Appendix Flashcards
Research in Organizational Behaviour
- Based on research that involves objective and systematic information gathering
- Separates the sturdy from opinion and common sense
Evidence-based Management (EBM): rely on
Many managers rely on:
obsolete knowledge gained years ago in school,
long-standing (but rarely tested) traditions,
patterns gleaned from experience,
methods that they “believe” in,
information from consultants.
EBM calls for organizational practices that are based on scientific evidence
Increases predictability
Increases odds of success
Increases your value to an organization
Scientific Method - theory
explains why, how, and when the variables are related
Hypotheses
predictions that specify relationships between variables
Measurement of Variables - validity
is an index of the extent to which a measure truly reflects what it is supposed to measure.
Do not want low validity
Reliability
is an index of the consistency of the data.
Low reliability is BAD
Less reliability means more random error
Everytime will it give the same response
Research Techniques/ Designs
- case studies
- observational
- correlational
- experimental
Observational
broad data, (participant, direct)
Correlational
Research that attempts to measure variables precisely and examine relationships among these variables without introducing change into the research setting. Ex: Surveys, Interviews, Existing (Archival) Data
Experimental
Lab or Field
Shows causation
Manipulates nature.
One variable changed and its consequence measured in other.
Control group.
Does Correlaiton Mean Causation?
Causation/Cause and Effect – Changes in X cause changes in Y.
Correlation: Correlation does not prove causation. – Indicates an association.
Internal validity:
- extent to which a researcher can be confident that changes in a dependent variable are due to the independent variable
- Has to do with the validity of the study design.
- Random assignment, control group improve this
External validity:
- extent to which the results of a study generalize to other samples and settings
- External validity is greater when the results of a study are based on large, random samples.
- Only makes sense if it is going to apply to other people
How research techniques could go wrong:
Correlations are often mistaken for cause/effect relationships.
Measurement is sometimes bad (e.g., low validity)
Small sample sizes (or inappropriate samples) could limit external validity
A single study might not replicate (e.g., the findings might be due to random error)
Moderating variable
is a variable that affects the nature of the relationship between an independent variable and the dependent variable such that the relationship depends on the level of the moderating variable
Mediating variable
is a variable that intervenes or explains the relationship between an independent variable and the dependent variable
Convergent validity
exists when there is a strong relationship between different measures of the same variable
Good measures should not be related to measures of different variables, ex - a measure of job satisfaction should not be related to measures of job performance
Discriminat validity
exist when there is a weak relationship between measures of different variables
Good measnures should have both convergent and discriminant validity
research tecnhniques: observation
the researcher proceeds to examine the natural activities of people in an organizational setting by listing to what they say and watching what they do.
Participant observation:
the researcher becomes a functioning member of the organizational unit they are studying to conduct the research, there is no substitute for experience
Direct observation,
the researcher observes organizational behaviour without participating in the activity being observed
correlation techniques
- correlation research
- surveys
- interview
- existing data
- cross sectional data
- longitudal design
- correlation and causation
Correlation research
attempts to measure variables precisely and examine relationships among these variables without introducing change into the research setting
Existing data
are obtained from organizational records and can include productivity, absence, turnover, and demographic information
Cross-sectional data
is when both the independent and dependent variables are measured at the same time
Longitudinal design
the independent variable will be measured at one point in time and the dependent variable will be measured some time later
Experimental techniques: Experimental research
involves manipulating nature, research that changes or manipulates a variable under controlled conditions and examines the consequences of this manipulation for some other variable
Control group
is a group of researcher participants who have not been exposed to the experimental treatment – not exposed to training
Random assigment
is randonly assigning participants to the experimental and control conditions of an experiment
- improves internal validity
Threats to internal validity
- are factors that are alternative explanations for the result of an experiment
- Selection of participants, testing, instrumentation, statistical regression, history, maturation, mortality
Quasi-experimental design
is a research technique in which the participants are not randomly assigned to the experimental and control conditions
issues and concerns in Ob research
sampling
random sampling
hawthorne effect
ethics
Sampling
researchers are usually interested in generalizing the results of their research beyond their study, the extent to which the results of a study generalize to other samples and settings is known as external validity
External validity
is the extent to which the results of a study generalize to other samples and settings
Large samples are used to endure that the results they obtain are truly representative of the individuals, groups, or orgnaizations being studied
Random sampling
means that research participants have been randomly chosen from the popualtion of interest
Hawthorne Effect
is a favourable response by participants in an organizational experiment that is the result of a factor other than the independent variable that is formally being manipulated
Ethics
- researchers in organizational behavior, no matter who employes them have an ethical obligation to do rigorous reseach and to report that research accuratly