hypothesis

The Steps of Quantitative Research

There are 11 stages of quantitative research: 1. Start with a theory; 2: develop a hypothesis; 3: Research design; 4: operationalise concepts; 5: select a research site; 6: sampling 7: data collection; 8: data processing; 9: data analysis; 10: findings/ conclusion; 11: publishing results.

Quantitative research is a strategy which involves the collection of numerical data, a deductive view of the relationship between theory and research, a preference for a natural science approach (and for positivism in particular), and an objectivist conception of social reality.

It is important to note that quantitative research thus means more than the quantification of aspects of social life, it also has a distinctive epistemological and ontological position which distinguishes it from more qualitative research.

11 stages of quantitative research

Theory

Hypothesis
Research Design
Operationalising concepts

Selecting a research site
Selecting a sample of respondents
Data collection

Data processing
Data analysis
Findings/ conclusions

publishing results

a flow chart showing the 11 stages of quantitative research design from hypothesis through data collection to publishing results.

Theory

The fact that quantitative research starts off with theory signifies the broadly deductive approach to the relationship between theory and research in this tradition. The sociological theory most closely associated with this approach is Functionalism, which is a development of the positivist origins of sociology.

One’s theoretical starting point may give rise to research questions. For example, Marxist-leaning sociologists of education have been interested in researching the effects of cultural capital on educational achievement.

Some quantitative research derives a hypothesis from the theoretical starting point to test. A hypothesis is a specific testable statement about how one or more independent variable will impact a dependent variable.

However, a great deal of quantitative research does not entail the specification of a hypothesis, and instead theory acts loosely as a set of concerns in relation to which social researcher collects data. The specification of hypotheses to be tested is particularly likely to be found in experimental research but is often found as well in survey research, which is usually based on cross-sectional design.

Research design

The third step in quantitative research entails the selection of a research design which has implications for a variety of issues, such as the external validity of findings and researchers’ ability to impute causality to their findings.

Operationalising concepts

Operationalising concepts is a process where the researcher devises measures of the concepts which she wishes to investigate. This typically involves breaking down abstract sociological concepts into more specific measures which can be easily understood by respondents.

For example, ‘social class’ can be operationalised into ‘occupation’ and ‘strength of religious belief’ can be measured by using a range of questions about ‘ideas about God’ and ‘attendance at religious services’.

Selection of a research site

With laboratory experiments, the site will already be established, in field experiments, this will involve the selection of a field-site or sites, such as a school or factory, while with survey research, site-selection may be more varied. Practical and ethical factors will be a limiting factor in choice of research sites.

Of course some research may take place over multiple sites.

Selection of respondents

Step six involves ‘choosing a sample of participants’ to take part in the study – which can involve any number of sampling techniques, depending on the hypothesis, and practical and ethical factors. If the hypothesis requires comparison between two different groups (men and women for example), then the sample should reflect this.

Step six may well precede step five – if you just wish to research ‘the extent of teacher labelling in schools in London’, then you’re pretty much limited to finding schools in London as your research site(s).

Data collection

Step seven, data collection, is what most people probably think of as ‘doing research’. In experimental research this is likely to involve pre-testing respondents, manipulating the independent variable for the experimental group and then post-testing respondents.

In cross-sectional research using surveys, this will involve interviewing the sample members by structured-interview or using a pre-coded questionnaire. For observational research this will involve watching the setting and behaviour of people and then assigning categories to each element of behaviour.

Processing data

This means transforming information which has been collected into ‘data’. With some information this is a straightforward process – for example, variables such as ‘age’, or ‘income’ are already numeric.

Other information might need to be ‘coded’ – or transformed into numbers so that it can be analysed. Codes act as tags that are placed on data about people which allow the information to be processed by a computer.

Data analysis

In step nine, analysing data, the researcher uses a number of statistical techniques to look for significant correlations between variables, to see if one variable has a significant effect on another variable.

The simplest type of technique is to organise the relationship between variables into graphs, pie charts and bar charts, which give an immediate ‘intuitive’ visual impression of whether there is a significant relationship, and such tools are also vital for presenting the results of one’s quantitative data analysis to others.

In order for quantitative research to be taken seriously, analysis needs to use a number of accepted statistical techniques, such as the Chi-squared test, to test whether there is a relationship between variables. This is precisely the bit that many sociology students will hate, but has become much more commonplace in the age of big data!

Findings and conclusions

On the basis of the analysis of the data, the researcher must interpret the results of the analysis. It is at this stage that the findings will emerge: if there is a hypothesis, is it supported? What are the implications of the findings for the theoretical ideas that formed the background of the research?

Publishing Results

Finally, in stage 11, the research must be written up. The research will be writing for either an academic audience, or a client, but either way, a write-up must convince the audience that the research process has been robust, that data is as valid, reliable and representative as it needs to be for the research purposes, and that the findings are important in the context of already existing research.

Once the findings have been published, they become part of the stock of knowledge (or ‘theory’ in the loose sense of the word) in their domain. Thus, there is a feedback loop from step eleven back up to step one.

Video Summary….

The presence of an element of both deductivism (step two) and inductivism is indicative of the positivist foundations of quantitative research.

Signposting and Related Posts

Quantitative research is one the major approaches to research methods alongside Qualitative research.

For related posts please see my page on Research Methods.

This post is probably quite advanced for most students of A-level sociology and so best treated as extension work for 16-19 year olds, the material here is really moving up towards undergraduate degree level.

Sources/ Find out More about Quantitative Research

Bryman (2016) Social Research Methods

Experiments in Sociology – An Introduction

Experiments aim to measure the effect which an independent variable (the ’cause’) has on a dependent variable (‘the effect’).

The key features of an experiment are control over variables, precise measurement, and establishing cause and effect relationships.

In order to establish cause and effect relationships, the independent variable is changed and the dependent variable is measured; all other variables (known as extraneous variables) are controlled in the experimental process.

Different types of experiment

There are three main types of experimental: The Laboratory experiment, the field experiment and the comparative method.

Laboratory Experiments take place in an artificial, controlled environment such as a laboratory
Field Experiments – take place in a real world context such as a school or a hospital.

The comparative method – involves comparing two or more similar societies or groups which are similar in some respects but varied in others, and looking for correlations.

The Key Features of the Experiment

It’s easiest to explain what an experiment is by using an example from the natural sciences, so I’m going to explain about experiments further using an example used from biology

NB – You do need to know about the scientific method for the second year sociology theory and methods part of the course ( for an overview of theories and methods click here), so this is still all necessary information. I’ll return to the use of laboratory and field experiments in sociology (/ psychology) later on…

An example to illustrate the key features of an experiment

If you wished to measure the precise effect temperature had on the amount* of tomatoes a tomato plant produced, you could design an experiment in which you took two tomato plants of the same variety, and grow them in the same greenhouse with same soil, the same amount of light, and the same amount of water (and everything else exactly the same), but grow them on different heat pads, so one is heated to 15 degrees, and the other 20 degrees (5 degrees difference between the two).

You would then collect the tomatoes from each plant at the same time of year** (say in September sometime) and weigh them (*weighing would be a more accurate way of measuring the amount of tomatoes rather than the number produced), the difference in weight between the two piles of tomatoes would give you the ‘effect’ of the 5 degree temperature difference.

You would probably want to repeat the experiment a number of times to ensure good reliability, and then average all the yields of tomatoes to come up with an average difference.

After, say, 1000 experiments you might reasonably conclude that if you grow tomatoes at 20 degrees rather than 15 degrees, each plant will give you 0.5 kg more tomatoes, thus the ’cause’ of the 5 degree temperature increase is 0.5 Kg more tomatoes per plant.

In the above example, the amount of tomatoes is the dependent variable, the temperature is the independent variable, and everything else (the water, nutrients, soil etc. which you control, or keep the same) are the extraneous variables.

** of course, you might get different results if you collected the tomatoes as they ripened, but for the sake of controlling extraneous variables, you would need to collect all the tomatoes at the same time.

The Role of Hypotheses in Experiments

Experiments typically start off with a hypothesis which is a theory or explanation made on the basis of limited evidence as a starting point for further investigation. A hypothesis will typically take the form of a specific, testable statement about the effect which one or more independent variables will have on the dependent variable.

The point of using a hypothesis is that it helps with accuracy, focussing the researcher in on testing the specific relationship between two variables precisely, it also helps with objectivity (see below).

Having collected the results from the above experiment, you might reasonably hypothesise that ‘a tomato plant grown at 25 degrees compared to 20 degrees will yield 0.5K.G. more tomatoes’ (in fact a proper hypothesis would probably be even tighter than this, but hopefully you get the gist).

You would then simply repeat the above experiment, but heating one plant to 20 degrees and the other to 25 degrees, repeat 1000 (or so times) and on the basis of your findings, you could either accept or reject and modify the hypothesis.

Experiments and Objectivity

A further key feature of experiments are that they are supposed to produce objective knowledge – that is they reveal cause and effect relationships between variables which exist independently of the observer, because the results gained should have been completely uninfluenced by the researcher’s own values.

In other words, somebody else observing the same experiment, or repeating the same experiment should get the same results. If this is the case, then we can say that we have some objective knowledge.

A final (quick) word on tomato experiments, and objective knowledge…

NB – the use of tomato plants is not an idle example to illustrate the key features of the experiment – nearly everyone eats tomatoes (unless you’re the minority of Ketchup and Dolmio abstainers) – and so there’s a lot of profit in producing tomatoes, so I imagine that hundred of millions, if not billions of dollars has been spent on researching what combinations of variables lead to the most tomatoes being grown per acre, with the least inputs…. NB there would have to be a lot of experiments because a lot of variables interact, such as type of tomato plant, altitude, wave length of light, soil type, pests and pesticide use, as well as all of the basic stuff such as heat, light, and water.

A woman picks tomatoes at a desert experimental farming greenhouse.

The importance of objective, scientific knowledge about what combination of variables has what effect on tomato production is important, because if I have this knowledge (NB I may need to pay an agricultural science college for it, but it is there!) I can establish a tomato farm and set up the exact conditions for maximum production, and predict with some certainty how many tomatoes I’ll end up with in a season…(assuming I’m growing under glass, where I can control everything).

The advantages of the experimental method

It allows us to establish ’cause and effect relationships’ between variables.

It allows for the precise measurement of the relationship between variables, enabling us to make accurate predictions about how two things will interact in the future.
The researcher can remain relatively detached from the research process, so it allows for the collection of objective knowledge, independent of the subjective opinions of the researcher.
It has excellent reliability because controlled environments allow for the exact conditions of the research to be repeated and results tested.

Disadvantages of the experimental method

(Why it may not be applicable to studying society as a whole or even individual humans…)

There are so many variables ‘out there’ in the real world that it is impossible to control and measure them all.
Most social groups are too large to study scientifically, you can’t get a city into a laboratory to control all it’s variables, you couldn’t even do this with a field experiment.

Human beings have their own personal, emotionally charged reasons for acting, which often they don’t know themselves, so they are impossible to measure in any objective way.
Human beings have consciousness and so don’t just react in a predictable way to external stimuli: they think about things, make judgements and act accordingly, so it’s impossible to predict human behaviour.
There are also ethical concerns with treating humans as ‘research subjects’ rather than equal partners in the research process.

Experiments – Key Terms

Hypothesis – a theory or explanation made on the basis of limited evidence as a starting point for further investigation. A hypothesis will typically take the form of a testable statement about the effect which one or more independent variables will have on the dependent variable.

Dependent Variable – this is the object of the study in the experiment, the variable which will (possibly) be effected by the independent variables.

Independent variables – The variables which are varied in an experiment – the factors which the experimenter changes in order to measure the effect they have on the dependent variable.

Extraneous variables – Variables which are not of interest to the researcher but which may interfere with the results of an experiment

Experimental group – The group under study in the investigation.

Control group – The group which is similar to the study group who are held constant. Following the experiment the experimental group can be compared to the control group to measure the extent of the impact (if any) of the independent variables.

Laboratory experiments: definition, explanation, advantages and disadvantages

Field experiments: definition, explanation, advantages and disadvantages.

Useful Introductory Sources on Experiments

Simply Psychology – The Experimental Method