Paper Example on Data Visualization and Programming

Introduction

Data visualization means the presentation of data in a visual form such as graphs and pictorial format. It assists an individual in decision making by seeing the analytics visually so that they can grasp new patterns and difficult concepts quickly. Through interactive visualization of the data, you can take the idea of display a step further by enhancement of the technology to drill down into charts and graphs for a more accurate data processing and changing how a person sees and processes data. The concept of data visualization has been in practice for several centuries, and this draws back from the use of maps and graphs in the early 17th century to the use of a pie chart in the 18th century. The use of technology has greatly lit the fire in regards to data visualization. Computer and other electronic devices have made it possible to process and present large amount of information at a very high speed. In the modern world, data visualization has become a highly evolving part of science and art, which is prone to change the corporate landscape over the years.

Literature Review

Information visualization is described as the accepted term used in the field of graphical communication where data visualization is generated. Underpinning the various data presentations, designs, and data analysis in the research are well-established principles of statistical graphics and human perception. Christensen (2017) wrote an extensive research paper on the field where visual elements of communication such as shape, color, and size used to measure the effectiveness of data communication and quantitative information analysis. Besides, Christensen, J. (2017) continues to look at the language of visualization technology, and information visualization generally looks at the subject from the standpoint of perceptual science. The research done on this particular subject is groundbreaking because of its approach to visual literacy and information presentation. The data analysis field is extensive and continuously evolving with the advancement of modern technology.

Differences between Data Visualization and Data Analytics

Data visualization is described as the presentation of data or information in a visual context in that the trends and patterns inherent in the data visualization process can be explicit. These trends and patterns, however, may not be precise in text-based data. Most of the modern tools that have been used data visualization process can filter the data so that the resulting data can be manipulated as per user perspective. On the other hand, the traditional forms of visualization, such as tables, column charts, and graphs, have been ousted in the modern world by the use of 3D visualization patterns. Data analytics has gone further to discover and identify the patterns and trends that exist in the field of data analysis. Even though data visualization enables an individual to observe and make sense from the data, it does not provide the required and complete picture of the intended information. The effectiveness of data visualization greatly relies on the data or information that is used kin relaying of the visualization data in the first place. As a result, the feeding of the visualization engine with incorrect data and information will result in erroneous, half-bake, or obsolete visualization of the data.

Data Visualization and Programming

Kumar& Kirthika (2017) argues that with the increasing demand for new ways of visualizing data, several standards, and guidelines to support the creation of visualized data has been put forth. There is an advanced body of that purely working and focusing on data visualization and the existing challenges that this field faces that is not common in the interactive system evaluation. This can be improved by how the experts in the field of information systems organize programming knowledge. Research establishes that knowledge of programming is organized in a broader conceptual structure instead of syntax, and this can improve the data visualization process. Golfarelli & Rizzi (2019) propose that they can organize their work and knowledge in what the scholar terms as plan. Plans are defined as the procedure of achieving a given, such as the computation of a sum. These programs are presented as codes with gaps for specific detailed information.

Data visualization and programming are, therefore, related because most of the visualizations programs and patterns are programmed to attain the desired output that will be presentable. Most of the programming knowledge has advantages but has left a lot of gaps in regards to their applications. Therefore data visualization, in addition to the programming languages and codes used, are more feasible to data analytics as compared to pure programming.

Importance of Data Visualization Compared to Programming in Data Analytics

According to Kumar& Kirthika (2017), because of how human being processes information and data using either graphs or charts to visualize a considerable amount of data, it is easier to present information as compared to the poring over reports and spreadsheets. Data visualization as a method of representing data is an easy way to convey the various concept universally. This can be experimented using different scenarios and making adjustments where required.

Data visualization, as a tool of data analytics, can also:

• Identify relevant areas that need proper improvement and attention
• Assist you to clarify which factors can influence the customer's satisfaction and a result it a major too in advertisements
• It helps an individual to understand which type of product is based on being placed at what position to attract the attention of the public.
• It can predict the sales volume concerning the quality of the visualization process.

Methodology

The main challenge in the evaluation of the data visualization processes is the complexity of the process and the difficulty to replicate the condition under which this system is used (Kumar, & Kirthika, 2017; Golfarelli & Rizzi, 2019). To mitigate the common pitfalls related to data visualization, the researchers use various methods in data collection and analysis supported by the previous studies. There is no globally applied system of evaluating data visualization processes, proper care has been taken to focus on the scenarios that are relevant to the study. The main two scenarios considered in the evaluation of the visualization process are the evaluation of the user experience and the assessment of the user performance.

Research Design

In the evaluation of data visualization integrity, three ways of visualizing football data interactively are compared in three different forms of interactive prototypes. The research will adopt a descriptive research design because the goal of the study is to describe the attitudes and preferences of the users towards the feasibility of data visualization tools and programming for data analytics. The prototypes generally represent the fantasy of football because the study only focuses on the visual representation of the player data. In this study, three prototypes will be evaluated: table with raw data, table with inline charts as well as a treemap.

Sampling and Data Collection

The study will be based on both primary data and secondary data. Primary data will be collected from a randomly selected sample of 30 respondents using data visualization tools and programming for data analytics. Secondary data will be collected from published researchers, scholarly journals and industry reports. Random sampling method was chosen to avoid bias and a large sample size of 30 respondents chosen to maximize the sample representativeness of the population. The sample will be drawn from data visualization companies across the country. The researcher will first write a letter seeking permission to interview the respondents after which, the randomly selected respondents will be approached with the informed constant form which they will fill after signing the form as required by the institutional review board (IRB) as part of the ethical consideration. The respondents will be required to participate anonymously to protect them. The researcher will explain to the respondents why the data is collected, and how it will be used. All data collected will be used solely for the research purpose and will be stored in a password-protected retrieval system. Six months after the study is concluded, the data will be deleted from the system.

Research Instrument

Development of Research Instrument and Pilot Study

Both qualitative and quantitative data were collected. The researcher will first develop a research instrument (questionnaires) adapted from various validated data visualization and programming models. The research instrument was mainly comprised of Likert type structured questionnaires with five-point scales from unlikely (1), least likely (2), neutral (3), likely (4), most likely (5). The goal is to examine the attitudes towards data visualization tools and programming tools for data analytics. These scales will be used to rate the respondent's degree to which they agree to disagree with specific statements about the two data analytics tools. The scale is adapted from Fedak (2019). The model for analyzing the data gathered through the Likert scale is the inverse square of distances (ISOD) model to estimate the ability from the respondent's responses on the Likert scale. This model will be effective in resolving issues related to the use of Likert scales such as coarseness, appropriateness of usage of parametric tests, leniency or stringency bias, and central tendency error (Purnell, 2009). The model will evaluate the data visualization tools in terms of their capability to:

1. Process multiple types of incoming data,
2. Apply various filters to adjust the results
3. Interact with the data sets during the analysis
4. Connect to other software to receive incoming data or provide input for them
5. Provide collaboration options for the users

Identification of the Variables

To ensure that there is accuracy in the data presentation analysis, each of the variables to be analyzed was identified in the figure above. Data visualization that is represented by the three prototypes described as the independent variables (IV) that have been used throughout the evaluation of the data visualization process. The dependent variable (DV), which was the user experience and performance, was measured against the independent variables. The figure below shows the analysis of the dependent, dependent and controlled variables use in the analysis

The Evaluation Method Used in This Data Visualization Process.

To ensure that there were fairness and valid judgments on the three prototypes, all the information was evaluated against a specific matrix utilizing a variety of evaluation methods. The use of the mixed techniques helps in capturing both the subjective and objective information so that they are used to measure the impact of each of the visualization technique and their effects on the user experience and performance

Research Methods

Quantitative Method

The quantitative data collection method generally relies on the structured data collection method and random sampling that has a diverse experience with the predetermined categories of responses. The quantitative methods that were used in the analysis of data visualization taking the three prototypes as the case study are:

Time Tasks

Time task is the scripted tasks or questions that are asking the participants to present a prototype in a given manner and a controlled way. Each of the functions provided reflects the real scenario, such as making a comparison and a selection based on the fantasy player prices and points. The tasks were organized in such...