Quantitative Research Quick Reference
Every definition, sampling type, rule and figure from the quantitative research week and its set reading on one page — each marked by what kind of claim it is, and whose.
How to read this page
Core definitions — the teaching material
KEY TERMS AS THE SUBJECT DEFINES THEM
| Term | Definition, quoted or closely paraphrased | Claim type |
|---|---|---|
| Population | "Total category of subjects that is the focus of attention in a particular research project (can be non-human)" | Source definition |
| Sample | "A number of subjects drawn from the population" | Source definition |
| Variables | "Characteristics of an item or individual; what you analyse when you use a statistical method" | Source definition |
| Data | "The different values associated with the variable" | Source definition — and the seventh incompatible definition of this word across six weeks |
| Measurement | "The act of measuring by assigning symbols, and numbers based on a set of rules" | Source definition |
| The reliability–validity link | Measurement "must be reliable in order to claim validity of findings" | Source requirement |
Full treatment, including the conflicts each definition creates with other weeks, at the linked pages below.
Sampling — the six types
SAMPLING TYPES AS NAMED IN THE TEACHING MATERIAL
| Type | What the source says | Usable? |
|---|---|---|
| Purposive | "Selecting particular respondents because of certain attributes or based on their particular ability to contribute to your purpose" | Yes — the definition distinguishes it |
| Random | A selection based on chance | Not distinguished from the next row |
| Simple random | "A random operation based on a chance process of some kind" | Not distinguished from the previous row |
| Stratified | Sampling within subgroups so each is represented | Yes |
| Systematic | "Taking an observation at regular intervals e.g. every 5th person. This is best if the list from which you are sampling is in random order but can cause problems when there is some regularity or pattern in the list" | Yes — and the caveat is the most useful sentence in the set |
| Cluster | Sampling whole groups rather than individuals | Yes |
Quota, judgement and self-selected sampling are named elsewhere in the material as bare labels with no definitions.
The full boundary is at sampling methods in research, and the question the source asks on its own slide and never answers is at how large should a sample be.
Bias — the teaching material and the set reading together
BIAS
| Item | Statement | Source |
|---|---|---|
| The most common bias | Non-response. Respondents choose whether to participate; if non-responders hold different views, the result is biased | Teaching material |
| What bias is | "A statistic is biased if the value of the statistic tends to be wrong (or more precisely, if the expected value — the average value from many samples drawn using the same sampling method — is not the same as the population value)" | Set reading |
| A typical bias source | Age or socioeconomic status — people with extreme values on these tend not to take part | Set reading |
| Compliance | "The proportion of people contacted who end up as subjects" | Set reading |
| An acceptable compliance rate | A stated percentage, reported as what journal editors in sport and exercise science were happy with | Set reading — not a project research threshold |
| Group bias | Failure to randomise subjects to groups means a result may reflect the group difference rather than the treatment | Set reading |
The teaching material states one bias. The set reading supplies the definition and the mechanism.
Study design — from the set reading
Descriptive study
- Subjects usually measured once
- Establishes only associations between variables
- Needs a much larger sample — the article says hundreds or thousands
- Most project research is this
Experimental study
- Subjects measured before and after a treatment
- Establishes causality
- May need far fewer subjects, especially a crossover design
- Rarely available in project research
THE THREE CONTROLS ON BIAS, AND WHAT EACH PROTECTS
| Control | Protects | Lost without it |
|---|---|---|
| Random selection from the population | That your sample resembles the population | The right to generalise beyond the people you studied |
| Random assignment to groups | That groups differ only by the treatment | The right to attribute a difference to the treatment |
| Blinding | That knowing the treatment does not create the effect | The right to separate the treatment from the expectation of it |
Arrangement is this library's; the content is the set reading's. Full treatment at bias control, randomisation and blinding.
What to measure — from the set reading
- Characteristics of the subjects — enough to identify the population they were drawn from.
- The independent and dependent variables defining the research question. The question fixes the dependent variable; the independent variables are everything that could affect it.
- Mechanism variables, in experiments only — variables that explain how the treatment works rather than whether it did.
Data management — the teaching material
The material requires a proposal to say how data will be managed at three stages: while it is being gathered, once it is gathered and stored, and afterwards. It raises format, access and entry as decisions to be made at design time, and points at a national code for the responsible conduct of research for the retention obligations.
The reproduction, and the deletion that matters
Where each topic is treated in full
NAVIGATION
| Topic | Page |
|---|---|
| What quantitative research is, and its four taxonomies | What quantitative research is |
| Population, sample, variables, data | Population, sample, variables and data |
| Measurement and the reliability–validity link | Measurement and the basis of validity |
| The six sampling types and their defects | Sampling methods in research |
| Sample size, and why the material has no rule | How large should a sample be |
| Non-response and the causal chain behind it | Non-response and sampling bias |
| Why sample rather than study everyone | Whole population or sample |
| Managing data across three stages | Planning data management |
| Association against causation | Descriptive and experimental study designs |
| The only concrete size guidance in the dataset | Sample size in quantitative studies |
| Variable selection and the restrict-or-measure choice | Choosing what to measure |
| Randomisation, blinding and what each protects | Bias control: randomisation and blinding |
What to carry forward
- Two sources on one page. The teaching material supplies vocabulary; the set reading supplies procedure and every number — and its numbers belong to sport and exercise science.
- Six sampling types named, no procedure for any of them, no sampling frame mentioned anywhere. You have the vocabulary and not the method.
- A descriptive study establishes only associations. An experiment establishes causality. Most project research is descriptive.
- Bias is a property of your method, not your result — which is why the whole defence sits at design time.
- The one definition you will most need, the confidence interval, exists in the set reading and was deleted from the notes that reproduce it.
Frequently asked questions
Why does this page separate the teaching material from the set reading?
Because they are different kinds of source and the difference changes how much weight a claim carries. The set reading is a published article from sport and exercise science, and it is clearer and more quantified than the week that links to it — which makes it easy to mistake for what the subject taught.
Can I use the sample-size figures from the set reading?
Not as standards. They were derived for studies of athletes and physiological measures, and transferring them to a project management study needs a justification neither the article nor the teaching material supplies. Use the reasoning about why descriptive studies need larger samples; do not carry the numbers.
Which sampling type should I use?
The material gives no criterion for choosing between the six, which is one of the four things it does not supply. What it does give — the systematic sampling caveat about list order — is the most useful single sentence in the set.
Where do I find the confidence interval definition?
Not in the teaching material. It exists in the set reading and was one of five passages deleted when the study notes reproduced that article. You will need a statistics source, and the material that depends on the term is still there without it.
Is this page a substitute for the detailed pages?
No. A reference table can carry definitions and lists; it cannot carry the conflicts, the gaps and the provenance rules that make each item safe to use. Use this page to find things and the linked pages to rely on them.
References and source attribution
- The supplied teaching source: weekly study notes, slide decks and assessment activities for a master's-level research methods subject in project management. Author, institution and year not stated in the supplied files.
- Hopkins 2000, 'Quantitative Research Design', a sport and exercise science web journal, vol. 4, issue 1, approximately 4,318 words — the Week 8 set reading. Retained as a published bibliographic citation; the journal, the reviewer and all institutional affiliations are scrubbed per the library's naming rules.
Suggested questions for Ask KEVOS
- What are the six sampling types and how do they differ?
- How do I know whether my study can claim a cause?
- What does the quantitative research week actually define?
- Which figures on this page can I reuse in my own study?
- What does the material say about managing research data?