Agus Wardhono
A. Introduction
What is research? According to Tuckman (1987, 1) “Research is a systematic attempt to provide answers to questions”. Such answers may be abstract and general as is often the case in basic research, or may be concrete as is often the case in demonstration or applied research.
Basic research is concerned with the relationship between two or more variables. It does not often provide immediately usable information for altering the environment. Its purpose is to develop a theory that indentifies all the relevant variables in a particular environment and hypothesizes about their relationship. Then, using the findings of basic research, it is possible to develop a product, such as: a curriculum, a teacher-training program, a textbook, or an audio visual aid.
A further step is to test the product, the province of applied research. In effect, applied research is a a test or tryout that includes systematic evaluation.
B. Research Problem
1. Some Critical Criteria in Choosing a Problem
a. Workability
1) Is study within the limits and range of your resource
and time?
2) Will you have access to the necessary samples in the number required
3) Is there reason to believe you can come up with an answer to the problems?
4) Is there required methodology manageable and understandable?
b. Critical Data
1) Is the problem of sufficient scope to fulfill the requirement that has motivated the study?
2) Are there enough variables?
3) Are there enough results to write a thesis?
c. Interest
1) Are you interested in the problem areas, specific problems, and potential solution?
2) Does it relate to your background?
3) Does it relate to your career?
4) Will you learn useful skills from pursuing it?
d. Theoretical Value
1) Does the problem fill a gap in the literature?
2) Will others recognize its importance?
3) Will it contribute to advancement in your field?
4) Will it be publishable?
e. Practical Value
1) Will the solution to the problem improve language learning practice?
2) Are the student likely to be interested in the results
3) Will language learning be changed by the out came?
4) Will your own language learning practices be likely to change as a result?
C. Variable
1. Definition
A variable is an attribute of a person or of an project which varies from person to person or from object to object.
Examples:
a. Variables of persons : age, sex, intelligence, personal pronunciation, linguistic repertoire, etc.
b. Variables of objects : size, stability, quantity, quality, plot, conflict, style, etc.
Phonological, morphological, syntactic and semantic components of language are variables, but each of them is a very broad variable. Any of the eight inflectional bound morphemes, such as: {-Z1} (= the English plural morpheme) or {-D1} (= the past tense English morpheme), is a variable. A child’s language acquisition is also a broad variable. In can be broken down into narrow ones, such as: lexical, phonological, morphological and syntactic acquisitions
D. Educational Research
Ary et al.(1992:33) classify educational research as fallows:
1. Experimental: One or more independent variables are manipulated in a controlled setting in order to determine the effect on the dependent variable(s).
Example:
a. The effects of students’ reading activities on their reading ability
b. The effect of Outline and Headings on Readers’ Recall of Text
2. Causal – comparative: This category is similar to experimental method, except the researcher cannot directly manipulate the independent variables, because the variables have occurred naturally.
Excamples:
a. The relationship of language students’ language backgrounds and their academic achievements.
b. The effects of language students’ learning facilities and their language talents on their academic achievements.
3. Descriptive: Its major purpose is to tell what. It is subdivided into: 1) survey, 2) developmental studies, 3) follow-up studies, 4) documentary analysis, 5) trend analysis, and 6) correlational studies.
Examples:
a. A survey of language teachers’ needs.
b. The development of a child’s language acquisition.
4. Qualitative research: the researcher observes persons or objects in their natural setting. Its major purpose is to understand the influence of the particular context on the ecvents. This methodology includes case studies and other naturalistic approaches.
Examples:
a. A participant observation study of a sixth-grade English classroom.
b. A qualitative study of language teachers’ beliefs and practice at elementary schools.
5. Historical: This category involves the collection of data from the past to understand past events. Its marjo purpose is to tell what was.
Examples:
a. A lexical study of the Indonesian language in 1945.
b. A study of word-classification based on the Traditional Grammar.
E. The Natural of Problem (Ary et al., 1992: 45)
1. Experimental research
In this kind of research the researcher addresses his questions concerning relationhips among variabeles. The researcher manipulates the independent variables (the cause) while controlling all other variables and observe any subsequence changes in the dependent variable (the effect).
2. Causal-comparative research.
It also seeks to determine the relationships among tow or more variables, but in this type of research manipulation of the independent is not possible. The independent variable has already occurred.
3. Descriptive research
It asks question about the nature, incidence, or distribution of educational variables and /or the relationships among those variables. No manipulation of variables is attempted-only description of variables and their relationships as they occur naturally.
F. Formulating Hypothesis
In educational research he next step after selecting problems is to state a hypothesis (Tackman, 1978: 25). A hypothesis, a ‘suggested answer to the problem, has the following characteristics:
1. It should conjecture upon a relationship between two or more variables
2. It should be stated clearly and unambiguously in the form of declarative sentence
3. It should be testable; that is, it should be possible to restate it in an operational form that can be evaluated based on data.
Examples:
a. I.Q. and reading skill are positively related
b. Directive language teachers are more effective than nondirective language teachers.
c. The ability to discriminate among parts of speech inceases with chronological age and educational level.
G. Two logical processes in developing a hypothesis
1. Induction process
It begins with data and observations (empirical events) and proceed toward hypothesis and theories. In this process the researcher starts with specific observations and combines them to produce a more general statement of relationship, namely hypothesis. Many researchers begin by searching the literature for relevant specific findings in order to induce a hypothesis, and other often run a series of exploratory studies before attempting to induce a hypothetical statement about the relationship between variables in question. The findings that obese people eat as much immediately after a meal as they do some hours after a meal, that they much less unappealing food than appealing food, that they eat more than they think it is dinner time even though little time had elapsed since their previous meal led Schacter (1968) to induce that for obese persons hunger is controlled externally rather internally as it is for persons of normal weight.
2. Deduction process
Deduction process begins with theories and general hypothesis and proceeds toward specific hypothesis. Deduction is a procees that goes from general to the specific. For example, it can be generally satated that the amount of time spent on writing a composition will be shorter as the person’s writing ability increases.
H. Constructing Alternative Hypothesis
From any problem statement, it is generally possible to derive more than one hypothesis. Look at the following example:
Problem: What is the combined effect of student personality and instructional procedure on the amount of language learning achieved?
There are three possible hypotheses:
1. More structured instructional procedures will provoke greater achievement among concrete students while more structured instructional approaches will provoke greater achievement among abstract students.
2. less structured instructional procedures will provoke greater achievement among concrete students while more structured instructional approaches will provoke greater achievement among abstract students
3. more structured and less structured instructional procedures will provoke equal achievement among abstract students as among concrete students.
Both induction and deduction are needed to chose among these possibilities (Tuckman,1978, 28)
I. Testing a Hypothesis.
The purpose of testing hypothesis is to determine the probability that it is supported by fact. However, because a hypothesis is a general expectation about the relationship between variables, there is extremely large number of instances under which it can be tasted, and it would be impractical to attempt to gain support in all these instances.
Since it is difficult to obtain unequivocal support for a hypothesis, the researcher instead attempt to test and disprove its negation. The negative or “no difference” version of a hypothesis is called a null hypothesis.
Examples:
a. Nondirective language teachers are more effective than directive language teachers.
b. Directive language teachers are more effective that nondirective language teachers.
c. Nondirective and directive language teachers are equally effective.
Hypothesis (c) is the null hypothesis or no differences hypothesis
Exercise:
1. Select a suitable research title in language teaching.
2. Formulate a hypothesis for that title
3. formulate a null hypothesis for that hypothesis
Action Research
( By Geoffrey E. Mills Second Editition,2003)
A. Definition
Action research is any systematic inquiry conducted by teacher researchers, principles, school counselors, or other stakeholders in the teacing learning environment to gather information about how their particular schools operate, how they teach, and how well their students learn. This information is gathered with the goals of gaining insight, developing effective practice, effective positive changes in the school environment, and improving student outcomes and the lives of those involved.
Action research engages teachers in a four-step process:
1. Identify an area of focus
2. Collect data
3. Analyze and interpret data
4. Develop an action plan.
B. Critical Prespective Components of Action research
1. Action research is participatory and democratic
2. Action research is socially responsive and takes place in context.
3. Action research helps teacher researchers examine the everyday, taken-for-grented ways in which they carry out professional practice.
4. Knowledge gained through action research can liberate students, teachers, and administrators and enhance learning, teaching, and policy making.
5. Teacher researchers have decision-making authority.
6. Teacher researchers are committed to continued professional development and school improvement.
7. Teacher researchers want to reflect on their practices.
8. Teacher researchers will use a systematic approach for reflecting on their practices.
9. Teacher researchers will choose an area of focus, determine data collection techniques, analyze and interpret data, and develop action plan (Mills, 2003: 8-9)
A. Definition
Action research is any systematic inquiry conducted by teacher researchers, principles, school counselors, or other stakeholders in the teacing learning environment to gather information about how their particular schools operate, how they teach, and how well their students learn. This information is gathered with the goals of gaining insight, developing effective practice, effective positive changes in the school environment, and improving student outcomes and the lives of those involved.
Action research engages teachers in a four-step process:
1. Identify an area of focus
2. Collect data
3. Analyze and interpret data
4. Develop an action plan.
B. Critical Prespective Components of Action research
1. Action research is participatory and democratic
2. Action research is socially responsive and takes place in context.
3. Action research helps teacher researchers examine the everyday, taken-for-grented ways in which they carry out professional practice.
4. Knowledge gained through action research can liberate students, teachers, and administrators and enhance learning, teaching, and policy making.
5. Teacher researchers have decision-making authority.
6. Teacher researchers are committed to continued professional development and school improvement.
7. Teacher researchers want to reflect on their practices.
8. Teacher researchers will use a systematic approach for reflecting on their practices.
9. Teacher researchers will choose an area of focus, determine data collection techniques, analyze and interpret data, and develop action plan (Mills, 2003: 8-9)
C. Justifying Action Research
1. Action Research is Persuasive and Authoritative
Research done by teachers for teachers involves collection of persuasive data. The data are persuasive because teachers are invested in the legitimacy of the data collection, that is, they have identified data sauces that provide persuasive insights into the impact of an imervention on student’s outcomes. Similarly, the findings of action research and the actions recommended by these findings are authoritative for teacher researchers. In doing action research, teacher researchers have develop solution for their own problems. Teachers – not outside experts – are the authorities on what works in their classroom.
2. Action Research is Relevant
Kennedy (1997) argues that one of the aims of research is to increase certainity by creating predictability within the classroom, because routines increase predictability and decrease anxiety for both teachers and students.
One of the outcomes of action research is that it satisfies the desire of all teachers to increase the predictability of what happens in their classroom.
3. Action Research allows Teachers Access to Research Findings
Kennedy believes that apparent lack of connection between research and practice is due to teachers’ poor access to research findings.
4. Action Research Challenge the Intractability of Reform of the Education system
Action research gives teacher researchers the opportunity to embrace a problem – solving philosophy and practice as an integral part of the culture of their school and their professional disposition, and to challenge the intracbility of educational reform.
5. Action Research is not a Fad
Mills (2003, 13-14) believes that action research is decidedly not a fad for one simple reason: Good teachers have always systematically looked at the effect of their teaching and students’ learning.
D. Steps in the Action Research Process
1. Identifying an area of focus
2. Collecting data
3. Analyzing and interpreting the data
4. Action planning
Action Research
By Michael J. Wallace 1998
By Michael J. Wallace 1998
- I. Introduction
A. Research, inquiry and professional development
Wallace (1991) proposed a model for a teacher education at the core of which is a process of reflection on professional action. He suggested a process (called the reflective cycle) which provided the momentum for increased professional competence. The process involved could be summarized by the following representation
( Wallace, 1998:13)
B. Research, Inquiry and the reflective cycle
The following figure shows that there is more than one way into the reflective cycle; this is in line with the fact that the process of professional development varies from one person to another. Teachers all have their own different kinds of professional experience, knowledge, background, and expertise. Strengths an dneeds may vary from one individual to another.
In that figure there is a fork after ‘Strategies for PD’. On the right-hand side are listed a few of the strategies which many of the teachers have used (e.g. attending conferences, informal discussion with colleagues, etc.). Such activities very often give them information or ideas which cause them to reflect on their practice, and perhaps change it.
C. Action research is problem- focused
Some of the teachers’ professional development is openended and relatively unfocused. They sometimes skim through professional journals just to see if there is anything interesting. We occasionally even enroll on training programs without a very clears idea what the criteria will be in terms of our professional development
Action research is different from this: it nearly arises from some problem or issue (Wallace, 1998: 15) arising out of their professional practice. It is therefore very problemfocused it its approach and very practical in its intended outcomes.
C. Action research and the reflective cycle
Action research involves the collection and analysis of data related to some aspect of teachers’ professional practice. This is done so that teachers can reflect on what they have discovered and apply it to their professional action. This is where it differs from other more traditional kinds of research, which are much more concerned withy what is universally true, or at least generalisable to other contexts.
This is a loop process, in the sense that the process can be repeated (reframing the problem, collecting fresh data, rethingking our analysis, etc.) until they have found a satisfactory solution.
D. The status of action research
It is likely that the attitude of the majority of teachers varies between indifference and downringht hostility. So it has to be made clear precisely what is being argued for here.
It has been assumed here that it is natural, and appropriate, for teachers to develop their expertise by reflecting, on their practice. But it is not being argued that every teacher can be, or should be, a ‘researcher’ in any traditional sense of that word.
Action research has been proposed as an ‘empowering’ procedure. But if becomes top-down requirements, it turns into the reverse. Therefore various conditions have been laid down from time to time. Some writers recommend that action research should be collaborative or team-based. It has also been suggested that the same stringent requiriements of validity, reliability and and verification for conventional research should also apply to action research.
If reflection is to be of any real value it must be valid (i.e. the data analysis must be relevant and appropriate). But since the position of action research in this discussion is primarlly an approach relaing to individual or small group professional development, the generality of the findings to other contexts will not mostly be important. Wht is important is theat the processes involved are helpful to the practicing teacher’s reflection, irrespective of wether they can be verified by someone else.
Action research overlaps the areas of professional development and conventional research, and for some teachers may will form a bridge between the two. But the aim is not to turn the teacher into a researcher, but to help the teacher to continue to develop as a teacher, using action research as a tool in this process.
E. Professional Problems and Alvailable Data
Problems areas:
1) Problems of classroom management
2) Problems of appropriate materials
3) Problems related to particular teaching areas(e.g. reading, oral skills)
4) Problems relating to student behavior, achievement, or motivation
5) Problems relating to management issues (e. g. time management, relationships with colleagues/higher management)
Number Problem Kind of data that might be available and how it might be collected
1.
2.
3.
II. Selecting and Developing Topic
A. Eight Important points.
Wallace, 1998: 21) states that there are eight important points
1. Purpose. Why are you engaging in this action research?
2. Topic. What are you going to investigate?
3. Focus. What are the precise questions?
4. Product. What is the likely outcome of the research?
5. Mode. How are you going to conduct the research?
6. Timing. Is there a deadline for its completion?
7. Resources. What are the human and material resources?
8. Refocusing. As you procced, will you have to rethink your
original questions?
1. Purpose
The topic you have chosen should relate in some direct way to your professional needs, otherwise it is or not action research.
2. Topic
The topic could cover:
a. The problems of classroom management
b. Problems of appropriate materials
c. Problems related to particural teaching areas
d. Problems related to student behavior, achievement, or motivation
e. Problems relating to personal management issues.
3. Focus
If you have to choose between importance and interest, you should go for interest. If you are doing action research for dissertation, this focus has to be expressed in the form of working title. Try to make the focus of your topic as specific as you can.
4. Product
What is the intended outcome of your research? Some possible answer are: article, thesis, dissertation.
5. Research Modes
How are you going to conduct the research? One of the purposes of studying action research is to widen your range of choices.
6. Timing
The availability of time in which to a research is a major issue, and it will influence the scope of what you can do. A further issue is whether or not you be working to a deadline.
7. Resources
Apart from your own energy, interest, and time, you may also need other resources to help you to do the research, material and people.
8. Refocusing
There should be a dynamic relationship between the problem and your conceptualization of that problem as the research proceeds. From time you should go back to your initial statement. Did you ask yourself the right questions? Should the problem be reframed?
III. Collecting
A. Categorizing Research action Research
Most action research techniques can be implemented in various ways
Cat/Tech Quan/ Qual Intro/ Emp Ind/ Coll Intro/ Comp Illumination
Heuristic
Verbal.
Reports Usually.
qualitative Introspect Individual Usually Complement Usually
Heuristic
Observat… Either Either Usually collabor Usually Introspective Usually
Heuristic
Interview. Usually
qualitative Introspective Either Either Usually
Illumination
Question Either Introspec. Either Either
Usually
Illumination
Case studies Usually qualitative Either Usually Individual Either Usually
Evaluation Usually quant Usually empirical Either Either Either
Trialing Usually quant Usually empirical Either Either Either
B. Reliability
Reliability means if the research procedures used by A are exactly fallowed by B, will th3e findings be the same each time? Or, is the research exactly replicable?
C. Validity
Validity means testing what you are supposed are supposed to test, and not something else.
D. Introspective and empirical data
Research techniques can also be classified into whether the data is generated by “looking inward” (introspective data), or by “looking outward: (empirical data)’
E. Individual and collaborative approaches
Individual approaches to action research are those which do not directly involve anyone else; obvious examples are writing field – notes and keeping a diary. The advantages of such approaches are that they tend to be more flexible, less professionally risky, and more easily implemented than others.
Collaborative approaches involve others; an example is sitting in on a colleague’s lesson to observe it, or tape – recording discussions about various aspects of teaching.
KEY RESEARCH TERMS
Access
In a field research context, the ability to make contact with potential informants.
Analytic induction
In qualitative research, developing a "working hypothesis" as a result of collecting and analyzing data.
Anonymity
Insuring that the names of research study participants are not disclosed.
Applied research
Research aimed as solving a specific, pragmatic problem--better understanding of the marketplace, determination of why a strategy or tactic failed, reduction of uncertainty in managerial decision making.
Assumption
A non-testable theoretical statement about the possible relationship between a presumed cause and effect.
Basic research
Research aimed at expanding the frontiers of knowledge rather than solving a specific pragmatic problem.
Bias
In sampling, an influence that systemically prevents obtaining a representative sample.
Bimodal distribution
A symmetrical frequency distribution with two predominant peaks.
Borderline case
A case used in qualitative conceptual analysis to help define the boundaries of the terms being defined.
Case
In qualitative research, a careful, in-depth study of an individual or situation.
Categorical variable
A variable whose values represent theoretically discrete categories that cannot be further deconstructed.
Census
Data obtained from every member of the population of interest.
Cluster sampling
Random samples of units organized on some prior basis.
Communism
Research data must be shared among community of researchers. One of Merton's four norms of scientific conduct.
Concept
An abstraction that describes a phenomenon, generally formed by generalization from particulars.
Confounding
Reflecting the fact that two or more variables that might have caused a particular effect were simultaneously present, so that we don't know to which to attribute the effect.
Construct
A concept of which we have a mental image but that has no direct physical referents.
Continuous variable
A variable whose values represent a theoretical continuum.
Convenience sampling
Samples obtained primarily because they are readily available.
Correlation
The relationship between two variables.
Deductive reasoning
"Reasoning down" from hypothesis to data.
Dependent variable
A variable presumed to be explained or caused by an independent variable.
Descriptive study
Research that addresses the question who, what, when,where, and how.
Dimension
A continuous variable that represent information about the differences among the categories of a categorical variable.
Disinterestedness
Disregarding one's own personal considerations when interpreting research data. One of Merton's four norms of scientific conduct.
Ethnography
Qualitative research method in which researcher attempts to understand research situation from inside research subjects' perspective.
Evaluation study
Research to determine the effectiveness and efficiency of specific programs.
Experiment
Research approach in which one variable is manipulated and the effect on another variable is observed.
Explanatory study
Research that explains relationships among phenomena with the goal of formulating accurate predictions.
Exploratory study
Preliminary research that attempts to clarify the exact nature of the problem to be studied.
External validity
The extent to which causal relationships measured in an experiment can be generalized to the environment outside the experiment.
Falsifiability
Sir Karl Popper's celebrated edict that a hypothesis can never be proven "true"... just "not falsified as yet".
Field experiment
Experiment conducted outside the laboratory environment.
Fieldwork
In qualitative research, the relationship established by the researcher and the subjects in the research situation.
Frequency distribution
Graphical depiction of data value distribution
Garbologist
Researcher who sorts through people's garbage to analyze household consumption patterns.
Gatekeeper
One who helps to channel the flow of research information.
Grounded theory approach
Research approach developed by Glaser and Strauss in which the researcher "grounds" self in empirical data before developing theoretical framework
Hypothesis
A testable theoretical statement of the relationship between two concepts or constructs.
Independent variable
A variable believed to be a cause of an effect.
Inductive reasoning
"Reasoning up" from data to hypothesis.
Informant
Person selected by qualitative researcher for willingness to share insights into the research situation in which both find themselves.
Informed consent Insuring that all potential participants in a research study should have full details about the research project and possible consequences before agreeing to take part in it.
Internal validity
The extent to which competing explanations for the research results obtained can be reasonably excluded from consideration.
Interval level of measurement
Use of a scale with equal intervals between units to describe data.
Invented case
A case that releases the restrictions of reality to see what kind of characteristics might ideally apply to a term being examined in qualitative conceptual analysis.
Invisible college
A group of researchers interested in the same problem area which communicate regularly with one another. Term popularized by Derek de Solla Price and Diana Crane.
Judgmental sampling
Non-random samples chosen according to some researcher-selected criterion of population representativeness.
Kurtosis
The degree of peakedness or flatness shown by a frequency distribution.
Levels of measurement
Standard rules for determining which statistical analysis techniques may be applied to various types of variables.
Linear relationship
A relationship between an independent and dependent variable best described by a straight line.
Manipulated variable
An independent variable that the researcher can manipulate (usually, vary across treatment groups in an experimental design.)
Mean
The sum of the values for all observations of a variable divided by the number of observations. A measure of central tendency.
Measured variable
An independent variable that can't be manipulated by researcher, only measured.
Measures of central tendency
Important descriptive statistics: mean, median, mode.
Measures of dispersion
Important descriptive statistics: range,semi-interquartile range, variance, and standard deviation.
Measurement
Process of assigning numbers or labels to things in accordance with specific rules to represent qualities or quantities of attributes.
Median
The observation below which 50 percent of the observed values of a variable fall. A measure of central tendency.
Method of authority
Acceptance of an idea because it appears to be accepted by experts.
Method of intuition
Acceptance of an idea because it appears to be self-evident.
Method of science
Acceptance of an idea for testing because it appears to be testable.
Method of tenacity
Acceptance of an idea because it appears to be an accepted idea.
Mode
The value of a variable which occurs most frequently. A measure of central tendency.
Model case
Clear and unquestioned example of a >construct in qualitative research conceptual analysis.
Multistage sampling
Sampling at different stages in a process.
Nominal level of measurement
Creation of mutually exclusive and exhaustive categories to describe data.
Non-probability sampling
Any sampling procedure that does not involve random sampling at some stage to insure a representative cross-section of the population of interest is obtained.
Normal distribution
A continuous distribution that is bell shaped and symmetrical around the mean: mean, mode, and median are equal. 68% of the observations fall within plus one or minus one standard deviation of the mean. Approximately 95% fall within plus or minus two standard deviations, and approximately 99.5% fall within plus or minus three standard deviations.
Norms of science
Four ideal standards for researcher behavior first described by Merton
Null hypothesis
The idea that the observed value is the result of randomness and chance error.
Ordinal level of measurement
Use of a ranking scale to describe data.
Organized skepticism
Responsibility of community of researchers to challenge research findings for validity. One of Merton's four norms of science.
Paradigm
Thomas Kuhn's description of how "normal science" is practiced until inability to address relevant new scientific issues with existing ideas forces a "paradigm shift" in "The Structure of Scientific Revolutions."
Parameter
A statistic descriptive of some characteristic of a population, such as the mean or standard deviation.
Population
The total group to which a researcher expects to be able to generalize and which is to be represented by the sample taken.
Probability sampling
Sampling procedures through which every element of the population has a known, non-zero chance of selection.
Purposive sampling
Samples chosen by intentionally seeking individuals or situations likely to provide greater understanding of a concept of research interest.
Qualitative research
Research that "qualifies" phenomena in words rather than numbers.
Quantitative research
Research that "quantifies" phenomena in numbers rather than words.
Quota sampling
Samples chosen by using frequency distribution of population characteristics to determine proportion of characteristic to be represented in sample.
Random sampling
Choosing samples by chance in such a way that every sample has an equal chance of being selected each time a sample is drawn. Used to minimize bias.
Range
Distance between smallest and largest observed values of a variable. A measure of dispersion.
Ratio scale
An interval scale with a true zero point which represents the complete lack of what is being measured.
Related case
A case that is almost the same as but not quite the same as the model case in qualitative conceptual analysis.
Reliability
Evidence that that a measurement is consistent upon repetition.
Research design
Plan to be followed to answer the research question; structure or framework to solve a specific problem.
Research front
Area in which majority of a science's advances are taking place. Term popularized by Derek de Solla Price in "Networks of Scientific Papers."
Sample
A means by which units are taken from a population in such a way as to represent the characteristics of interest in that population.
Sampling frame
A list of all the units in a population from which the sample is to be drawn.
Saturation
Describes a situation in qualitative research in which so many examples of a concept of interest have been gathered that nothing new is being learned by researcher.
Semi-interquartile range
Half the distance between the first quartile and the third quartile of a distribution. A measure of dispersion.
Skewness
Lack of symmetry in a frequency distribution.
Snowball sampling
Samples in which selection of additional respondents is based on referrals from the the initial respondents, continuing until no new respondents are identified.
Social sciences
The disciplines (e.g., psychology) concerned with the study of people
Spurious association
A variable or variables besides the independent variable being studied which may cause change in the dependent variable being studied.
Standard deviation
A measure of dispersion calculated by subtracting the mean of series from each value in a series, squaring each result, summing them, dividing the sum by the number of items minus one, and taking the square root of this value.
Stratified sampling
Dividing a population into groups (strata) on the basis of some variable such that the groups are more homogeneous on the variable of interest than in a simple random sample. Random samples are taken from all strata, usually in proportion to the size of that stratum in relation to the total sample.
Systematic sampling
Choosing every nth unit from the sampling frame.
Theory
Any potential explanation of the relationship between a presumed cause and effect. A testable theory is known as a hypothesis. A non-testable theory is known as an assumption.
Treatment
Any potential cause of an effect controlled by researcher.
Triangulation
Determining the consistency of evidence gathered from different sources of data and/or different research methods about a particular research question of interest.
Type one error
In hypothesis testing, incorrectly rejecting a true null hypothesis.
Type two error
In hypothesis testing, failing to reject the null hypothesis when it should be rejected.
Universalism
Research to be judged by quality of work alone. One of Merton's four scientific norms.
Validation study
Research to evaluate accuracy of prior explanatory studies.
Variance
The sum of the square deviations from the mean divided by the number of observations minus one.
