Questions for the course "Scientific Methods" with the topic: Quantitative research (lecture 8).
Click the button to start the quiz
What are some of the typical quantitative research methods?
Surveys
Experiments
What research design does a survey cover?
Qualitative
Quantitative
What is a survey?
An organized method of obtaining data from participants via written or oral questions
It is a comprehensive system for collecting information
What types of surveys does their exist?
Supervised
Semi-supervised
Unsupervised
What does supervised surveys mean?
Interviwer administers the servey togheter with the participants
Ofte telephone
Can be one-to-one
Can be a group
What does Semi-supervised surveys mean?
Interviewer explains the survey, often through example questions, but let the participant fill out the survey themselves
What does unsupervised surveys mean?
Interviewer are not present
Often web-based
Often paper-based
What are some of the research objectives, when performing a survey?
Explain
Describe
Measure a frequency
Evaluate a characteristic of a population
Discover a factor that affect the characteristics of a population
What should you consider when designing a survey?
Multiple people should be in the creation process
If you should measure descriptive
If you should measure behavioural
If you should measure attitudinal
Allignment with RQ
What are some things that could be included in the survey, to increase motivation?
According to Kitchenham and Pfleeger, 2008
What the purpose of the study is
Why it should be of relevance to them
Why each individual's participation is important
How and why each participant was chosen
How confidentiality will be preserved
Try to offer a benefit
How can you test a survey, before deploying it?
According to Kitchenham and Pfleeger, 2008
Piloting
A focus group
Using representative of your sample population
Using people who might use the results
What are some of the advantages of using a survey?
Quickly gather large amount of data
Cheap
Quick
What are some of the disadvantages of using a survey?
Complex to design
Competetive market
What is an experiment?
A scientific procedure undertaken to make a discovery, test a hypothesis, or demonstrate a known fact
What two types of variables are there in experiments?
Independent
Dependent
What are typical types of experiments in Software engineering?
Quasi-experiments
Controlled experiments
What does Quasi-experiments mean?
An experiment that does not have random assignment
An experiment that does not have a control group
Types of members are equally distributed in groups
What are the steps in the experimental process?
Scoping
Planning
Operation
Analysis and interpretation
Presentation and package
When defining experiment scoping, what are the questions to be answered?
What is studied? (Analyse)
What is the intention? (Purpose)
Which effect is studied? (Quality focus)
Whose view? (Perspective)
Where is the study conducted? (Context)
What are the steps in experiment planning?
Context selection
Hypothesis formulation
Variables selection
Slection of subjects
Choose design type
Instrumentation
Validity evaluation
What are some common principles for experiment design?
Randomization - Pick subjects randomly
Blocking - Eliminate undesired effect of a factor
Balancing - Each treatment is applied equally
What are types of subject assignments to treatments in experiments?
Between subjects
Within subjects
When using "Within subjects" slection of subjects, what is it important to be aware of?
Mixing the ordering
Ordering can affect the results
Is bewtween subjects more statistically powerful than within subjects?
No, but the opposite is true
What's the benefits of using between subjects?
Minimize the learning and transfer across conditions
What's the benefits of using within subjects?
Removes individual variation
How can you make sure, that you can trust the result of the experiment (Validity evaluation)?
Inspect instruments, and ensure no errors
Variables represents the concepts from theory
Carefully select subjects
Choose analysis method carefully
Ensure to acknowledge, that the results are not generalizable
What are common types of quantitative data analysis?
Descriptive statistics
Inferential statistics
What does descriptive statistics do?
Summarize the data
Measure tendency
Measure variability
Measure outliers
Measure skewness
What does inferential statistics do?
Make inferences about a population based on a sample
Test hypothesis
Estimate parameters
Is there a difference in the tests that can be used, based on the normality of the data?
"Normality" refers to normal distribution.
Yes, not all tests can be done, if there is a large skewness in the data
What type of hypothesis testing is there?
Referring to hypothesis testing in experiments
Parametric
Non-parametric
What does parametric test entail in hypothesis testing?
Referring to hypothesis testing in experiments
Assumes normal distribution
Data is interval or ratio
What does non-parametric test entail in hypothesis testing?
Referring to hypothesis testing in experiments
Does not assume normal distribution
Data is ordinal
What does a low p-value mean?
Strong evidence against the null hypothesis
Reject the null hypothesis
Can you accept a hypothesis?
No, you can only reject or fail to reject