QRM Week 2
FPM1315 Quantitative Methods Week 2 Introduction
This week focuses on the foundational principles that underpin all statistical analysis in psychological research.
Before conducting any statistical test, it is essential to understand how data are measured, whether they meet key assumptions, and how these factors influence the selection of appropriate analytical techniques.
At postgraduate level, the expectation is not simply that you can run analysis, but that you can justify your methodological decisions. This includes explaining why a particular test was chosen, whether its assumptions were met, and how the nature of the data shaped your decisions.
These concepts are therefore central not only to your assignments, but also to developing as an independent researcher.
In quantitative research, statistical analysis is not just a mechanical process. Instead, it involves a sequence of decisions that begin long before any tests are conducted.
First, we must understand how our variables are measured.
Second, we examine the distribution of the data.
Third, we assess whether key assumptions are satisfied.
Only then can we select an appropriate statistical test.
For example, imagine you are analysing study scores from a student questionnaire. You have two groups of students. Group A studied normally whilst Group B used a new study method after a test.
Group B scores higher. But is that because the method works? Or just luck?
A statistical test known as the t-test can help you decide that.
The t-test asks, are these two averages actually different? Or could this difference just be random?
However, before you decide on using the statistical test known as the t-test, you must consider: are these scores treated as interval data? Are the observations independent of each other?
Skipping these steps can lead to incorrect conclusions, even if the statistical test itself is executed correctly.
This is why this week is so critical. It forms the decision-making framework for all subsequent analysis.
You should be able to firstly differentiate between measurement scales and evaluate reliability and validity.
Secondly, assess data distributions and test statistical assumptions.
And thirdly, evaluate when to use parametric versus non-parametric statistical tests.
First, understanding the nature and quality of your data.
Second, evaluating whether your data meet the requirements of statistical analysis.
And third, making informed decisions about which statistical techniques are appropriate.
Together, these skills ensure that your analyses are not only technically correct, but also methodologically justified.
To conclude, this week establishes the critical foundations for all statistical work in research methods.
By understanding how variables are measured, how data are distributed, and whether key assumptions are met, you are better equipped to make informed and defensible analytical decisions.
Rather than viewing statistics as a set of procedures to follow, you should begin to see it as a structured process of reasoning, where each step is guided by the nature of your data and your research question.
Developing this decision-making mindset is essential for conducting robust, transparent and credible research at postgraduate level and beyond.
As you commence your studies this week, consider how might your choice of measurement scale, for example, ordinal versus interval, influence the type of statistical test you select, and what are the risks of getting this wrong?
If your data does not meet key assumptions such as normality or independence, how would this affect your interpretation of results and what alternative approaches could you consider?
Thank you for listening to this introduction to week two of Quantitative Research Methods.
I hope that you enjoy the lectures, learning material activities and discussions this week.
Quantitative Methods Week 2 Introduction Lecture
Writing
Welcome to this Quantitative Research Methods Week Two lecture on methods of data collection.
In this lecture, we are going to explore methods of data collection, what influences the choice of these methods, and what you as students need to be aware of when conducting research.
Data collection is at the heart of any research project. The decisions you make at this stage will directly affect the quality of your results and the conclusions that you can draw from the data.
Whether you're working on a dissertation, coursework, or even workplace research, choosing the right method is critical. It shapes the reliability, the validity, and the usefulness of your findings.
As we go through, I want you to think about your own research ideas and which methods might work best for you.
The learning outcomes for this lecture are that by the end of this lecture, you should be able to:
1. Identify and describe key data collection methods used in research, including both numerical and non-numerical approaches.
2. Evaluate the factors that influence the choice of method, such as time, access and the type of research question.
3. Recognise practical and ethical considerations and understand how these impact the quality and integrity of your research.
These outcomes will help guide your thinking as you plan and carry out your own research projects.
What is data collection?
Data collection refers to the systematic process of gathering information in order to answer a specific research question.
There are two main types of data: primary data and secondary data.
Primary data is data that you collect yourself, for example through surveys, interviews or observations.
Secondary data is data that has already been collected by someone else, such as government statistics, academic articles, or industry reports.
Each type has its distinct advantages. Primary data is more tailored to your research, whereas secondary data can save time and provide a broader context.
In the table on this page, you'll see a more complete table outlining the different characteristics and pros and cons of primary and secondary data sources.
It's important to remember that the method you choose determines not just the data you collect, but also the depth, the accuracy and the relevance of that data.
Quantitative methods
Quantitative methods focus on numerical data. Data that can be measured and analysed statistically.
Common examples include:
- Surveys with closed questions such as multiple choice or rating scales.
- Experiments, where variables are controlled and measured.
- Structured observations, where behaviours are counted or recorded in a systematic way.
Generally, these methods are useful for any type of research question that asks how much, how many, or to what extent.
These methods are particularly useful when you want to identify patterns or trends, compare groups, or make generalisations to a larger population.
For example, if you want to know how many students prefer online learning versus face-to-face learning, a survey may be appropriate.
However, while quantitative methods are strong in terms of objectivity and reliability, they often lack the depth needed to understand why people think or behave in certain ways.
Qualitative methods
This brings us on to qualitative methods. In contrast, qualitative methods focus on understanding experiences, meaning and perspectives.
Examples include:
- Interviews, which can be structured or more open-ended.
- Focus groups, where participants discuss topics together.
- Observations, where you study behaviour in a natural setting.
These methods can allow you to explore people's thoughts and feelings, motivations and behaviours, or complex social processes.
For example, instead of asking how many students prefer online learning, you might explore why they prefer it.
The strength of qualitative research lies in its depth and richness.
However, it can be time-consuming to collect and analyse. It can be more subjective as interpretation plays a role, and it can be difficult to generalise to larger populations.
Mixed methods
Mixed methods research combines both quantitative and qualitative approaches within a single study.
For example, you might start with a survey to identify trends, then follow up with interviews to explore those trends in more detail.
This approach can allow you to triangulate findings, meaning you can cross-check results from different methodologies.
Mixed methods can provide both breadth and depth, giving a more complete understanding of your research topic.
However, it also requires more time and effort and can require careful planning to ensure the methods complement each other.
So while mixed methods are powerful, it's important to consider whether it's realistic within your project constraints.
What influences method choice?
So how do you decide which method to use?
There are several key factors here.
Firstly, the research question. This is the most important factor.
Secondly, the type of data needed. Do you need measurable data or detailed insight?
Thirdly, time and resources. Do you have enough time to conduct interviews or analyse a large data set?
Fourthly, access to participants. Can you realistically reach your target group?
Finally, ethical considerations. Is your method appropriate, safe and respectful?
Ultimately, your method must fit your research aim. A mismatch between these can weaken your entire project.
Strengths and limitations
It's important to emphasise that no data collection method is perfect. Each comes with its own strengths and limitations.
For example:
- Surveys are quick and can gather responses from many people with relative ease, but responses may be shallow.
- Interviews provide rich, detailed data, but take time to conduct and analyse.
- Observations can capture real behaviour but may be influenced by researcher bias.
As a researcher, your role is to balance:
Reliability: The consistency of results.
Validity: Whether you are actually measuring what you intend to measure.
Practicality: What is realistically possible within the practical constraints that you face.
Being aware of these trade-offs helps you make more informed decisions.
Ethical considerations
Ethics play a crucial role in data collection and must never be overlooked.
You must ensure:
- Informed consent: Participants understand what they are agreeing to.
- Confidentiality and anonymity: Protecting participants' identities.
- The right to withdraw: Participants can leave the study at any time.
- Data protection: Storing and handling data securely.
For example, if you are recording interviews, participants must know how the data will be used and stored.
Failing to follow ethical guidelines can not only harm participants, but also invalidate your research and damage your credibility.
And in the image there, I've just shown the Code of Human Research Ethics, which is one of the main guidance documents that underpin ethical considerations that we use.
What students need to be aware of
There are several key challenges to be aware of.
Bias: For example, leading questions or personal assumptions can influence results.
Sampling issues: Is your sample representative, or are you only surveying people maybe similar to yourself?
Practical constraints: Time, access to participants, and workload can limit what you can realistically achieve.
Data quality: Are your responses accurate, honest and reliable?
It's better to choose a simple, well-executed method than a complex one that is poorly managed.
Always think critically about your choices and justify them.
Summary
To summarise this lecture, data collection methods include quantitative, qualitative, and mixed approaches, each suited to different types of research questions.
The choice of method depends on your aims, the type of data that you need, available resources and ethical considerations.
Every method has its strengths and its limitations, and no single approach is perfect across all contexts.
As students, you must be aware of bias, sampling issues, ethical responsibilities, and practical constraints.
Ultimately, your goal is to collect data that is valid, reliable, and appropriate for answering your research question.
If you keep your research question at the centre of your decisions, you're much more likely to choose the right method.
Thank you for listening to today's lecture on methods of data collection.