DATA ANALYTICS AND RESEARCH FUNDAMENTALS
Hotelschool Year 1
RESEARCH WORKSHOPS 1 ™ 6
WS #1 Research Cycle
Research Cycle
Five steps
1. Problem analysis: What is the aim of your research?
2. Research design: How can you reach this aim?
3. Data collection: How can you collect this data?
4. Data analysis: What does the data look like? What can be interpreted from them?
5. Reporting: which conclusions are backed up by this data?
Tool design: survey
When you choose to use a survey, it is important to pay attention to how you phrase your
questions. You want to trigger people to give their most honest opinion, without predisposing
them to any specific ideas.
Phase 1: Problem Analysis
While conducting a problem analysis you often look for the answer to the following
questions:
- What is the direct cause for the research (and who ordered it )?
- What is the problem/the yet unknown?
- What is the aim of the study? What will be done with the results?
- What is the research question?
- What are the hypotheses?
Direct cause
answer the all-important WHY-question.
- What is the direct reason for conducting this research? Describe the situation.
- Who ordered the research? What was their initial question? Describe for whom you
are doing the research and what his/her question is.
In short: why is there a need for this piece of research?
Problem
Here you elaborate on the characteristics of the problem in the current situation.
- What is yet unknown at this moment in time? What information is missing?
- When the current situation as a whole is problematic: what exactly is going wrong?
Aim
- What is the aim of the study? What will the results of this study allow you to
do/decide that you can't do/decide now?
- A good way of thinking about the aim of your research is in terms of ACTION. What
will happen once it is completed? That will be the aim of your research.
1
,Research question (RQ) and sub-questions
Which overarching question will your research answer? And which sub-questions do you
need to answer first to get there?
- The RQ should address the most important issue in your research. Sub-questions
can help lead to this answer.
Hypotheses (optional)
If you have enough information to make predictions about the outcomes of your study you
can spell these predictions out in the form of hypotheses.
Well defined hypotheses are verifiable, so they can be tested!
- Verifiable: "When showing 10 photos and names to 100 people, 70% of them will
remember only 5 names or less."
- Not verifiable: "Tomorrow could be a sunny day". If indeed it is sunny tomorrow there
is no need to reject this hypothesis, but the same is true for when it rains. After all,
you said it could happen. This is why the hypothesis is not verifiable.
Phase 2: Research Design
Figure out how you are going to conduct your research.
The final outcome of this phase is a plan-of-action for your research that is detailed enough
so someone else would be able to conduct it for you: make the description of your research
as detailed as possible.
5 elements that require your attention when coming up with your research plan
1. Operationalization of variables
2. Type of research and study
3. Population and sampling
4. Research method
5. Representativeness, biases and quality
The order may vary depending on the flow of your report. However, you do need to address
them all.
Operationalization
Every concept or term that you use in the problem analysis needs a detailed definition. What
do you mean exactly when you use the term 'x' in the context of your research? What does
'x' refer to?
Type of research and study
What type of research would be most suitable for answering your research question?
- Descriptive - presenting known information
- Exploratory - trying to find new information
- Examinatory - checking if your conjectures (hypotheses) are true
Quantitative research
If you intend to express the outcomes of your research in numbers you are conducting
quantitative research: consist of calculations and its output of graphs and diagrams.
Quantitative research is often conducted using experimental designs or tailored surveys.
2
,Qualitative research
To describe any type of study that aims to acquire information that isn't numerical. For
instance studies aimed at discerning overall themes, coming up with descriptions, gathering
people's opinions or preferences.
Qualitative research tends to use observatory designs, case studies or interview-techniques.
Population and Sampling
Population and sampling are the usual suspects in any description of a research design.
The population is the focus group of your research.
Most often it is impossible to acquire information about every member of your population.
Imagine you are working for a big bank and you would like some feedback on a new idea to
improve services. It would be highly ineffective to try to consult millions of customers to ask
for feedback.
Instead you would send your idea to a small group of customers to gather their views.
This smaller group is called a sample
Drawing a sample from a population is called sampling.
Drawing conclusions about a population based on a sample is
referred to as making inferences or generalizing.
Research method
The method section is the heart of your research design. There are
three questions you need to ask yourself here:
1. How will you acquire information? Which research tool are
you going to use?
2. How will you measure that which is of interest to your research? Which instruments
are you going to use to tap into your constructs?
3. How will you execute your research? What procedure will you follow
Research tools
Experiment, conduct a survey, interview people, make observations etc.
Which tool would be most suitable for your research depends on your RQ, the aim of your
study and the type of your research.
Instruments
How will you now measure the variable? What instrument are you going to use to measure
precipitation? You have several options:
Your choice of which instrument(s) to use in your research is again both a theoretical and a
pragmatic one.
Writing up your research method is a bit like writing a recipe for a cookbook.
First you choose a dish (research tool) that suits the theme of the book (your research) and
then you describe the ingredients that go into the dish (instruments). Lastly you spell out
each step that needs to be taken to make the dish (procedure).
Representativeness, biases and quality
3
, How successful will my research design be at answering my research question?
To answer this question there are two things you definitely need to consider:
1. Representativeness
2. Quality of your measurements
Representativeness
Important to ask yourself whether your sample is sufficiently representative of this
population.When your sample is not representative of the overall population you are not
allowed to generalize your conclusions and doing so would be considered a mistake.
- poor sampling can seriously jeopardize the quality of your research!
Quality of the measurements
Besides the representativeness of your sample, you also need to check the quality of your
measurements.
In discussions about the quality of measurements you often encounter the term bias.
Bias refers to the degree to which the objectivity of measurements is affected by noise.
Noise can, among other things, be caused by poorly chosen instruments. For instance, the
use of leading questions in a questionnaire.
Validity and Reliability
Reliability
In a research setting, reliability refers to the degree to which multiple measurements come
up with the same result (how close the measured values are to each other).
Important in performing research that results are reliable. How to repeat your measurements
in order to determine how reliable they really are
Examples of possible approaches:
- Test/re-test reliability: imagine you take an IQ test and repeat that two weeks later,
to what extent do the results agree to each other?
- Inter-rater reliability: when two people are assessing something (for example
whether someone performs proper research), to what extent do the results agree
with each other?
- Internal consistency: imagine you want to assess someone's mood with three
different questions, to what extent do the results agree with each other?
Validity
Validity refers to the degree to what extent your measurement corresponds to what you want
to measure, the true value → often approached with the term accuracy.
Deviations in measurement equipment and other systematic errors can cause a low validity.
WS #2: Qualitative
Research
4
Voordelen van het kopen van samenvattingen bij Stuvia op een rij:
Verzekerd van kwaliteit door reviews
Stuvia-klanten hebben meer dan 700.000 samenvattingen beoordeeld. Zo weet je zeker dat je de beste documenten koopt!
Snel en makkelijk kopen
Je betaalt supersnel en eenmalig met iDeal, creditcard of Stuvia-tegoed voor de samenvatting. Zonder lidmaatschap.
Focus op de essentie
Samenvattingen worden geschreven voor en door anderen. Daarom zijn de samenvattingen altijd betrouwbaar en actueel. Zo kom je snel tot de kern!
Veelgestelde vragen
Wat krijg ik als ik dit document koop?
Je krijgt een PDF, die direct beschikbaar is na je aankoop. Het gekochte document is altijd, overal en oneindig toegankelijk via je profiel.
Tevredenheidsgarantie: hoe werkt dat?
Onze tevredenheidsgarantie zorgt ervoor dat je altijd een studiedocument vindt dat goed bij je past. Je vult een formulier in en onze klantenservice regelt de rest.
Van wie koop ik deze samenvatting?
Stuvia is een marktplaats, je koop dit document dus niet van ons, maar van verkoper eefkosten. Stuvia faciliteert de betaling aan de verkoper.
Zit ik meteen vast aan een abonnement?
Nee, je koopt alleen deze samenvatting voor €8,46. Je zit daarna nergens aan vast.