Midterm 1 Flashcards
Independent samples t-test
The scores in one sample do not tell us anything about the scores in the other sample (e.g., drawing names from two different hats)
Paired (dependent) samples t-test
Each score in one sample is connected to/paired with/dependent on a score in the other sample (e.g., sample 1: parents, sample 2: their infants; sample 1: pre-test, sample 2: post-test)
ANOVA
Testing hypotheses about multiple population means. Using independent samples (e.g., group A - pill A, group B - pill B, group C - pill C)
Sum of squares between
Sum of squares between group means and the grand mean. As the name suggests, it quantifies the variability between the groups of interest. Variability of group means around overall means.
Degrees of freedom
Number of values in the final calculations that are free to vary
df = n-1
Sum of square error
Sum of squares between the data and the group means. It quantifies the variability within the groups of interest.
Univariate
Univariate analysis is the simplest of the three analyses where the data you are analyzing is only one variable.
The most common univariate analysis is checking the central tendency (mean, median and mode), the range, the maximum and minimum values, and standard deviation of a variable.
multivariate analysis
looks at more than 2 variables and their relationship.
create a 3-d model to study the relationship
principles of science: determinism
consider how specific events or contexts predict certain behaviors, how behaviors might influence other behaviors, how cognitions can be influenced by contexts or behaviors, etc.
parsimony
Attempts to develop explanations that can be easily understood, but also minimize complexity where complication is unnecessary. In other words – don’t include unnecessary variables; don’t leave out necessary variables
Testability
Primary task of science, to try to falsify ideas, i.e. to stringently test our theories
Scientific tests are articulated in the form of hypotheses; and the form of a hypothesis should serve to suggest an appropriate statistical test
Replicability
The purpose in publishing an investigation’s results is not just to provide a context for replication and contribute to the scientific body of knowledge; it is to provide an opportunity for other interested scholars of science to examine an investigation’s procedures and confirm that they have no objections to the manner in which the evidence was collected and evaluated.
Empiricism
Scientists seek to identify ways to obtain recordable observations of events, objects, and/or concepts that comprise a theory under consideration; a researcher must express these “ways” as operational definitions
Instantiation
A deliberate process that involves specifying concrete instances of abstract concepts in order to help clarify their meaning
Crucial process for refining initial theoretical ideas
All theories must be subjected to instantiation process, either to make the definition of “fuzzy” concepts clearer and more communicable
E.g., Attitudes towards college influences whether or not a person goes to college” → high school seniors only, or juniors?
E.g., When assessing attitudes, should one make distinction between attitudes towards community colleges, 4-year colleges, and universities? What about trade schools?
proximal and distal
Proximal determinants are the more immediate determinants of behavior, and distal determinants are variables that influence behavior but do so through the more immediate determinants
etic and emic
The essence of emic approaches is to understand a culture in the way that members of that culture understand it, to learn the concepts they use, and to try to see the world as they do.
By contrast, the essence of etic approaches is to understand a culture in more abstract scientific terms that apply across different cultures and that can be used to make cross-cultural comparisons.
An emic construct is one that reflects the perceptions and understandings of the members of a culture. For example, the concept of “motherhood” would be defined emically by how members of a cultural group view that role.
Etic constructs, by contrast, focus is not on how a specific culture defines “motherhood” but rather on a conceptual definition of the concept of “motherhood” as used by the scientific community
Conceptual definition
Clear and concise definitions of one’s concepts
Process as “outlining constructs” or “stating what one means by the use of particular words”
Operational definition
In operationalizing “hunger”, psychologists have (1) asked people to respond to questionnaire items regarding their degree of perceived hunger; (2) deprived individuals of food for differing amounts of time so as to create more hunger in some than in others (e.g., people deprived for 24 hours must surely be hungrier than those deprived for only 2 hours); (3) measured the amount of food consumed from a standard portion given to each study participant (e.g., 2 pounds of spaghetti), under the assumption that the more a participant consumes (adjusted by body weight and metabolism), the hungrier he or she is; and (4) measured the amount of adversity the person will go through to obtain food.
All of the above seem to be reasonable procedures for measuring, that is, “operationalizing,” hunger. Unlike conceptual definitions, which often prove difficult to pin down, operational definitions are more concrete and thereby suggest a greater degree of precision and rigor.
Multidimensional constructs
Examples of multidimensional conceptualizations of constructs in the social sciences abound. For instance, theories of risk taking have delineated four types of risk taking propensities of individuals: (1) physical risk taking (putting oneself in harm’s way, physically), (2) social risk taking (taking risks in social relationships), (3) monetary risk taking (taking risks with money), and (4) moral risk taking (taking risks involving the breaking of rules or laws). These “components” of risk taking derive from the proposition that risk taking can occur in different settings and that risk tendencies can vary as a function of setting
shared vs surplus meanings
Given that each investigator makes his or her conceptual definition explicit (by providing clearly articulated and precisely defined propositions), specific points of agreement and disagreement can be identified. The points of agreement may then be assumed to represent the essential (i.e., agreed-upon) core of the concept. Researchers refer to this as shared meaning, which can be contrasted with the remainder, which is termed surplus meaning. In science, it is better to have concepts that are dominated by shared meaning and that do not have too much surplus meaning.
slope
in regression analysis, the slope represents the direction and strength of the relationship between a predictor and criterion variable. It indicates how much the criterion variable is expected to change as the predictor variable increases by one unit.
y-intercept
The y-intercept is the point where the regression line crosses the y-axis, representing the value of the criterion variable when all predictors are equal to zero.
Example: In predicting academic performance (criterion) based on study hours (predictor), the y-intercept would show the expected score when no time is spent studying.
predictor
Definition: A predictor variable (independent variable) is a variable that is used to predict or explain changes in the criterion variable. It is the “cause” in a non-experimental relationship.
Example: In predicting mental health (criterion) from social support (predictor), social support would be the predictor variable.
criterion
The criterion variable (dependent variable) is the outcome or effect that is predicted by the predictor variable in a non-experimental study.
Example: In a study examining stress (criterion) based on sleep quality (predictor), stress would be the criterion variable.
