[HBA05C] Research Methods 1: summary

Introduction
Business research involves establishing objectives and gathering relevant information to
obtain the answer to a business issue, such as “what’s the target market of my product?”. It
can also be used to solve a business-related problem, such as determining how to decrease the
amount of excess inventory at hand.
The roles of business research are numerous:
 Show patterns and direction.
 Create insights.
 Test concepts.
 Foster innovations.
 Highlight analytical and empirical skills.
It’s important to create a problem definition and decision statement:
 During problem definition, you engage in defining and developing a decision
statement.
 Understanding the business issue.
 Identifying the problems caused by the issue.
 Determining the unit of analysis and research variables.
 Writing the research questions/hypotheses.
 A decision statement expresses the critical question(s) the research must answer.

, Space and time
Cross-sectional studies
In medical research and social science, a cross-sectional study (also known as a cross-
sectional study, transversal study, prevalence study) is a type of observational study that
involves the analysis of data collected from a population, or a representative subset, at one
specific point in time.
Cross-sectional studies are carried out at one time point or over a short period:
1. Present-present: cross-sectional study.
2. Present-future: prospective cohort study.
3. Present-past: retrospective cohort study.
4. Present-past: case-control study.
5. Present-future: randomised controlled trial.
They’re usually conducted to estimate the prevalence of the outcome of interest for a given
population, commonly for the purpose of public health planning.
Data can also be collected on individual characteristics, including exposure to risk factors,
alongside information about the outcome.
In this way, cross-sectional studies provide a sort of a snapshot of the outcome and the
characteristics associated with it, at a specific point in time.


Strengths:
 Best for exploratory and descriptive studies.
 Ex: national census.
 Cost-efficient.
 Fewer logistic problems.
Disadvantages:
 Trying to understand causal processes based on observations observed at one point in
time can be complex.
Examples of research problems that would be best suited by cross-sectional studies include:
 Tracking how many hours students spend on a particular course on a particular day of
the week.


Longitudinal studies
Longitudinal studies are designed to allow observations over a period of time. There are
different types of longitudinal studies:
1. Trend studies.
a. They sample different groups of people at different points in time from the
same population.

, b. For example, before an election a sample of adults is drawn and, a year later, a
different sample is drawn from the same population and a change is shown.
2. Cohort studies.
a. They’re concerned with examining the development of groups from a
particular time point.
b. A cohort is a group of people who enter or leave an institution at the same
time.
c. For example, there are cohorts by age, cohorts by activity, birth cohorts.
3. Panel studies.
a. They’re studies about the same set of people that are interviewed two or more
times over time.
b. For example, online opinion panels that invite members of the public to sign
up and then complete regular surveys.
Strengths:
 Better for testing causal processes.
 Allow for more in-depth understanding of behaviour.
Disadvantages:
 Expensive.
 Logistically more complicated.
 Time consuming.
 Attrition (losing respondents).
Examples of research problems that would be best suited by longitudinal studies include:
 Tracking students’ employment status for 5 years.


Direction in studies
In retrospective research, we ask respondents to recall their past. For example: “what
percentage of abuse victims have parents who were abused?”. However, looking backwards
has some limitations:
 Poor memory.
 Lying.
 Unavailable or incomplete records.
In prospective research, we begin with a sample and follow their behaviour into the future.
For example: “what percentage of abuse victims later abuse their children?”.
Sample selection differs and plays a critical role in each approach:
 It can be random or not random.
 For example, if I want to take a sample from the people attending a lecture, I can do it
randomly or just by selecting the people sitting in a specific row.
Choosing a study type

, There are a few things to ask yourself when creating a study:
 How does time matter in my study?
 Can I use a snapshot of data to answer my question or do I have to asses my question
over a period of time?
 If time is implied in my research, is it more appropriate to look backwards
(retrospective research) or forwards (prospective research)?
 The ultimate selection of a study type will be completed once the research design is
selected:
 Experimental.
 Non-experimental.


Identifying a target population
It’s important to define how we select our respondents and their participation in the activity:
 Who’s the focus of my study?
 What are the characteristics that define the boundaries of my target population?
Defining a target population is important to selecting a sample.


Units of analysis
It’s important to understand who am I looking at in my research: this is called unit of
analysis.
 Am I looking at an individual?
 A cohort?
 A group?
 A particular social artefact?
 A mixture?
However, be aware to avoid mistakes:
 Ecological fallacy: applying results from group analysis to individuals.
 Individualistic fallacy: applying information related to an individual to groups of
individuals.