Quantitative analysis is the use of statistical or mathematical models to present reality in a numerical view (Ghauri et al, 2020). It uses quantitative data for the analysis which is focused on numbers and thus this type of analysis is well used in topics around mathematics, finance, economics and business studies.
Quantitative analysis is well used in research seeking to determine a trend or test a hypothesis and theory. This type of numerical data can present a less biased or unobjective view on a particular topic versus qualitative data given that it provides a more simplistic view. It could be said that quantitative analysis is used to present the fact rather than the opinion (Vogt, 2011). However quantitative analysis will only be reliable if it is taken from a reliable source, with many financial/ economics studies basing their data collection on trusted sources such as Bloomberg, Office of National Statistics or other agencies.
Quantitative analysis can form part of any research seeking to test a hypothesis or theory, showing a correlation or relationship between datasets or showcase a trend over time among others. Having a better understanding then allows the researcher to make future predictions based on the understanding of behaviour (Walliman, 2017). For instance if the analysis uncovered that every 1% increase in UK GDP led to a 0.5% increase in the FTSE 100 indices then the researcher could use forecasted GDP growth from the IMF to predict the movement of the FTSE 100.
In financial topics quantitative analysis forms the basis for the technical analysis which investors would undertake to predict movements in share prices and the wider market and so is also of interest to researchers looking to understand how the financial markets function. Looking at the example above the relationship between UK GDP and the FTSE 100 is fact and proven based on the data used. However what quantitative analysis fails to do is explain why this relationship exists. This is when qualitative analysis would be included to question participants over their views and come to a consensus. Quantitative analysis could also be used to quantify social data such as qualitative text which could be broken down by themes and categories with quantitative analysis used to determine the key trends based on number of mentions (Bernard & Bernard, 2013).
Many business, government agencies and groups use quantitative data as a way to communicate with stakeholders and showcase performance. For example Deliveroo may use a quantitative metric to show average order size as a way to showcase their performance to shareholders, or may track average delivery time as a metric to show customers the efficiency of the business versus competition. Quantitative analysis can be used to form Key Performance Indicators (Bell et al, 2018). All of this provides a benefit to researchers who have access to accurate, reliable and detailed publicly-available quantitative data for their own analysis.
Assume a study which seeks to find the determinants of stock market movements for the FTSE 100. To answer this question a OLS regression model can be considered with the annual movement of the FTSE 100 the dependant variable. Explanatory variables can come from a number of sources such as GDP growth, inflation, unemployment statistics from the ONS, or money supply growth from the Bank of England (Schwab, 2013).
Quantitative data presents the researcher with so much choice to test specific explanatory variables and if those fail to remove them a re-run the test with other variables. Though this ease will only be seen in topics where there is a high level of secondary data publicly available. The data is easy to obtain in this case and easy to analyse a large amount of data quickly using statistical programmes such as Stata (Patten & Newhart, 2017). Within research quantitative analysis is able to test a hypothesis or theory.
Key advantages of quantitative data are in the speed of data collection and ability to use tools such as Excel, Stata, SPSS and other computer-based programmes to run the analysis. It makes it a much more efficient way of analysis versus qualitative which may require time-consuming thematic analysis and coding techniques to see key themes within the dataset.
For quantitative analysis simple methods such as correlation, mean, mode and range could all be initially done to show trends within the data as well as test the quality of the data collected. For example, having a mean of 24 but a range of 10-150 suggests that there could be some anomalies within the dataset which could be exaggerating the mean. This allows the researcher to pick out those specific results and check them.
Another advantage of quantitative data is that it allows for anonymity and thus protects the identity of participants within the final analysis. There are no qualitative answers used which could potentially identify the participant from the sample (Bell et al, 2018).
The main disadvantage with quantitative data though is that it provides a simplified conclusion over the data. For instance a workplace could run a short-survey with closed questions to determine employee satisfaction. Using a Likert Scale question all employees will market the business out of 1-10 allowing the HR team to come to an average with all responses. Thus the benefits of this analysis is that it is quick and easy to collect with closed questions allowing the survey to be self-administered by the participants with less help than may be required with open-ended questions (Bell et al, 2018). Given that this analysis provides an absolute response in terms of an average number, this can then be compared with previous surveys to see the long-term trend (Hair et al, 2019). For instance scoring an average of 7.2 in 2020 after 6.8 in 2019 and 6.5 in 2018 shows a continued improvement with a like-for-like dataset. However what quantitative data alone fails to provide is the reason as to why the participant scored the number they did. It provides no detail into the response which may give the business more insight into what they have done well to improve this score and what may need to be done in the future to improve this further towards 10.
Secondly quantitative data is only beneficial if the sample is large enough to act as a reasonable estimate of the sampled population. For secondary data from the IMF/ ONS the research trusts that these agencies have put in significant work to come calculate their figures and takes them as a representation of the population i.e. UK economy. However for primary data collection the quantitative data must accurately portray the chosen population. For instance in a company with 500 employees equally split into 5 departments the research strategy must use a sampling technique which collects data from an equal proportion of each department and overall a good response rate from the overall workforce to ensure that the agglomerated results are reliable. So a disadvantage is that quantitative data still requires the researcher to ensure that sampled population accurately represents the total studied population otherwise bias could be present within the data and discredit the results. Also the time period chosen for quantitative data can also impact the results and what is classed as fact. Tracking the performance of the FTSE 100 versus UK GDP growth over the past 5-years to determine the correlation will give a different result than tracking the same variables over a 10-year or 20-year period. Researchers must be weary of this when making comparisons between studies using quantitative analysis.
Finance, economic, business and mathematics can be seen as the main fields to benefit from the use of quantitative data given the availability of historical data from trusted sources. However quantitative data can also play a central role in sub-topics of business including management whereby methodological choices can be made to collect quantitative data through surveys or questionnaires, with responses quantified and statistically assessed by the researcher.
For simplified answers quantitative data can be extremely useful is for instance determining the % of people who agree with a statement versus disagree or the % of people who have purchased a specific product and so many other fields of study can benefit from this. However as stated quantitative analysis is based on closed answers which only provide one dataset. Fields of study which are focused on behaviour, or psychology could use quantitative analysis to state the facts, however this would need to them be interlinked with qualitative analysis to provide the detail into the ‘WHY’, delving into the reasoning behind specific customer behaviour etc.
In terms of a template quantitative analysis would be completed with either primary or secondary data. Primary data is what the researcher collects themselves and could be done through surveys, questionnaires. As noted above with the business example a company could run a business-wide employee survey to collect data on their employee satisfaction, happiness, motivation among others. When all this data is collected analysis can be run to determine the key trends, potentially using a previous survey as a comparison. Relationships could also be tested such as the relationship between employee satisfaction and employee engagement among others. The business could also bring in other forms of data such as average salary to then find additional relationships (Zikmund et al, 2013).
Secondary data uses data that has already been collected by another agent. The researcher would take this data and use such to answer their research questions, prove their theory or hypothesis. There are a range of techniques which have been discussed to do this including regression models, correlation analysis among others (Hair et al, 2019).
Bell, E., Bryman, A., & Harley, B. (2018). Business research methods, Oxford: Oxford university press.
Bernard, H. R., & Bernard, H. R. (2013). Social research methods: Qualitative and quantitative approaches, London: Sage.
Ghauri, P., Grønhaug, K., & Strange, R. (2020). Research methods in business studies, Cambridge: Cambridge University Press.
Hair Jr, J. F., Page, M., & Brunsveld, N. (2019). Essentials of business research methods, London: Routledge.
Patten, M. L., & Newhart, M. (2017). Understanding research methods: An overview of the essentials, London: Taylor & Francis.
Schwab, D. P. (2013). Research methods for organizational studies, London: Psychology Press.
Vogt, W. P. (Ed.). (2011). SAGE quantitative research methods, London: Sage.
Walliman, N. (2017). Research methods: The basics, London: Routledge.
Zikmund, W. G., Carr, J. C., & Griffin, M. (2013). Business Research Methods, London: Cengage Learning.
Essay Writing Service UK provide a number of services for students who need a little extra push towards getting the results they need. It's easy to get a price and place an order online by clicking here, or alternatively feel free to send us an email or call one of our consultants who can discuss your requirements over the phone on 0203 011 0100.