the subjects we have studies to all the people of interest by allowing us to make inferences based on probabilities.
Statistical Tests
Findings from a research study involving a small group of subjects are extended to other potential subjects.
Error Variance
Variability among subjects who receive the same treatment in an experiment.
Statistical Signifigance
The probability of finding the observed results by chance alone is less than .05.
Independent Group T-Test
Used to determine if two groups of subjects differ significantly on a dependent variable.
Analysis of Variance (ANOVA)
Used to determine if two or more groups of subjects differ significantly on a dependent variable.
Factorial ANOVA
Used to determine the significance of effects of two or more independent variables on a dependent variable.
T-Test For Correlation
Used to determine if the correlation between two variables is significantly greater than zero in absolute value.
Multiple Regression
Used to determine if two or more predictor variables can significantly predict a criterion variable.
Meta-Analysis
Quantitative way of combining the results of studies.
Mediator Variable
A variable that is part of the intervening process between two other variables.
Moderator Variable
Variable that affects the relationship between two other variables.
Informed Consent Form
States the purposes and risks involved in the research.
P-Hacking
Where a researcher might try a number of different ways to analyze data until something becomes statistically significant; or a researcher might conduct a large number of statistical tests and only report the small percentages that are statistically significant.