U5
In this assignment, you will articulate a business problem and identify variables and quantitative statistical techniques to investigate the issue.
Business Problem: Formulate a current business problem using examples and descriptions drawn from scholarly literature or a specific business organization.
Using your own ABRP or the example project, identify the business problem.
State and briefly explain it.
Explain the problems relationship to the research question.
Research Question: Refine the business problem into one or more research questions that require the use of inferential statistics and allow for an exploratory investigation.
From the business problem, explain a research question that will require use of inferential statistics.
With each question, address the relationships among variables and/or the difference among groups or conditions.
Variables: Refine the research question into variables that are operational and measurable.
Identify the variables that are involved in that research question.
Explain the significance and magnitude of the statistical relationships or differences.
Data Collection Instruments: Explain how to evaluate the ability of the instruments or other data collection methods to quantify the variables.
Identify the instruments or other data collection methods that will be used to gather the data needed to measure your variables.
Explain how these instruments and/or methods will be evaluated to assure their validity and reliability.
1
Capella Proprietary and Confidential
Last updated: 4/7/2019 6:58 PM
Quantitative Study Example Project
What follows is a hypothetical quantitative study that you can use to set up your U05a1
assignment. The variable data from this example are from an actual study, but the names
of participants and variables have been changed. In all other respects, the description is
accurate. For this example, imagine that you are researcher who often consults with small
to medium size manufacturing companies in Northwest Ohio who make auto parts for the
large auto manufacturing companies. You have noticed concern among your clients about
the turnover of their line factory workers. In the last year for which data were available
(2017) it was determined that the average annual population of motor vehicles
manufacturing employees in the State of Ohio during calendar 2017 was 19,600
employees (Bureau of Labor Statistics, 2018), of which about 30% were estimated to be
factory line workers or 5,880 workers. A list can be obtained of these employees through
a provider of data lists.
You decide to conduct a study to investigate what independent variables might be
valuable in predicting employees likelihood of leaving their jobs. Suppose that you have
reviewed the research literature on the subject and identified a construct called
turnover intention and found a scale called the Turnover Intention scale that might be
used to measure and predict how likely employees are to terminate their employment.
Constructs are often explanatory variables that cannot be directly observed. For example,
one cannot see a turnover intention, but these intentions can be quantified using a
survey instrument. This literature review also identified two other constructs that might
have value in predicting what employees turnover intentions might be. One of these
variables is job mastery, a survey instrument scale that measures how well employees
believe that they have mastered the skills involved in their jobs. A scale called the Job
Mastery scale exists that would allow you to measure this construct. Another variable you
identify is a survey instrument used to measure a persons control of her state, called the
Impulse Control scale.
You decide to conduct a study of employees who work as line factory employees of the
auto industry in Ohio. You want your study to look at how well the two variables, Job
Mastery and Impulse Control, will predict Turnover Intentions. In doing so, you are
aware that it is also important to pay attention to the direction of the effects. That is,
whether there is a direct effect (an increase in the independent variable leads to an
increase in the dependent variable) or an inverse effect (an increase in the independent
variable leads to an increase in the dependent variable).
