Term
| Concept/Construct/Variable |
|
Definition
- Concept: A term that experesses an abstract idea formed by generalizing from particulars and summarizing related observations. (e.g., "speech anxiety). Useful b/c they (A) simplify the research process by lumping items (people, objects, etc.) into general catergories; and (B) simplify communication when discussing them.
- Construct: A combination of concepts. An abstract idea that is usually broken down ito sub-dimensions represented by lower-level concepts. Usually cannot be observed directly. Usually designed for research purprose, so meaning relates only to context in which it is found.
- Variable: The empirical counterpart of a construct or concept, linking the empirical domain with the theoretical. Phenomena or eventsthat can be mrasuredor manipulated in research. Should have more than oone value, otherwise it is a (fixed) constant.
|
|
|
Term
Types of variable: Independent, dependent and control variables |
|
Definition
- Independent: Predictor variable. Answers question: "What do I change?"
- Dependent: The variable we attempt to explain. Their values vary depending on the values of the I.V. Answers question: "What do I observe?"
- Control variable: Variable that is not changed during trials (i.e. keeping the pressure constant throughout a lab experiement. Answers question: "What do I keep the same?"
|
|
|
Term
Types of variable: Discrete and continuous variables |
|
Definition
- Discrete variable: Includes only a finite set of values; cannot be divided into subparts. E.g., # of children in a family; gender; ethnicity; party affiliation.
- Continuous variable: Can take on any value; can be meaningfully broken into smaller subsections. E.g., height, average # of children in family, time spent watching TV
|
|
|
Term
Qualitative vs. Quantitative Research Characteristics and Strengths/Weaknesses |
|
Definition
1 Qualitative: Observing complex social phenomena: topics that (A) defy simple quantification, and (B) best understood in natural setting. PROs: Observe behavior in natural setting, can increase the depth of understanding. Allow researcher to pursue new areas of interest; follow-up questions can be developed as needed. CONs: Small sample size=limited generalizability. No statistical evidence=limited claims. Also, research's close involvement in phenomena can undermine data reliability. 2. Quantitative: Based on surveys and experiments. Numerical data. PROs: Greater precision in measuring variables and reporting results. Large sample size=large generalizability. CONs: Less flexibility...pre-structued standardized procedure. Artificiality. Limited in (A) measuring complex concepts and (B) handling a variety of concepts. |
|
|
Term
|
Definition
- Nominal measures... Names for characteristcs; do not exist along an explicit continuum; exhaustive; mutually exclusive (e.g., religious affiliation, place of birth, gender)
- Ordinal measures...Can be logically rank-ordered; no consistent distance between points of measuremen; e.g., "not very important," "fairly important," "very important," "extremely important."
- Interval measures...Consistent distance separating attribute, so we can say how much more of an attribute; logical distance can be expressed in mngful standard intervals; e.g., temperature: 90 deg. vs. 80 deg= 50 deg. vs. 40 deg.; zero-point in arbitrary
- Ratio measures..In additional to all the properties of nominal, ordinal and interval measures, ratio measures have a true zero-point; e.g., length of time, number of times; can state one ratio of one to another: X has twice as many affiliations as Y
|
|
|
