Free CBDA Exam Dumps Preview

The best action for the analyst to show value from the onset of their work is to develop a meaningful question that can be answered with data the company already has in its possession. This way, the analyst can demonstrate the potential of analytics to solve relevant business problems, without spending too much time or resources on data collection or market research. The question should also be aligned with the organization's strategy and goals, and provide actionable insights for decision making

A data flow diagram (DFD) is a graphical representation of how data flows and transforms through a system or process. A DFD shows the sources and destinations of data, the data inputs and outputs, the data transformations and logic, and the data stores and flows. A DFD can help the analyst model howand when data is transformed throughout various processes across the organization, as well as identify potential data quality issues, bottlenecks, and redundancies. A DFD can also complement a future state data model by showing the relationships and dependencies among the data entities and attributes.

The analyst's follow-up question is valid because it helps to refine the scope and context of the research questions for the analytical study. By comparing the top customer concerns across branches, the analyst can identify the common and unique issues that affect customer satisfaction and loyalty. This can also help to prioritize the most critical or urgent problems that need to be addressed by the bank

According to the Introduction to Business Data Analytics: A Practitioner View, the breakeven point is the point at which the total revenue equals the total cost of a product or service. The breakeven point indicates the minimum sales volume or price required to cover the fixed and variable costs and to start making a profit. The breakeven point can help the management team make a decision on pricing by showing them how sensitive the profitability is to the price changes and how much margin of safety they have. The breakeven point can also help the management team evaluate the feasibility and risk of the pricing proposal and compare it with alternative scenarios.

The business analyst is concerned about the validity of the survey. Validity is the extent to which a survey measures what it intends to measure. In this case, the survey is supposed to measure job satisfaction, but the two questions asked to different groups of employees are not equivalent or relevant to this construct.
The question "Do you enjoy working in your workplace?" is more directly related to job satisfaction than the question "Do you like the current work benefits?". The latter question may capture only one aspect of job satisfaction, and may not reflect the overall level of contentment or happiness with the job. Therefore, the survey results may not be valid or accurate in measuring job satisfaction

Developing the narrative is the process of creating a clear, concise, and compelling story that communicates the key insights, findings, and recommendations from the data analysis to the stakeholders 1. Developing the narrative is an important step after completing the research study, the data analysis, and the high impact visuals, as it helps to bridge the gap between the data and the decision-making, to engage and persuade the audience, and to drive action and change 2. Developing the narrative involves defining the purpose, audience, and message of the story, choosing the best format and medium to deliver the story, and using effective storytelling techniques, such as structure, context, emotion, and call to action 3.

Presenting the results to stakeholders is the process of delivering the data story to the intended audience, using the appropriate communication channels, methods, and tools 4. Presenting the results to stakeholders is a subsequent step after developing the narrative, as it requires a well-crafted and well-prepared data story to be effective and impactful. Presenting the results to stakeholders involves planning and rehearsing the presentation, adapting to the feedback and questions, and evaluating the outcomes and impacts of the presentation 5.

Validating regression analysis is the process of checking the assumptions, accuracy, and suitability of a statistical model that estimates the relationship between one or more independent variables and a dependent variable. Validating regression analysis is a part of the data analysis step, not a step after completing the data analysis. Validating regression analysis involves testing the significance, fit, and residuals of the model, and comparing the model with alternative models or methods.

Curating the data is the process of organizing, annotating, and preserving the data for future use, reuse, or sharing. Curating the data is a part of the data management step, not a step after completing the data analysis. Curating the data involves applying the data policies, standards, and best practices of the organization, and ensuring the quality, integrity, security, and accessibility of the data.

Customer retention rate is a measure of how many customers continue to use a product or service over a given period of time. It is an important indicator of customer loyalty, satisfaction, and value. Customer retention rate can help the bank evaluate how the website is being used by comparing the number of customers who visited the website before and after the launch of the new features. A high customer retention rate would suggest that the new features are attractive, useful, and engaging for the customers, while a low customer retention rate would indicate that the new features are not meeting the customers' needs or expectations. Customer retention rate can also help the bank identify the segments of customers who are more or less likely to use the website, and tailor their marketing and communication strategies accordingly.

K-means clustering is a technique that partitions a set of data points into a predefined number of clusters, based on their similarity or distance. This technique can be useful to divide the customer base into groups that have similar characteristics, preferences, or behaviors, and then design insurance products that cater to each group's needs and expectations. K-means clustering can also help identify outliers or anomalies in the customer data that may require further investigation or attention.

References:
Guide to Business Data Analytics, page 58-59
CBDA Exam Blueprint, page 7
[Introduction to
Business Data Analytics: A Practitioner View], page 17.

Sampling error is the difference between the results obtained from a sample and the results obtained from the population from which the sample is drawn 1. Sampling error can affect the validity, reliability, and generalizability of the survey results 2. To reduce the degree of sampling error, the data team should use a large sample size and a random selection of the target population. A large sample size means that the sample is more likely to represent the diversity and variability of the population, and that the results are more precise and accurate 3. A random selection of the target population means that every member of the population has an equal chance of being included in the sample, and that the results are less biased and more representative 4.

The other criteria would not help the team meet this objective, as they would increase the degree of sampling error. A large sample size and variation in the target population would not reduce the sampling error, as variation refers to the differences or heterogeneity within the population, not the sample. Variation in the target population can increase the sampling error, as it makes it harder to capture the true characteristics of the population with a sample 5. A small sample size and specific subset of the target population would not reduce the sampling error, as they would make the sample less representative and more prone to bias. A small sample size means that the sample is less likely to reflect the diversity and variability of the population, and that the results are less precise and accurate. A specific subset of the target population means that the sample is not randomly selected, but based on some criteria or convenience, and that the results are more biased and less representative. A small sample size and using customers who agreed to take the survey would not reduce the sampling error, as they would also make the sample less representative and more prone to bias. A small sample size has the same drawbacks as mentioned above. Using customers who agreed to take the survey means that the sample is not randomly selected, but based on self-selection or voluntary response, and that the results are more biased and less representative.

Variation is the degree to which the data values differ from each other or from a central tendency measure, such as the mean or median. Variation can affect the data quality across cities, as it can indicate the presence of outliers, errors, noise, or inconsistency in the data collection or processing methods. Variation can also influence the statistical analysis and interpretation of the results, as it can affect the significance, confidence, and validity of the findings

A composite data element is a data element that is made up of smaller units called sub-elements, which are separated by a sub-element separator character, such as a colon (:). For example, ITEMNO is a composite data element that consists of three sub-elements: part number, aisle number, and bin number.
A street address is also a composite data element that can consist of sub-elements such as street number, street name, city, state, and zip code. First name, total sale, and birthdate are simple data elements that do
not have sub-elements.

A pie chart is a circular chart that shows the proportion of each category in a whole by dividing the circle into slices. A pie chart would result in confusion when comparing the number of sales for a specific model of electric car across all 50 US states, because it is difficult to compare the angles and areas of the slices, especially when there are many categories with similar values. A pie chart also does not show the absolute values of each category, unless they are labeled or annotated. A better alternative would be a bar chart, which can show the number of sales for each state along a common axis, making it easier to compare and rank the values

Reliability is the degree to which a data collection method produces consistent results under the same conditions 1. In this case, the reliability of the study data might be compromised by the different interviewers (senior managers vs. external market research company), who might have different biases, expectations, or rapport with the employees. This could affect how the employees respond to the same set of questions, and thus introduce variability in the data. Validity, timeliness, and precision are not directly affected by the choice of interviewers, as they depend more on the quality, relevance, and accuracy of the questions and the data analysis.

Providing `one source of the truth' means ensuring that there is a single, consistent, and authoritative source of data that can be used for analytics and decision making across the organization. This objective can be achieved by enforcing master data management principles and practices, which involve defining, governing, and maintaining the quality and integrity of the core data entities that are shared by multiple systems and processes. Master data management helps to eliminate data silos, reduce data duplication and inconsistency, and improve data accuracy and reliability

Probabilistic linkage is a technique that uses statistical methods to match records from different data sources based on the similarity of key variables, such as name, address, date of birth, etc 1. Probabilistic linkage can handle variations, errors, or missing values in the data, and assign a score or probability to each potential match 2. Probabilistic linkage would be useful in this situation, as the address column may have different formats, spellings, or abbreviations in the internal and external data sources, and a deterministic linkage (which requires exact matches) might miss some valid matches or create false matches.

Deterministic linkage is a technique that uses predefined rules or criteria to match records from different data sources based on the exact agreement of key variables, such as identifiers, codes, or hashes 3.
Deterministic linkage would not be useful in this situation, as the address column may not have consistent or unique values in the internal and external data sources, and a probabilistic linkage (which allows for some variation or uncertainty) might find more accurate matches or avoid false matches.

Genetic linkage is a term used in genetics to describe the tendency of genes or DNA sequences that are located close together on a chromosome to be inherited together 4. Genetic linkage is not relevant to this situation, as it has nothing to do with matching records from different data sources based on the address column.

Cuff linkage is a term used in sewing to describe the process of attaching a cuff to a sleeve by stitching or fastening. Cuff linkage is not relevant to this situation, as it has nothing to do with matching records from different data sources based on the address column.

According to the Guide to Business Data Analytics, one of the steps in conducting business data analytics is to identify the research questions that will guide the analysis and help answer the business problem or opportunity. The research questions should be relevant, specific, measurable, achievable, and testable. In this situation, the business problem is the delay in customer payments and the potential solution is to offer a discount. A valid question to ask in this situation is whether discounts have been offered before, and if so, what was the effect on customer behavior and profitability. This question is relevant because it can help assess the feasibility and effectiveness of the proposed solution. It is also specific, measurable, achievable, and testable, as it can be answered by collecting and analyzing historical data on customer payments and discounts..

Data validity refers to the extent to which data accurately represents the phenomenon or concept that it is intended to measure 1. Data validity is essential for predictive analytics, as it affects the quality and credibility of the analysis results and the subsequent decisions or actions based on them. If data is invalid, the predictions may be inaccurate, misleading, or irrelevant. However, data validity may be challenging to ensure in clinical research, as data may be scarce, incomplete, inconsistent, or subject to errors or biases 2. Therefore, the team may establish scenario development as a required technique to address this concern. Scenario development is a form of document analysis that involves creating hypothetical situations or stories based on assumptions, evidence, and logic to explore the possible outcomes or implications of a problem or opportunity 3. Scenario development can help the team generate appropriate data for initial analysis by simulating different conditions, variables, or events that may affect the clinical trials, and by testing the validity of the data against the scenarios 4.

Descriptive and predictive analytics are types of analytics that can help with creating SMART objectives.
SMART stands for Specific, Measurable, Achievable, Relevant, and Time-bound, which are criteria for setting effective and realistic goals 1. Descriptive analytics is the type of analytics that summarizes what has happened in the past using data, such as historical trends, patterns, or performance 2. Descriptive analytics can help with creating SMART objectives by providing a baseline, benchmark, or context for the current situation and the desired outcomes. Predictive analytics is the type of analytics that forecasts what is likely to happen in the future using data, such as statistical models, machine learning, or artificial intelligence 3. Predictive analytics can help with creating SMART objectives by providing a projection, estimation, or scenario for the future situation and the expected results.

Diagnostic and prescriptive analytics are other types of analytics that are not as helpful with creating SMART objectives. Diagnostic analytics is the type of analytics that explains why something has happened in the past using data, such as root cause analysis, correlation analysis, or hypothesis testing. Diagnostic analytics can help with understanding the causes and effects of past events, but it does not provide guidance or direction for setting future goals. Prescriptive analytics is the type of analytics that recommends what should be done in the future using data, such as optimization, simulation, or decision analysis. Prescriptive analytics can help with suggesting the best actions or alternatives for achieving future goals, but it does not define or measure the goals themselves.

Interviews are a technique to elicit information from stakeholders and subject matter experts. Interviews can be planned or unplanned, structured or unstructured, depending on the context and purpose of the interview. However, regardless of the type of interview, it is important to have clear goals for the interview, such as what information is needed, what questions will be asked, and how the information will be used.
Having clear goals for the interview helps the interviewer to prepare, conduct, and follow up the interview effectively, and also helps the interviewee to understand the expectations and provide relevant and accurate information.

The mean of a set of numbers is the sum of the numbers divided by the number of numbers. The median of a set of numbers is the middle value when the numbers are arranged in ascending or descending order.
To find the mean and median of the given scores, we can use the following steps:

To find the mean, we add up all the scores and divide by 7, the number of students. The mean is (64 + 70
+ 80 + 80 + 90 + 98 + 100) / 7 = 582 / 7 = 83.14
To find the median, we arrange the scores in ascending order: 64, 70, 80, 80, 90, 98, 100. Since there are an odd number of scores, the median is the middle score, which is 80.
Therefore, the mean and median for the outlined scores are 83.14 and 80, respectively.

The question "How effective is our marketing spend?" is too broadly scoped to be effectively answered, because it is a vague and ambiguous question that does not specify the criteria, scope, or timeframe for measuring the effectiveness of the marketing spend. The question also does not define what constitutes marketing spend, or how it relates to the sales data or the budget allocations. 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 marketing spend per channel affect the sales revenue and customer retention rate in the last quarter?"

Expert judgement and experience are valuable sources of knowledge and insight for business data analytics, but they can also introduce bias in the decision making process. Bias is a tendency to favor or reject a certain perspective, outcome, or solution based on personal or subjective preferences, beliefs, or expectations. Bias can affect the quality, validity, and reliability of the data analysis and the resulting decisions. Some examples of bias that can affect expert judgement and experience are confirmation bias, availability bias, anchoring bias, and overconfidence bias. To avoid or minimize bias, business data analysts should apply critical thinking, data literacy, and ethical principles throughout the data analysis process. They should also seek diverse perspectives, challenge assumptions, validate findings, and communicate uncertainties and limitations.

The data scientist is encouraging using the Gestalt Principle of Similarity with regards to data visualization.
This principle states that the brain groups objects together that are similar in appearance, such as color, shape, size, or orientation. By using color to group objects needing to be associated, the data scientist is suggesting a way to reduce the complexity in the model and make it easier for the viewers to perceive the patterns and relationships among the data