Data refers to the characteristics associated with any type of information. Data gathering may occur in different ways including through observation, research, or analysis of variables. In each of these data collection approaches, the focus is on gathering information that would be analyzed to help reach a specific conclusion. Technological advancements, across the world, have introduced new dynamics for data collection, as they allow for users to collect and store large amounts of data, referred to as big data (Masha, 2014). The term ‘big data’ was derived from the fact that technology allows for the creation and storage of large volumes of data, especially in companies and organizations. A good example of a company that manipulates big data is Google, which stores large volumes of data due to the number of searches conducted every minute across the world through its search engine.
Another important aspect to note when evaluating big data is that the human brain can analyze large volumes of data, which plays an essential role in determining the decision that one is likely to make in any given situation. In each scenario, the brain maximizes its ability to manipulate available data to determine the best decision that would match overall expectations in terms of reaction to the scenario. The successful interjection of available data into decision-making implies that the handling and ultimate usage of data occurs in a competent manner maximizing a wide array of planning, organizing, analysis, and implementation techniques. When collecting data, one of the key aspects to note is that it cannot be collected in isolation considering that the collection process is subject to external influences. It is from this perspective that this report intends to examine how personal ‘bias’ may influence data gathering and interpretation.
Delegate your assignment to our experts and they will do the rest.
Data Collection and Interpretation
Data interpretation is an important part of everyday life. It refers to the process of making sense of numerical data, which has been gathered and analyzed. The basic expectation where interpreting data is that it becomes much easier to create an established framework through which to make viable conclusions based on available data. However, data interpretation can only be achieved through effective data collection, which aids in ensuring that data to be analyzed is gathered and stored before interpretation. Data collection refers to the process of gathering and measuring specific information focusing on the variables of interest to have to reach specific conclusions, evaluate an outcome, or testing a hypothesis. Data collection can be achieved through primary or secondary data sources. In primary data sources, an individual is considered as being the first person to have collected such data to help in effective interpretation.
Secondary data sources refer to data that has already been collected and analyzed, which in some cases may not be the most effective type of data. After data has been collected, it then goes through a phase of analysis, which involves the process of triangulating and percolating of the data depending on the variables of interest. Effective interpretation of data depends wholly on the data analysis process with the view being that this would help create an advanced outcome in which data is defined based on overall expectations. Data percolation occurs through a series of steps, which are pre-determined depending on the type of data that has been collected and the nature of conclusions expected from the data collected. Percolation ensures that only the most relevant data is extracted; thus, enhancing overall effectiveness in making some of the expected conclusions.
During the data collection process, one of the key aspects to consider is bias. Avoiding bias is one of the ways to ensure that any data collected and analyzed is valid and accurate depending on the expectation. Marr (2016) indicates that the repercussions associated with inaccurate or improperly collected data can be far-reaching because the inaccuracies may affect the conclusions achieved through data gathered. Personal bias is one of the notable types of bias that may affect data collection and interpretation, as it creates a situation where it becomes much harder for individuals to make valid conclusions. Consequently, this highlights the need for having to engage in an overview of possible personal biases that may influence the data collection and interpretation processes. The identification and analysis of personal biases would be of great value in maximizing the overall validity of interpreted data to ensure that decisions made remain effective.
Big Data in Effective Decision Making
Good decision-making is key to the success of companies and organizations, as it enhances their capacity to achieve the best possible outcomes, especially in ensuring that companies work towards overcoming some of the unforeseeable obstacles. The use of big data has become an essential part of the decision making processes considering that it helps those involved in making decisions to make better-informed decisions. Big data helps in the evaluation of past decisions that have been made and their implications to the success or failure of the company or organization. Therefore, it becomes much easier to ensure that the decisions made reflect on the best possible outcome matching basic expectations for companies and organizations. Big data helps in formulating predictions of the future based on what would happen if a company or organization would consider a new strategic direction. That implies that big data ensures that companies would rebuild themselves in terms of their capacities to achieve the best possible outcomes.
The incorporation of big data as part of the functioning of companies and organizations can also be seen from the fact that it helps business leaders understand the dynamics of their business environments. For companies to achieve the best out of their business models, decision makers are expected to learn their business environments, as this would improve their capacity to determine how the company would build its capacity. Another key advantage of incorporating big data in the decision-making processes is that it helps in anticipating market shifts. Market shifts occur when market performance is influenced by a wide array of factors, which may include demand and supply. Through the evaluation of big data, companies can make decisions based on the anticipated market shifts as a way of advancing their capacity to achieve the best possible outcomes.
Big data is equally essential because it helps in risk management. Every company or organization finds itself exposed to a wide array of risks, which affect its overall functionality in terms of capacity to deliver or achieve projected goals. Berengueres (2019) indicates that big data ensures that companies refrain from the idea of 'going with the gut' considering that this is not an effective way of dealing with possible risks occurring within the business environment. Big data helps in promoting statistical reasoning that ensures that the decisions made remain efficient in risk management and promoting profits. In every area where a company intends to make decisions, incorporation of big data may act as a guarantee that indeed the decisions made remain proactive in creating an enhanced platform for prospective outcomes. Big data provides those involved in decision making with a vast array of analytical capabilities and techniques, which remain at their disposal when making different decisions as a way of ensuring that they maintain overall efficiency in the achievement of the best possible outcomes.
Influences of Personal ‘Bias’ on Data Gathering and Interpretation
Personal bias tends to have a significant impact on the process of gathering and interpretation of data; thus, impacting the validity and reliability of conclusions or decisions made based on existing data. If not dealt with effectively, personal bias may create a situation where false data is interpreted, which is likely to affect the overall effectiveness of using such data. The first major impact of personal bias on data gathering is that it contributes to the occurrence of selection bias. Selection bias results from instances where data is selected subjectively without due consideration of how this is likely to impact the overall usability of the data. Big data analytics focuses on the utilization of multiple types of data with the view that this would help maximize overall effectiveness in achieving the best possible outcomes.
However, this is affected by selection bias considering the data is not a good reflection of what is expected in data interpretation. Efficiency in data interpretation can only be achieved in instances where the data considered is objective rather than being subjective (Marz & Warren, 2015). In other words, this means that the data used does not present any form of bias in terms of quality or reliability, which is a direct outcome of selection bias. Dealing with selection bias can only be effective in cases where one eliminates the general idea of view data from a personal perspective irrespective of whether the data is personal or not. When collecting data, it is important to make sure that the data is not subjective in any way with the view being that this would impact the quality of data gathered. Therefore, this means that one would consider all data presented irrespective of its impact on the overall conclusion.
Another key impact of personal bias on data collection and interpretation is that it results in data overfitting and underfitting. On the one hand, underfitting refers to a situation where the data seems to give an oversimplistic picture of reality with the view being that this would curtail the effectiveness of the data. On the other hand, overfitting refers to a situation where data is overcomplicated. In each of these cases, the data interpretation process may fail to achieve intended goals and objectives considering that it fails to consider the assumptions of interest. The introduction or incorporation of personal bias in the data collection and interpretation processes may result in either overfitting or underfitting. Consequently, that becomes a key issue of concern because most of the data may not help in promoting efficiency, especially in cases where the data is of value when making decisions.
Lastly, personal bias when engaging in data collection and interpretation may cause outliers in the data collected. Outliers refer to extreme data values that do not reflect on the overall expectations when focusing on the type of data that is being collected or interpreted (Zikopoulos & Eaton, 2011). Personal bias creates a situation where some of the data gathered may be unrealistic in every possible way, which means that the analysis may not necessarily reflect on the best possible outcomes. An example is when one’s personal bias lead him/her towards indicating that the average age of customers in a store is 110 years. From the onset, this data presents an outlier, which may have arisen from personal bias on what is expected as part of the data collection process. Ultimately, interpretation of this data is likely to present a major challenge become the data is inaccurate and unrealistic.
Analysis of Graphs and Methods of Interpretation
The graph above engages in an analysis of the percentage of sugar in different foods. The data, presented in the graphs, has been determined based on information presented on the packages of the foods. To aid in the analysis of the graph, the method that would be most appropriate is a frequency distribution. Frequency distribution evaluates the rate of data occurs within a specific data set. In this case, the data set selected focuses on specific foods, which include Ketchup, Peanut Butter, Chocolate Bar, Ice Cream, Chocolate Cake, Soda, and Crackers. Therefore, when one comes across one of the food items presented, it becomes much easier to determine the percent of sugar present. The basic expectation is that this would serve as a guarantee for efficiency in ensuring the validity and reliability of the conclusions made from the data gathered.
Data analysis and interpretation is a vital aspect that helps to have a basic understanding of the information presented. The chart focuses on representing temperature data for Seattle for 14 days. The appropriate method of interpreting data, in this case, is regression, which is a technique that focuses on determining the relationship between different variables. For the given chart, regression will focus on analyzing the temperature date for Seattle focusing on the high and low temperatures. The analysis helps to determine how the temperature changed within the fourteen days of study. The interpretation of data using the regression method is important as it helps to better an individual understanding of the given information. Secondly, the interpretation helped to create a visual representation of how temperature varied on different days. Considering that the chart involved two main variables, which are high and low temperatures, the method helps to create a basic understanding of any given chart.
Discussion of the BP Oil Spill Case Study
The BP Oil spill also known as the Deepwater Horizon Oil spill is a disaster that occurred in April 2020 in the Gulf of Mexico. The oil spill is considered one of the largest, industrial disasters in the history of the petroleum industry. The oil spill was approximately 8% larger than the previous oil spill that had occurred with the region. A research conducted by the federal government of the United States estimated the total discharge to be approximately 4.9 million barrels, which is equivalent to 210 million US gal. The implementation of different measures to contain the flow helped to effectively deal with the spillage. In September 2010, there was a report that indicated that the disaster was fully contained and that there was no more spillage. Considering the amount and extent of the oil spillage, the BP oil spill is considered one of the largest environmental disasters that ever happened in American history.
The oil spill resulted from an explosion that occurred at around 7:45 pm CDT, on April 20, 2010, on the Deepwater horizon. The deep-water horizon was a semi-submersible and a mobile drilling rig that was 10years old and which could operate in 10,000 feet water depth. The explosion occurred because of an expansion of the high-pressure methane gas, which rose into the drilling rig. During the explosion, there were 126 people on board, who comprised of BP employees and other employees of different companies. Following the explosion, a total of 94 people were rescued while the rest were never found despite an extensive search operation conducted. Considering the nature of the explosion, most of the people that died may have been as a result of chocking from methane gas and smoke.
The oil spillage was discovered two days later following the explosion, which continued for approximately 87days. The estimated daily oil spillage was approximately 1,000 to 5,000 barrels, which is equivalent to 160 to 790 m3. Following the disaster, different measures were implemented to ensure that the spilled oil was collected even before it entered the gulf waters. The given measures purposed to reduce the effects of oil spillage and focus on ensuring that the situation was contained. Research to determine the extent of the disaster indicated that approximately 68,000 square miles were affected. The distance of the oil spillage as an indication that the spill was indeed a massive issue that required a proper implementation of the effective measure to contain the disaster. The efforts to deal with the issue involved both short and long-term efforts that helped to ensure that the spillage stopped and that no more environmental harm was experienced. The efforts focused not only on stopping the spillage but also to ensure prevent a recurrent of future leakages.
The BP oil spill had a wide range of effects on the environment, the economy, and the general health of an entire ecosystem. Firstly, it is important to note that the spill hosted approximately 8,332 species, which included 1,270 fish, 604 polychaetes, 218 birds, 1,456 mollusks among others. The spill posed a major threat to the lives of all the animals that existed in the spill area. Approximately 40% of the animal pupation within the spill area was found dead, which is an aspect that resulted from a lack of oxygen. Another major impact of the spillage was chemical positioning for most residents in Alabama, Mississippi, Louisiana, and Florida. On the effects of the spillage on the economy, the Gulf coastal economy was affected resulting in a total loss of approximately 22.7 billion considering that the spill affected major economic activities such as tourism and fishing.
Conclusion
Technological advancements have played a key role in the introduction of the big data concept that focuses on the collection, presentation, and analysis of huge volumes of data. Big data analysis remains one of the key aspects of consideration for companies and organizations across the world today. Data collection and interpretation is one of the key aspects of consideration when referring to big data, as it creates an enhanced platform through which to ensure that the quality of data does not change. However, it is much more likely for one to project personal bias during the collection and interpretation of data; thus, creating a significant challenge in terms of data validity and reliability. Personal bias influences data collection and interpretation, as it creates a high possibility of selection bias, data overfitting, and underfitting, and outliers in the data collected.
References
Berengueres, J. (2019). Introduction to data visualization & storytelling: A guide for the data scientist . London, UK: Stokes-Hamilton.
Marr, B. (2016). Big Data for small business for dummies . New York, NY: John Wiley & Sons.
Marz, N., & Warren, J. (2015). Big Data: Principles and best practices of scalable realtime data systems . Manning Publications Co.
Masha, E. M. (2014). The Case for Data Driven Strategic Decision Making. European Journal of Business and Management , 137-146.
Zikopoulos, P., & Eaton, C. (2011). Understanding big data: Analytics for enterprise-class Hadoop and streaming data . McGraw-Hill Osborne Media.
