GRADUATE SCHOOL OF BUSINESS LEADERSHIP

MASTERS IN BUSINESS ADMINISTRATION

MODULE: MBA 740 – BUSINESS RESEARCH METHODS

FACILITATOR: MR. T. SIBANDA
GROUP 10
QUESTION 20 –DESCRIBE THREATS TO EXTERNAL VALIDITY IN QUANTITATIVE BUSINESS
RESEARCH?
 GROUP 10 – MEMBERS

NAME SURNAME REG. NUMBER

CHRISTIAN MUDIWA R111082H
FARAI MOYO R212645P
NYASHA KADZUNGE R112381M
ONETTE MHAKO R1710125G
ABNER MAMVURA R211496H
KUMBIRAI TAVAGWISA R167816X
ANESU CHIMHINI R211683Q
TAFADZWA MASARIRAMBI R212105R
ANESU MAPIRAVANA R156167N
MIGHTY MANDAZA R144505T
CHENGETAYI MUTANDWA R2011808B
RUMBIDZAI CHIHOTA R0825679W
TINASHE MUGADZA R2011563Z
Pritha Bhandari (2021), Quantitative research is the process of collecting and analyzing numerical data. It
can be used to find patterns and averages, make predictions, test casual relationships and generalize
results to wider populations.

Springer (2010), External validity is the extent to which experimental findings can be generalized beyond
the original study
 ORDER BIAS
 Occurs when the effect of the order of the interventions have an unintended impact on the
results
 The extent to which findings resulting from a particular order of administration of treatments or
interventions cannot be generalized to situations in which the sequence of interventions is
different

POPULATION VALIDITY

 It is the extent to which findings are generalizable from the sample of individuals on which a
study was conducted to the population from which the sample was drawn
 Occurs when a researcher analyzes a subset of her/his dataset such that there is a discrepancy
between those sampled and those not sampled from the full dataset, leading to findings from
the subset that are less generalizable than would have been the case if the total sample had
been used
 ECOLOGICAL VALIDITY

 Extent to which findings from a study can be generalized across settings, conditions, variables
and contexts.
 Thereby representing the extent to which findings from a study are independent of the setting
or location in which the investigation took place

SPECIFICITY OF VARIABLES
 Occurs when one of the seven variables are so unique to the study that the findings are not
generalizable: type of participants, time, location, circumstance, operational definition of the
independent variables, operational definition of the dependent variables, and types of
instruments used
 MULTIPLE TREATMENT
INTERFERENCE
 It is a threat to external validity inasmuch as the order that the treatments or interventions are
administered (i.e., sequencing effect) reduces a researcher’s ability to generalize findings to the
population because generalization typically is limited to the particular sequence of interventions
that was administered
 Occurs when participants in a study are included in multiple treatments

TREATMENT DIFFUSION

 It is the extent to which the intervention is diffused to other treatment conditions in a unique (i.e.,
unreplaceable) way that threatens the researcher’s ability to generalize the findings
 PRETEST X TREATMENT
INTERACTION
 Situations in which the administration of a pretest increases or decreases the participants’
responsiveness or sensitivity to the intervention or treatment, thereby making the observed findings
pertaining to the pretested group unrepresentative of the effects of the independent variable for the
un-pretested population from which the study participants were selected allowing the researcher to
generalize the findings to pretested groups but not to un-pretested groups

SELECTION X TREATMENT
INTERACTION
 Stems from important pre-intervention differences between intervention groups that emerge because
the intervention groups are not representative of the same underlying population—making it
unjustifiable for the researcher to generalize the results from one group to another group
 MATCHING BIAS

 Extent to which findings from the matched participants cannot be generalized to the results that
would have occurred among individuals in the accessible population for whom a match could not
be found (i.e., individuals in the sampling frame who were not selected for the study)

TEMPORAL VALIDITY

 Extent to which research findings can be generalized across time—or the extent that results are
invariant across time
 REACTIVE ARRANGEMENTS

 The five components of reactive arrangements adversely affect external validity because, in their
presence, findings pertaining to the intervention are determined by which of these components
prevail

RESEARCHER BIAS
The more unique the researcher’s characteristics and values that influence the data collected, the less
generalizable the findings
SELECTION BIAS

 This is one of the most significant threats to external validity. Selection bias is when the research
criteria and study inclusion method automatically excludes some part of the population from the
research process. Examples
I. When collecting data about parenting from a mother’s group only and not collecting from the
father’s as well.
II. When administering the survey online, it means you are excluding members of your population
without access to internet.
 HISTORY
 It is also a threat to external validity of quantitative research, it happens when an unrelated event
influences the outcomes. History effects mean events which take place in the environment that
alter the conditions of a research impacting its end result.

HAWTHRONE EFFECT

 It refers to the increase in performance of individuals who are noticed, watched and paid
attention to by researchers or supervisors. Even at workplace there is a relationship between
productivity and observation. Letting employees know that they are being observed may
engender a sense of accountability and such accountability may intern improve performance at
work place.
EXPERIMENTOR EFFECT

 The threat is related to the researchers influence on the outcome of his/her research. The
researcher is the one who chooses the research topic hence there is a predicted outcome in the
mind. By having the prediction in advance it influences a lot of things like the methodology,
literature review sample and even the method of analyzing data. This makes the research
unreliable.
 Ways to overcome the experimenter effect are
1. Double blind design
2. Mechanize procedures
3. Research protocols
4. Investigator intervention
5. Considering more aspects
 TESTING EFFECT

 The administration of a pre- or post- test affects the outcomes of a research. For example participants
are familiar with the pre-test format questions, they are less anxious during the post test and recall
less anxiety then.

SITUATION EFFECT

The factors like setting of time, date location, researchers characteristics limit the generalization of the
findings. For example the participants practice mindfulness at night rather than in morning and the
outcome do not show any improvement this time.
 APPTITUDE TREATMENT

 The interactions between characteristics of the group and individual variables together influence
the dependent variable. Interactions between certain characteristics of the participants with
depression for example negative though patterns and the mindfulness exercise like to focus on
the present improve anxiety levels. The findings are not replicated with people with personality
disorders.
THANK U