Discussion 1: Variables, Research Questions, and Data Coding
D1.1. Compare the terms active independent variable and attribute
independent variable. What are the similarities and differences?
Active and attributeare two types of independent variables.
Understanding the difference between these two is crucial for any analysis of
research results. During the study, a sample population is offered at least
one gradation of an active independent variable. Curriculum changes and
experiential learning opportunities are two examples of activeindependent
variables. When experimenting, the researcher is not obligated to present or
modify the active independent variables given to the participants (Morgan et
al., 2019).
In contrast, an attribute-independent variable is an unchangeable
independent variable that is nonetheless crucial to the research.
Independent attribute variables are those whose values, such as individual
characteristics or aspects of the participants' continuous environments, are
not consistently altered during the research. Independent attribute variables
include parental education level, household income, age, race/ethnicity,
intelligence test scores, and self-perception. Nonexperimental studies rely
only on attribute independent variables (Morgan et al., 2019).
D1.2. What kind of independent variable (active or attribute) is
necessary to infer cause?
&&&&&&&When analyzing study data statistically, researchers cannot tell the
difference between an active independent variable and an attribute
independent variable. However, only methods with an activeindependent
variable might yield results that can be utilized to conclude that the desired
variable was the primary driver of the observed alteration or distinction in
the dependent variable of interest (Morgan et al., 2019).
D1.2.a Can one always infer cause from this type of independent
variable? If so, why? If not, when can one infer cause, and when
might causal inferences be more questionable?
One cannot always infer causation from an active independent
variable since such a variable alone is insufficient for drawing causal
inferences. Research designs based on random assignment, either
experimental or quasi-experimental, allow for the inference of causal
relationships between independent and dependent variables. It is
questionable to draw causal conclusions when the dependent variable is
altered based on an attribute-independent variable. If one wishes to
conclude the relationship between two groups without imposing a causal
explanation on the dependent variables, one might do it with the help of an
attribute-independent variable (Morgan et al., 2019).
D1.3. What is the difference between the independent variable and
the dependent variable?
In comparative studies, there are benefits and drawbacks to relying
on a single indicator as an independent variable. The two primary drawbacks
are their low informational value and the potential for calculational error
(Kunißen, 2019). The influence of an independent variable is thought to be
measured by its corresponding dependent variable. It represents the
expected result or benchmark. Points on exams, survey responses,
measurements from devices, or logs of exercising are typical examples of
dependent variables (Morgan et al., 2019). Like independent variables,
dependent variables must possess a minimum of two possible values.
However, unlike independent variables, such as a student's grade on
anexam, dependent variables often have a wider range of values, making
them more challenging to depict (Morgan et al., 2019).
D1.4. Compare and contrast associational, difference, and
descriptive types of research questions.
Associational questions are those in the realm of research that seek
to shed light on the link between a couple ofvariables and another variable,
particularly in a predictable fashion. Examining the dissimilarities between
many groups on a single dependent variable is the goal of a difference
research question (Morgan et al., 2019). These two inquiries may be
answered using inductive statistical methods, assessing the connection
between variables. Descriptive research questions seek to summarize and
describe a subset of a population instead of extrapolating from a sample.
The average, standard deviation and percentage are all descriptive statistics
that may be used to shed light on this inquiry (Morgan et al., 2019).
One of the most common justifications for using a primarily
descriptive methodology is the need to fill in gaps in knowledge with plain
accounts of individuals' experiences and perspectives. Due to the potentially
biased nature of the issue and the diversity of participants' perspectives, a
descriptive qualitative approach may be the best method for answering the
research question (Doyle et al., 2020).
D1.5. Write a research question and a corresponding hypothesis
regarding variables of interest to you but not in the HSB dataset. Is
it an associational, difference, or descriptive question?
How often is electronic material used in the nonprofit sector as part
of successful strategy formulation? This is a descriptive question. The scope
of this method is restricted to learning about the data's distributional
features as they pertain to the population under study.
D1.6. Using one or more of the following HSB variables, religion,
mosaic pattern test, and visualization score
& & & D1.6.a Write an associational question.Does the pupil's ability
to visualize situations in three dimensions predict their success in algebra?
D1.6.b Write a difference question.Do groups of students with a
religious background have a higher chance of winning a match than groups
with no such background?
D1.6.c Write a descriptive question.How many pupils who
received an identical score on their achievement tests were eighteen or
older?
References
Doyle, L., McCabe, C., Keogh, B., Brady, A., & McCann, M. (2020). An
overview of the qualitative descriptive design within nursing
research.Journal of Research in Nursing,25(5), 443–455.
Kunißen, K. (2019). From dependent to independent variable: A critical
assessment of operationalization’s of ‘welfare stateness’ as macro-level
indicators in multilevel analyses.Social Indicators Research,142(2), 597–
616.
Morgan, G. A., Barrett, K. C., Leech, N. L., & Gloeckner, G. W. (2019).IBM
SPSS for Introductory Statistics(6th ed.). Taylor & Francis.
not, when can one infer cause and when might causal inferences be more
questionable?
Powered by TCPDF (www.tcpdf.org)
