GLOSSARY
Action research: A method of initiating change processes, with an incremental focu:
rowing the gap between the desired and actual states.
Alternate hypothesis: An educated conjecture that sets the parameters ome exnects to fin
mate hypothesis:
Ambiguous question
respondents in different wavs.
Analvtiea! studv: A study thet gies to
dependent variable of interest to the researcher.
ANOVA: Stands for Analvsis of Variance. which tests for significant mean differences in
‘Variables among multinle groups.
Applied research: Research conducted in-a partieular setting »
solving an existing problem in the situation.
Area sampling: Cluster ssmpling within a specified area or region: a probability sampling
design
Attitudinal factors: People's feelings, dispositions, and reactions toward the organization and
factors in the work environment such as the work itself, co-workers, or supervision
research: Research conducted 1 generate knowledge and understanding of phenomena
setting) that adds to the existing body of knowledge {about organizations and
management theory).
Behavioral factors: Actual behavior of employees on the job, such as being late, working hard.
remaining absent. or quitting work.
Bins: Any error that creeps into the data. Biases can be introduced by the researcher, the
respondent. the measuring instrument. the sample. and so on.
Bibliography: A listing of books, articles, and other relevant materials, alphabetized according
to the last name of the authors. referencing the titles of their works. and indicating where
they can be located
Broad problem grea; A situation where one senses a
Solving. even though the specific problem is.
specific objective of
possible nerd for research and problem
lea
between two or
more dependent variables and several independent variables.
Case studv: The documented history of noteworthy events that have taken place in a given
institution.
Categorization: The process of onganizing, arranging and classifying coding units (in
qualitative data analysis)
Category reliability: The extent io which judges are able 10 use category deflnitions 10 classify
qualitative data.
Category scale:
Causal analysis
‘more variables.
Causal study: A research study conducted to establish cause-and-effect relationships among
variables.
Chi-square test: A nonparametric test that establishes the independence or otherawise between
‘two nominal variables
ek a single response.Cluster sampling: A z. A piobabllny sampling design in which the sainple comprises groups or
chinks of elements with intragroup heterogeneity and intergroup homogeneity.
Coding: The analytic process through which the qualitative data that you have gathered are
reduced, rearranged, and integrated to form theory (compare Daia coding)
Comparative seale: A scale that provides a benchmark or point of reference t
‘opinions, and the like.
Comparative study: A study conducted by collecting dat from several settings or
assess arrinides.
Complex probability sampling: Several probability sampling designs (such as systematic and
fied random), which offer an alternative to the cumbersome, simple random sampling
ted! telephone interviews (CAT): Interviews in which questions are prompted
‘onto a PC monitor that is networked into the telephone system, to which respondents
provide their answers.
Conceptual analysis: Establishes the existence
themes, or characters) in a text.
s tO critetonerelated validity, which is established at the same time
cence and frequency of concepts (such as words,
Confidence: The probability estimate of how
‘usual accepted level of confidence in 5
Conjoint analvsis: A used
importance respondents attach to attributes and the utilities they attach to specific levels of
artributes.
Consensus scale: A scale developed through consensus or the unanimous agreement of a pane!
of judges as to the items that measure a concept,
Constant sum rating scale: le where the respondents dis
+
ich reliance can be placed on 1
findings: the
thieores around which the test was designed,
Content analy: ational research method ty
symbolic contents of of recorded communicati
Content validity; Establishes the representatives sampling of 2 whole set of items that measures
a coficept and reflects how well the dimensions and elements thereof are deleinated.
Contextual factors: Factors relating to the organization under study such as the backeround and
environment of the organization including its origin and purpose, size, resources, financial
standing, and and he lil
Control group: The group that is not exposed to any treatment in an experiment
Conteniled variable: Any exogenous or extraneous variable that could contaminate the cause
andveffect relationship, but the effect
either matching or randomization3
instruments measuring the same concept, or by measuring the concept by two different
methods, are highly correlated.
Correlational analvsi
Correlational Study:
Criterion-related validity: That which is the
individuals on a criterion thar it is expected to predict.
Criterion variable: The variable of primary interest to the study, also known as the dependent
variable,
Cross-cultural research: Studies done across two or more cultures to understand, desierbe.
‘analyze, or predict phenomena
Cross-sectional study: A research study for which data are gathered nce (stretched thou:
‘itmay be over a period of days, weeks, or months) to answer the research question.
Bata coding: In quantitative research data coding involves assigning a number to the
‘participants’ responses so they can be entered into a database.
Data display: Taking the reduced qualitative dam and displaying them in an organized.
condensed manner.
Data mining: Helps to trace pattems and relationships in the data stoved in the data warehouse
Data reduction: Breaking down data into manageable pieces,
Data transformation: The process of changing the original numerical repres
Quantitative v
Data warehouse
Deductive reasoning: The colleen ofa general theory £ a specific case,
i i A. forecasting method that uses 2 cautiously selected panel of expetis to a
Dependent variabls
Descriptive statistics: Statistics such as frequencies,
which provide descriptive information about
Descriptive study: A research study that describes the variables
researcher.
Dichotomous scale: Scale
aspects of a concept.
Dircetional hypothesis: An educated conjecture as to the direction of the relationship, or
differences among variables, which could be positive or negative, or more or less
respectively
Discriminant analysis:
mean, and the standard deviation
a situation of interest to the
ed 10 elicit a
Yes’No response, or an answer to nwo different
A statistical technique that help to identify the independent variables
that discriminate a sealed dependent variable of interest
Discriminant validitv: That which is established when two variables are theorized to by
uncorrelated, and the scores obtained by measuring them are indeed empirically found be
$0.Disproportionate stratified random Jampling A probability sampling design that involves a
procedure in which the number of sample subjects chosen from various strata is not directly
proportionate 1
Double-barreled question: Refers to the improper framing of a question that should be posed
a5 WO Of More separate questions, so that the respondent can give clear and unambiguous
answers.
Double-blind studv: A study where neither the experimenter nor the subjects are aware as tov
who is given the real treatment and who the placebo
Double sampling: A probability sampling design that involves the process of collecting
"information, and later us mg a subsample ofthe primary samo for more infomation
Dummy variabl hare coded 0 or 1
sample subjects for a research study conducted over an extended period of rime.
Editing data: The process of going over the data and ensuring that they are complete and
‘acceptable for data analysis
Efficiency in sampling: Atained when the sampling design chosen either results in a cost
reduction to the researcher or offers a greater degree of accuracy in terms of the sample
size.
Electronic questionnaire: Online questionnaire administered when a
‘lp fe computer networks
Element: A single member of the
Ethies:
microcomputer is hooked
ie populate
d societal norms of behavior.
‘between two variables in some way, and needs 10 be controtled.
Experimental design: A study design in which the researcher might create an artificial setting.
‘control some varishles, and manipulate the indenendent variable to establish cause-and-
effect relationships.
Experimental group: The group exposed to a treatment in an. ec ee cee
Exploratory study: A research study w
the subject un
ct relationships
(in. contrast to establishing cause-and-effect relationships by many variables in a Jab or a
Geld setting),
External consultants: Research experts
‘problems to find solutions
External validity: The extent of generalizability of the resu
A particular representation of the graphic scale
smiling to sad.
Face-to-face interview: Information gathering 1. hen bath the interviewer and interviewee meet
“reads supposed t0
Factorial validity: That which indicates, through the use of factor analytic techniques, whether
atest Is a pure measure of some specific factor or diField experiment: An experiment done to detect cause-and-effect relationship in the natural
environment in which events normally occur.
Field study:
interference
Fixed rating scale: See Constant sum
Focus group: A group consisting of eight to ten members rar
indicators
Frequencies: The number of times various subcategories of a phenomenon occur, from which
the percentage and cumulative percentage of anv occurrence can be caleulaied.
Fundamental research: See Basic research.
Funneling technique: The questioning iechnique that consists of initially asking general and
broad questions. and gradually narrowing the foeus thereafter to more specific timmes.
Generalizabilitv: The applicability of research findings in one setting to others.
Goodness of measures: Atrests to the reliability and validity of measures.
Graphic rating seale: A scale that graphically iMlustrates the responses that can be provided,
rather than specifying any discrete response categories
Grounded theory: A systematic set of procedures to develop an inductively derived theory
fromthe data.
Group videoconferencing: Video transmittal technology that enables r
‘to participate in 2 conference using video cameras and monitors.
History effects: A threat to the intemal validity of the experimental results. when events
unexpectedly oceur while the experiment is in progress and contaminate the cause-and~
effect reladonship.
Hypothesis: A tentative
empirical data,
Hypothesis testing: of testing if the if:
framework hold true when subjected to Sgorous
Hypotheticn-deductive method pf research: A seven-step process of identifving 2 broad
problem grea, defining the problem statement, developing, hypotheses, determining
measures. data collection, data analvsis, and the interpretation of data.
Independent samples test: Test shat is done to sez if there are significant differences in the
means for two groups in the variable of
jote groups of people
statement that predicts what you expect to find in
generated from the theoretical
‘accounts for (or explains) its variance
Inductive reasoning: A process where we
‘at general conclusions.
Inferential statistics: Scatistics that help 10 establish relationships among variables and draw
conclusions therefrom.
Inkblot tests: A motivational research technique that uses colored panems of inkblots to be
interpreted by the subject
Instrumentation effects: The ity in experimental designs caused
changes in the measuring instrument berween the pretest and the positesem consistency reliabilit of the consistency of
measure to establish that they hang together as a set.
Anterjudge reliability; The degree of consistency be:
qualitative) data.
Internal consistency: Homogeneity of the jtems in the measur
Internal consultants: Research &
solutions go problems.
Internal validity of vat nats :
effect relationship found
Interrater reliability; The consist
‘phenomenon or interpret
intervening variable: A.
helps in conceptualizing and explaining the influence of the coe ‘variable on the
dependent variable.
Interviewing: A data collection method in which the researcher asks for information verbally
Intranet: the
itemized rating seale: A scale that offers several categories of rn of w
respondent picks 1!
dudgment sampling:
fh the
ampling design in which
nf ¢ sample subject
dividual's ability to provide
ype of special information
needed by the researcher.
Lab experiment: An experimental design set up in an artificially contrived senting w
controls and manipulations are introduced to establish cause-and-effect relationship among
2 researcher.
warlables of interest,
Leading questions: pueshutte phrased | in such a mi
answers that cl
Likert scale: An interval scale that
‘40 lead the respondent jo give the
weed Ean review of the published work from
fi the researcher.
Literature review: Th
secondary
Literature survey: Se:
Logistic regressio
nonmetric, dichotomous varia
al study; A research study for which data are gathered at several points in time to
answer a research question.
Manipulation: How the researcher exposes the subjects to the independent variable to
deter ct relationships in experimental designs.
MANOVA: A statistical technique that is similar to ANOVA, with the difference that ANOVA
tests ihe mean differences of more than two groups on one dependent variable, wheress
MANOVA ‘tests mean differences among groups across several dependent variables
simultaneously, by using sums of squares and cross-product matrices.
Lon:Matehing: A. id of comtrofling
deliberately spreadin; equally aero:
fo nship
Maturation effects: A threat validity that is a function of the biological,
psychological, and other processes taking place in the respondents as a result of the passage
fume.
MeNemar's test: A nonparametric method used on nominal data, |
the difference between wo dependent samples when
not to
ssesses the significance of
dichowomo:
Measure of central tendency; Descriptive statistics of a data set
mode
Measure of dispersion: The variability in a set
variance, standard deviation, and the interquartile range
helps in conceptualiz
dependent variable.
Mode: The most frequently occurring numbei
Moderating variable: A variable on which the relationship hetween two other variables
the moderating variable is present, the theorized relationship between
contingent. That is,
two
the
Mortality
: The loss of research subje s during the course
the catsse-andaeffect relationship.
Motivational research: A particu
i experiment. which confounds
data-gathering technique directed toward surfacing
information, ideas, and thoughts that are not either easily verbalized, or remain at the
jevel in the respondents.
multiple regression model are hi, ighly correlated.
Multiple regression analvsis: A statistical technique to predict the variance in
variable by regress the independent variables against i.
Multistage cluster sampling: A probability sampling design th:
ithe dependent
at is stratified sampling of
Narrative analysis: A qualitative approach that aims
about ourse
es and their implications for our lives
Nominal scale; A scale thet categorizes individuals or objects into mutually exclusive and
collectively exhaustive groups, and offers basic, categorical information on the variable of
interest
Sesto: ed setting: Research
d scrutinise the st
Nonparticipant-observer:
integral part of the system.Nonprobability sampling: A sampling design in which nents in the population do not
have a known or predetermined chance of being selected as sample subjects
Non-response error: Exists to the extent that those who did respond to your survey are
Nuisance variable: ntaminates the lationship.
Null hypothesis: The conjecture that postulates no differences or no relationship between or
among variables.
Numerical seale:
the scale.
to subjective
Observational survev: Collection of data by observing people or events in the work
‘environment and recording the information
One sample f-test: A test that is used to test the hypothesis that the mean of the population from
is equal to a comparison standard.
Qne-shot studv: See Cro’
Open-ended questions: Questions that the respondent can answer in 3 free-flowing format
estricting the range of choices to a set of specific alternatives suggested by tilt
researcher.
Operational definition: Definition of a et in measurable terms by reducing: it from
level of abstraction through the delineation of its dimensions and elements.
Operations research: A quantitative approach taken to analyze and solve problems of
complexity.
Ordinal scal not only categorizes the qualizative di:
interest, but also allows for the rink-orderine of these categories
Paired comparisons: Respondents choose benveen nwo objects
repeated small number of object
constr
la
ameaningful way.
a tinge, with the process
the same group before and after a
meatment.
Panel studies; Studies conducted over a period of
changes made in a situation, using a panel cis as the sample base.
Parallel-form reliability: Thai fom of rellab is established when responses fo two
‘comparable seis of measures iapping the same construct are highly correlated
Parametric statistics: Statistics used 10 test hypotheses when the population from »
sample is be tributed,
Parsimonv: Efficient expl
the use of a small
Participant-observe ho collects observational data by becoming a member of
the system
Population: The enti events, or things that the researcher desires 10
investigate.
io determine the effects of certain
dependemt variable of interest through
drawn.
Posttest: AA test given to the subjects 10 measure the dependent variable after exposing them toa
reammient,Precision: The degree of closeness of 1 @ population
parameters, determined by the extent of the variability of the sampling distribution of the
sample mean.
Predictive study: A study that
8 particular situation
Predictive yalidity: The ability
iterion predicted for th
Predictor variable: See Independent variable.
given to subjects to measure
dependem variable heft em 10 a
treatment.
Pretesting survey question:
‘Test of the understandability and appropriateness of rit, questions
planned to be included in a regular survey, using 2 small number of respondents:
Primary data: Data collected first-hand for subsequent analysis to find solutions 10
researched
Probability sampling: The sampling design in which the elements of the population have some
known chanee or probability of being selected as samnle subjects
Problem definition: A precise, succinct statement of the question or issue that
investigated
Problem statement: Sec Problem definition.
Projective methods: Ways of eliciting responses difficult to obtain, othenwise than through
such means as word association, sentence completion, and thematic anperception tests
problem
to be
Proportionate stratified random sampling: A probability sampling design in which the
number of sample subjects drawn from each stratum is proportionate to the:
elements in the respective strata.
Pure researc
Purpasivencss in research: The situation in which research is focused on solving a well-
identified and defined problem, father than aimlessly looking for answers to vague
Qualitative data: Deis those are not immediately quantifiable unless they are coded and
‘categorized in some way.
Qualitative studv: Research involving analysis
‘ature and not readily quantifiable,
Questionnaire: A preformulsed wrinen set of questions 1o which the
answers, ually in rather closely delineated alternatives.
which a predetermined proportion of people
are descriptive in
respondent records
Randomization: The process of common the nuisance variables by randomly assigning
members among the various exnerimental and control groups. so that the confoundin;
variables are all groups
dicated by the difference in
he two extreme values 4Ratio scale: A scale an absolute
magnitude. but also the proportion. of the differences.
Recall-dependent question; Question that elicits from the respondents it
involves zecall of ces from the past thal may be hazy in their memory.
Reflective scale: Each item
underiving ¢: ct of interes!
Regression analysis: Used
fare} hypo
Relational analysis; Builds on conceptual anal by examining
concepts in a text
test to the consistency and.
The repeatability of similar results when identical research is conducted at
different times or in different organizational settings
Research: An organized. svstematic. critical. scientific inquiry or investigation into = specific
problem, undertaken with the objective of finding answers or solutions thereto:
Research proposal: A document that sets out che purpose of the study and the research design
details of the investigation to be carried out by the researcher.
Researcher interference: The extent
with the normal course of work at the
Restricted probability designs: See
Rigor: The theoretical and methodological precision adhered to in conducting research.
Sample: A subset or subgroup of the population
Sample size: The actual number of subjects chosen
characteristi
Sampling: The process of selecting items ftom the population so the sample characteri
‘be genieralized to the population. Sampling involves both design choice and sample size
decisions.
a
mmple to represent the population
‘the sampling process.
‘of mechanism by shich individual
some meaningful wav.
A step-by-step, logical, organized. and rigorous effort 10 solve
evenisor objects are distinguished on the
Scientific investigation:
problems.
Secondary data: Data that have already been gathered by researchers, data published in
ed
statistical and other joumals, and information available from any published or unpublis!
Source available either within or outside the organization, all of which might be useful to
the researche
Selection effects: The threat to intemal validity that is a function of improper or unmatched
selection of subjects for th control groups.
Semantic differential scale: Usually a seven-point scale with bipolar attributes indicated at
extremes:
nple random sampling: A probability sampling design in which every single element!
population has-a known and equal chance of being selected as.a sublect.
in theSimulation: A model-building technique for assessing the possible effects of changes that might
be introduced in a system.
Social desirability: The respondents! need to give socially Jturally acceptable responses to
the questions posed by the researcher even if they are not ie.
Solomon four-group design: The experimental design that sets up two experimental groups and
two contral groups, subjecting one experimental group and one control group to both the
pretest and the posttest, and the other experimental group and control group 10 only the
posttest
Split-half reliability; The correlation coefficient between one half o
concept and the other half.
Stability of a measure: The ability
vulnerability tocharines id thesituatiod:
Standard deviatior measure of dispersion for paramemic data: the square root of che
‘variance.
Standardized regression coefficients (or beta coefficients): The estimates resulting fromm a
multiple regression analysis performed on variables that have heen standardized (a process
whereby the variables are transformed imo variables with a mean of 0 and a standard
devistion of 1).
Stapel scale: A scale that measures both the direction and intensity of
cept
Static panel: A panel that consists of
extended period of time for
Statistical power (1-): The probability of of correctly rejecting the null hypothesis.
Statistical regression; The threat io intemal validity that results when various group in the
‘study have been selected on the basis of their extreme (very high or very low) scores on
some important variables.
Stratified random sampling: A probability sampling design that first divides the population
into meaningful, nonoverlapping subsets, and then randomly chooses the subjects from
gach subset
Structural variables: Factors related to the form and design o:
‘and positions, communie:
eontrol
Structured interviews: Interviews conducted by the researcher wi
ques
Structured observational studies: Studies in which the researcher observes and notes specific
activities and behavior that have been clearly delineated as. important factors for
observation. before the commencement of the study
Subject: A single member of the sampl
Synopsis: A brief summary of the research study
Systematic sampling: A probability sampling design that
Tn the population for the sample.
Eetest: A stati establishes
items measuring a
the attributes of a
¢ same group of people serving as subjects over an
the organization such as ro!
d
h a predetermined lst of
hy
choosing every ath element
istical test thar able between two
significant mean difference
a
Broun:
Telephone interview; The information-gathering method by which the interviewer asks the
interviewee over face, for information needed for the
research.
telephone, rather than faceme
Subject the data collected to appropriate statistical tests.
substantiate of reject the hypotheses developed for the research study,
Festing effects: The distorting effects on te experimental vesulis (the posttest scores) caused by
the prior sensitization, the instrument through the pretes
‘Thematic Apperception Test (TAT): A projective test that requires the respondent io develop
a story around a picture,
Vheoretical framework: A logically develoned, described, and explained networ
associations among variables of interest to the research study
Treatment: The manipulation of the independent variable in experimental designs so
determine irs effects on a dependent variable of interest io the researcher.
Twoewav ANOVA: tical technique that can be used to examine the effect of wo
two different points
Testability; The ability
order to
nonmetric independent variables on a single metric dependent variable.
Tvpe | error (a): The probability of rejecting the sull hvnothes!
when itis actually tue.
Il hypothesis given that the
iling
Tepe 11 error (By: The probability of
alismaiive hypothesis is actually rue,
\Unit of analysis: The level of aggregation of the data aallecled fee alysis.
Unobtrusive measures: Measurement of variables throueh data gathered from sources other
than people. such 35 examination of birth and death records or count of the number of
cigarette butts in the ashtray.
Unrestricted probability sampling: See Simple random sampling.
Unstructured interviews: Interviews conducted with the primary purpose of identifying s
Important issues relevant to the problem situation, without prior preparation of a planned or
predetermined sequence of questions
Unstructured observational studies: Studies
‘of almost all activities and behavior that occur
amticular varlubles will bé of specific imerost ip the smude
Validity: Evidence that the instrument, technique. or process used to measure a concept does
indeed measure the imended concept
Varinble: Anything that can take on differing or varving values.
Variance: Indicates the dispersion of a variable in the data set, and is obtained by subtracting
the mean from each of the observations. squaring the results. summing them, and dividing
the total by the number of observations:
A honparamerric tes
Wilcoxon signed-rank tes uséd 10 Ekamine differences between twa
related samples or repeated measurements on a single sample. It is used as an alternative to
a paired samples retest when the population cannot be assumed to be normally distributed,
Word association; A projective method of identifying respondents’ attitudes and feelings by
asking them to associate a specified word with the first thing that comes to their mind,