A lab is conducting a study on protein interactions. They have used the data to create a graph visualization. In graph visualization, what would a layout be?
A layout is a way of arranging the nodes and links of a graph visualization to convey meaningful information about the data. A layout is determined by a dedicated algorithm that calculates the node positions based on certain criteria, such as minimizing edge crossings, maximizing node spacing, or emphasizing clusters12. A layout can also be influenced by user interaction, such as zooming, panning, or dragging3. Reference: 1: Guide to Business Data Analytics, IIBA, 2020, p. 642: Graph Drawing: Algorithms for the Visualization of Graphs, Giuseppe Di Battista et al., 1999, p. 33: Interactive Data Visualization: Foundations, Techniques, and Applications, Matthew O. Ward et al., 2015, p. 227.
While creating a dataset for analysis, the analyst reviews the data collected and finds a large percentage of records are missing values. Which activity would the analyst perform in order to use this dataset?
Weighting is a technique that assigns different values or weights to different records or variables in a dataset, based on their importance or relevance. Weighting can be used to handle missing values by giving them a lower weight or imputing them with a weighted average of other values. Weighting can also help to adjust for sampling bias or non-response bias in the data collection process. Reference:
* Understanding the Guide to Business Data Analytics, page 16
* Business Analysis Certification in Data Analytics, CBDA | IIBA, CBDA Competencies, Domain 3: Analyze Data
* CERTIFICATION IN BUSINESS DATA ANALYTICS HANDBOOK - IIBA, page 8, CBDA Exam Sample Questions and Self-Assessment, Question 4
An analytics team has been asked to answer the following question: "Given that you're a customer, would you work at our company?" The team is concerned about answering this question because it is:
The question ''Given that you're a customer, would you work at our company?'' is unclear, because it is a hypothetical and subjective question that does not specify the purpose, scope, or context of the analysis. The question also does not define what constitutes a customer, or how the customer's experience or satisfaction relates to the employee's motivation or performance. The question needs to be refined and clarified to make it more focused, relevant, and feasible for the analytics team to answer. For example, the question could be rephrased as ''How does the customer satisfaction score affect the employee retention rate in our company?'' Reference:
* Business Analysis Certification in Data Analytics, CBDA | IIBA, CBDA Competencies, Domain 1: Identify the Research Questions
* Understanding the Guide to Business Data Analytics, page 10-11
* CERTIFICATION IN BUSINESS DATA ANALYTICS HANDBOOK - IIBA, page 8, CBDA Exam Sample Questions and Self-Assessment, Question 16
The results for a certification exam were revealed in percentage and percentile. The results for one of the attendees was: 75%, 90th percentile. What is the value in sharing the percentile score?
The percentile score provides value by ranking the attendee's score among all the scores of the exam takers. A percentile score of 90 means that the attendee scored higher than 90% of the exam takers, and only 10% scored higher than the attendee. This gives a relative measure of how the attendee performed in comparison to other attendees, and how competitive or exceptional the score is. The percentile score does not depend on the average or the highest possible score of the exam, but only on the distribution of the scores of the exam takers. Reference:
* Business Analysis Certification in Data Analytics, CBDA | IIBA, CBDA Competencies, Domain 4: Interpret and Report Results
* Understanding the Guide to Business Data Analytics, page 9
* What is a Percentile? - Statistics By Jim
An analyst is performing regression analysis and reviewing the results. They would like to rescale the variables in the model to more clearly reflect the relationship between the regression coefficients. Which technique could be used to rescale the variables?
