Data Interpretation

6 Key excerpts on "Data Interpretation"

• 

  eBook - ePub

  SQL for Data Analytics

  Harness the power of SQL to extract insights from data, 3rd Edition

  • Jun Shan, Matt Goldwasser, Upom Malik, Benjamin Johnston(Authors)
  • 2022(Publication Date)
  • Packt Publishing

    (Publisher)

  Raw data is a group of values that you can extract from a source. It becomes useful when it is processed to find different patterns in the data that was extracted. These patterns, also referred to as information, help you to interpret the data, make predictions, and identify unexpected changes in the future. This information is then processed into knowledge.

  Knowledge is a large, organized collection of persistent and extensive information and experience that can be used to describe and predict phenomena in the real world. Data analysis is the process by which you convert data into information and, thereafter, knowledge. Data analytics is when data analysis is combined with making predictions.

  There are several data analysis techniques available to make sense of data. One of them is statistics, which uses mathematical techniques on datasets.

  Statistics is the science of collecting and analyzing a large amount of data to identify the characteristics of the data and its subsets. For example, you may want to study the medical history of a country to identify the most common causes of illness-related fatality. You can also dive deeper into some subgroups, such as people from different geographic areas, to identify whether there are specific patterns for people from each area.

  Statistics is performed on datasets. Different data inside datasets have different characteristics and require different methods of processing. Some types of data, such as name and label, may be qualitative , which means it provides descriptive information. Others, such as counts and amounts, are quantitative , which means you can perform numerical operations, such as addition or multiplication, on these values. For example, the following dataset is a collection of some biomedical information collected across a set of patients:

  Figure 1.1: Healthcare data

  In this case, the unit of observation for the dataset is an individual patient because each row represents an individual observation, which is a unique patient. There are 10 data points, each with 5 variables. Three of the columns, Year of Birth , Height , and Number of Doctor Visits in the Year 2018 , are quantitative because they are represented by numbers. Two of the columns, Eye Color and Country of Birth

  Sign up to read

  Learn more about book
• 

  eBook - ePub

  Research Skills for Management Studies

  • Alan Berkeley Thomas(Author)
  • 2004(Publication Date)
  • Routledge

    (Publisher)

  12 Data analysis and interpretation

  The range of techniques available for the analysis and interpretation of both quantitative and qualitative data is enormous. A full account of statistical methods alone would fill many volumes. The purpose of this chapter is therefore to provide an overview of the main methods of analysis and to indicate their potential applications rather than to give detailed instruction in how particular statistics are calculated or how to undertake textual interpretation. Guidance to sources dealing with these topics in depth is given at the end of the chapter.

  Basic processes: describing and explaining

  Once the dataset has been constructed, its contents must be analysed and interpreted. The accumulated body of data does not speak for itself. At this stage the researcher has to confront two key problems:

  1. How can the data be transformed from an extensive assortment of raw materials into a concise and meaningful description of what has been observed?
  2. Once a valid and coherent descriptive account has been constructed, how can it be connected with the problem field? Have new descriptive materials been created? Have theoretical expectations been tested? Has a new theory or causal model been constructed?

  These questions must, of course, be tackled in relation to the overall objectives of the study, but the general aim of analysis and interpretation is to enable the analyst to ‘see the wood for the trees’. The analyst seeks structure in the data: generalities and commonalities within all the variety and the differences that are displayed in the dataset, and linkages, patterns and connections among elements, variables, categories and types.

  Data can mount up alarmingly as a study progresses: datasets may swell and field notes bulge to the point where it may seem impossible to make any sense out of the material. The data must undergo data reduction in order to condense and summarize them so that they are meaningful in terms of the study’s objectives.

  Sign up to read

  Learn more about book
• 

  eBook - ePub

  Interaction Design

  Beyond Human-Computer Interaction

  • Helen Sharp, Jennifer Preece, Yvonne Rogers(Authors)
  • 2019(Publication Date)
  • Wiley

    (Publisher)

  For all data, but especially when dealing with large volumes of data (that is, Big Data), it is useful to look over the data to check for any anomalies that might be erroneous. For example, people who are 999 years old. This process is known as data cleansing, and there are often digital tools to help with the process. This initial analysis is followed by more detailed work using structured frameworks or theories to support the investigation. Interpretation of the findings often proceeds in parallel with analysis, but there are different ways to interpret results, and it is important to make sure that the data supports any conclusions. A common mistake is for the investigator's existing beliefs or biases to influence the interpretation of results. Imagine that an initial analysis of the data has revealed a pattern of responses to customer care questionnaires that indicates that inquiries from customers routed through the Sydney office of an organization take longer to process than those routed through the Moscow office. This result can be interpreted in many different ways. For example, the customer care operatives in Sydney are less efficient, they provide more detailed responses, the technology supporting the inquiry process in Sydney needs to be updated, customers reaching the Sydney office demand a higher level of service, and so on. Which one is correct? To determine whether any of these potential interpretations is accurate, it would be appropriate to look at other data such as customer inquiry details and maybe to interview staff. Another common mistake is to make claims that go beyond what the data can support. This is a matter of interpretation and of presentation. Using words such as many or often or all when reporting conclusions needs to be carefully considered. An investigator needs to remain as impartial and objective as possible if the conclusions are to be trusted

  Sign up to read

  Learn more about book
• 

  eBook - ePub

  Completing Your EdD

  The Essential Guide to the Doctor of Education

  • Iona Burnell, Jodi Roffey-Barentsen(Authors)
  • 2020(Publication Date)
  • Emerald Publishing Limited

    (Publisher)

  7

  ANALYSING AND INTERPRETING DATA

  Jim Crawley

  INTRODUCTION

  With appropriate, carefully planned, high-quality data analysis and interpretation, you will almost always get the best from your data and will take significant steps towards the answer/s to your research question/s and meeting your research objectives. Researchers usually find the process of analysing and interpreting the data they have gathered one of the most rewarding parts of the whole experience. This stage of your research should be exciting, informing, absorbing and fulfilling. From the moment your first piece of data has been collected, analysis and interpretation start to take place, even if at that early stage this takes place informally and mainly in your head. The early analysis and interpretation of data will give you a strong impression of the success (or otherwise) of the research to date. As the process continues, the stories from your data unfold. When data analysis is successful, the stories unfold naturally and clearly, and they will illuminate and bring your findings to life as you have planned, intended and hoped.

  There are, of course, also challenges with analysing and interpreting data. You may, like many researchers before you, feel weighed down under the pressure of analysing large (or small) quantities of complex data, and the stage of your research which was supposed to lead smoothly to your discussion and conclusions becomes a difficult situation where alterations, additions, shifts of emphasis and even changes of direction may need to be made. However well you prepare and organise for data analysis and interpretation, part of the excitement of carrying out research is that it can never be entirely predictable. It is highly likely that you will encounter at least some level of complication with this stage of research in just the same way as you may with others but resolving questions, reducing uncertainties and solving problems successfully with your data analysis and interpretation is an important step on the way to completing your thesis. Engaging in critically analytical discussions and revealing interesting and enlightening conclusions is a central part of doctoral work which will lead your thinking into coherence and originality, and it is through the stage of analysing and interpreting data that this will largely happen.

  Sign up to read

  Learn more about book
• 

  eBook - ePub

  Interaction Design

  Beyond Human-Computer Interaction

  • Yvonne Rogers, Helen Sharp, Jennifer Preece(Authors)
  • 2023(Publication Date)
  • Wiley

    (Publisher)

  data cleansing, and there are often digital tools to help with this process. This initial analysis is followed by more detailed work using structured frameworks or theories to frame the investigation.

  Interpretation of the findings often proceeds in parallel with analysis, but there are different ways to interpret results, and it is important to make sure that the data supports any conclusions. Imagine that an initial analysis of some customer care questionnaires has revealed a pattern of responses indicating that inquiries from customers routed through the Sydney office of an organization take longer to process than those routed through the Oslo office. This result can be interpreted in many different ways. For example, the customer care operatives in Sydney are less efficient, they provide more detailed responses, the technology supporting the inquiry process in Sydney needs to be updated, customers reaching the Sydney office demand a higher level of service, and so on. Which one is correct? To determine whether any of these potential interpretations is accurate, further data such as customer inquiry details and maybe staff interviews is needed. A common mistake is for the investigator's existing beliefs or biases to influence the interpretation of results (see Box 9.1 on bias).

  BOX 9.1

  Beware of Bias in Analysis and Interpretation

  Bias is an influence that can affect objective judgment and decision-making. Biases are formed because of the tendency of the brain to rapidly categorize new information and data connecting them with past experiences. It is natural to look for patterns and associations in the world so as to be prepared to act and behave accordingly, and this can lead to biases. They may be present in someone's thinking, and they may manifest in information or data. Some biases are conscious, e.g., preferring to work with women rather than with men, while others are unconscious. Biases influence how people interact with each other, how decisions are made, how people react to the design of an app or product, and how data is collected, analyzed, and interpreted.

  Sign up to read

  Learn more about book
• 

  eBook - ePub

  Integrating Analyses in Mixed Methods Research

  • Patricia Bazeley(Author)
  • 2017(Publication Date)
  • SAGE Publications Ltd

    (Publisher)

  3 Interpreting Data

  Chapter overview

  • The task of data analysis
  • An interpretive orientation to data and analysis
  • Interpreting statistical and non-numeric data sources – some cautionary notes
    • Cautions in interpreting numeric data and statistical tests
    • Interpreting text: beyond descriptive accounts
    • Keeping track of research decisions, activities and reflections
  • A framework for mixed methods analysis
    • Typological and dimensional frameworks for integrated analysis
  • A process-oriented logic model for integrated analysis
    • Starting points (resources) for mixed methods analysis
    • First level processes
    • Second level processes
    • Interpretive outcomes and applications
  • Concluding remarks
  • Further reading

  Interpreting data and drawing inferences from data is never a straightforward, cut and dried activity, but rather is subject to the vagaries of design decisions, administrative choices, procedural fashions, and contextual influences. Capacity for data analysis involves being able to view the world from the position of another, combined with skills in critical thinking that are applied to the interrogation and interpretation of data. Inferences drawn should make sense to those who contributed the data, to other researchers working with that or similar data, and in the light of what is already known – to which they should, hopefully, add further insights.

  Specific strategies for working with, analysing, and integrating mixed methods data are the subject of Part 2 of this book. The topic of generating and supporting conclusions built from mixed methods data is covered in Part 3

  Sign up to read

  Learn more about book