WGU D293 Pre-Assessment: Assessment And Learning
Analytics (PADB) | 2026/2027 Edition | 150 Verified Questions
WGU D293 Pre-Assessment 2026-2027 QUESTIONS AND ANSWERS ALREADY GRADED
A+. 100% Verified Solutions | Updated Per Latest Guidelines | Graded A+
This comprehensive exam prep document for WGU D293 Assessment and Learning Analytics (PADB)
features 150 verified questions with detailed answers and rationales. Designed to mirror the
pre-assessment format, it covers key competencies including assessment design, data-driven
instruction, and learning analytics. Each question is aligned with the latest WGU curriculum for the
2026/2027 academic year, ensuring relevance and accuracy. Ideal for students seeking to master the
core concepts and achieve a high score on the pre-assessment.
Key Features:
Assessment design principles and frameworks
Data collection and analysis methods
Learning analytics tools and applications
Ethical considerations in assessment
Interpretation and use of assessment data
Alignment of assessments with learning objectives
Updates for 2026:
- Updated to reflect the latest WGU D293 course objectives for 2026/2027
- Added new questions on emerging learning analytics technologies
- Revised rationales to include more detailed explanations
- Enhanced coverage of ethical and privacy issues in assessment
- Improved alignment with competency-based education models
Abstract:
This document provides a rigorous preparation resource for the WGU D293 Pre-Assessment in Assessment and
Learning Analytics (PADB). It comprises 150 verified questions that systematically address the core competencies
of the course, including the design and implementation of assessments, the application of learning analytics to
improve instruction, and the ethical use of student data. Each question is accompanied by a correct answer and a
detailed rationale that explains the underlying concepts and reasoning. The content is organized by key content
areas, allowing for targeted study. Updated for the 2026/2027 academic year, this resource reflects the most
current standards and practices in educational assessment and analytics. It is an essential tool for students aiming
to demonstrate mastery and achieve a high score on the pre-assessment.
Keywords:
WGU D293, Assessment and Learning Analytics, PADB, Pre-Assessment, Verified Questions, Data-Driven
Instruction, Educational Assessment, Learning Analytics
Answer Format:
Each question is presented in multiple-choice format with four options. The correct answer is indicated, followed
by a rationale that explains why it is correct and why the other options are incorrect. Distractors are analyzed to
clarify common misconceptions.
Compliance Checklist:
All questions are verified against WGU D293 course objectives
Rationales are aligned with current assessment and learning analytics theories
Content reflects the latest 2026/2027 curriculum updates
Page 1
, Questions are formatted to match the pre-assessment style
Ethical guidelines and privacy considerations are addressed
Content Area Overview:
Content Area Questions Key Topics Weight
Foundations of Assessment 1-30 Assessment types, validity, reliability, bias 20%
Designing Assessments 31-60 Learning objectives, item writing, rubric 20%
development
Data Collection and Analysis 61-90 Quantitative and qualitative data, statistical 20%
measures, data visualization
Learning Analytics 91-120 Analytics tools, dashboards, predictive 20%
modeling, intervention strategies
Ethics and Data Privacy 121-150 FERPA, informed consent, data security, 20%
ethical decision-making
Page 2
,Q1. A university is implementing a learning analytics dashboard that tracks student engagement metrics
(login frequency, time on task, discussion posts) to predict at-risk students. The system uses a logistic
regression model trained on historical data. Which of the following is the most critical validity concern for
using this model to issue early alerts?
A. The model may have high sensitivity but low specificity, leading to over-identification of at-risk students.
B. The model's predictors may lack construct validity as measures of meaningful engagement.
C. The logistic regression assumption of linearity between predictors and log-odds may be violated.
D. The model may exhibit algorithmic bias if historical data reflects systemic inequities.
Correct Answer: D. The model may exhibit algorithmic bias if historical data reflects systemic inequities.
Rationale: Algorithmic bias is the most critical concern because if historical data reflects inequities (e.g., lower
engagement due to socioeconomic factors), the model may unfairly label students from marginalized groups as
at-risk, perpetuating discrimination. While construct validity (B) is important, bias directly impacts fairness and
ethics. Sensitivity/specificity (A) and linearity (C) are technical issues but less central to ethical validity.
Why Wrong:
A - High sensitivity with low specificity is a performance trade-off, but it does not address the fundamental
fairness issue.
B - Construct validity is important but secondary to the ethical imperative of avoiding bias.
C - Violation of linearity can be mitigated with transformations or non-linear models; it is not the most
critical validity concern.
Reference: Slade, S., & Prinsloo, P. (2013). Learning analytics: Ethical issues and dilemmas. American Behavioral
Scientist, 57(10), 1510-1529.
Q2. An instructor designs a multiple-choice test to measure critical thinking in biology. Item analysis reveals
that for one item, the point-biserial correlation is -0.12 and the difficulty index is 0.95. Which of the following
is the most appropriate interpretation and action?
A. The item is too easy and has negative discrimination; it should be revised or removed.
B. The item is too difficult and has positive discrimination; it should be retained but reworded.
C. The item has high discrimination and moderate difficulty; it is functioning well.
D. The item has low discrimination but appropriate difficulty; it can be kept with minor revision.
Correct Answer: A. The item is too easy and has negative discrimination; it should be revised or removed.
Rationale: A difficulty index of 0.95 means 95% of students answered correctly, indicating the item is very easy. A
negative point-biserial correlation (-0.12) means that students who scored low on the overall test were more likely
to answer correctly than high-scoring students, indicating poor discrimination. Such an item does not differentiate
between high and low achievers and should be revised or removed.
Why Wrong:
B - The difficulty index of 0.95 indicates an easy item, not difficult; the correlation is negative, not positive.
C - High discrimination requires a positive point-biserial near 0.3 or above; -0.12 is negative and low.
D - Low discrimination combined with very low difficulty makes the item ineffective; minor revision is
insufficient.
Reference: Crocker, L., & Algina, J. (2006). Introduction to Classical and Modern Test Theory. Cengage Learning.
Q3. A school district implements a computer-adaptive test (CAT) for mathematics. The test uses a
3-parameter logistic (3PL) item response theory model. Which of the following is the primary advantage of
using the 3PL model over the 1PL (Rasch) model for this assessment?
A. The 3PL model assumes equal discrimination across all items, simplifying calibration.
B. The 3PL model includes a guessing parameter, which is important for multiple-choice items.
C. The 3PL model requires smaller sample sizes for accurate parameter estimation.
D. The 3PL model provides a single parameter for item difficulty, making it easier to interpret.
Page 3
, Correct Answer: B. The 3PL model includes a guessing parameter, which is important for multiple-choice
items.
Rationale: The 3PL model includes a pseudo-guessing parameter (c-parameter) that accounts for the probability of low-ability
students guessing correctly on multiple-choice items. This is a key advantage over the 1PL (Rasch) model, which does not
model guessing and can therefore overestimate the ability of low-performing students. The other options are incorrect: 3PL
does not assume equal discrimination (A), requires larger sample sizes (C), and includes three parameters, not one (D).
Why Wrong:
A - The 3PL model estimates discrimination (a-parameter) freely, not assuming equality.
C - The 3PL model typically requires larger sample sizes (e.g., >500) for stable estimation compared to 1PL.
D - The 3PL model includes difficulty, discrimination, and guessing parameters, not a single parameter.
Reference: Hambleton, R. K., & Swaminathan, H. (1985). Item Response Theory: Principles and Applications. Springer.
Q4. A researcher conducts a study to compare the predictive validity of two learning analytics models: Model
A uses clickstream data from a learning management system (LMS), and Model B uses a combination of
clickstream data and demographic variables. The area under the receiver operating characteristic curve
(AUC) for Model A is 0.72, and for Model B is 0.78. Which of the following conclusions is most justified?
A. Model B is significantly better than Model A because the AUC difference is 0.06.
B. Model A is more interpretable and should be preferred despite lower AUC.
C. The AUC difference may not be statistically significant; a confidence interval or test should be computed.
D. Model B should be rejected because including demographics raises ethical concerns about fairness.
Correct Answer: C. The AUC difference may not be statistically significant; a confidence interval or test
should be computed.
Rationale: An AUC difference of 0.06 may or may not be statistically significant depending on sample size and
variability. Without a statistical test (e.g., DeLong test) or confidence intervals, it is premature to conclude
superiority. Option A is incorrect because significance is not determined by the magnitude alone. Option D is an
ethical consideration but not a methodological conclusion about predictive validity. Option B introduces a trade-off
not supported by the data.
Why Wrong:
A - Statistical significance requires hypothesis testing; the raw difference is insufficient.
B - Interpretability is a factor but not the primary conclusion from the AUC comparison.
D - Ethical concerns are valid but not directly about the predictive validity comparison.
Reference: DeLong, E. R., DeLong, D. M., & Clarke-Pearson, D. L. (1988). Comparing the areas under two or
more correlated receiver operating characteristic curves. Biometrics, 44(3), 837-845.
Q5. A test blueprint for a final exam in a psychology course specifies that 30% of items should measure
knowledge, 40% comprehension, and 30% application, according to Bloom's taxonomy. The instructor
writes 50 items. After the exam, a bias review panel flags that items measuring application disproportionately
contain examples from Western cultures. Which of the following is the most appropriate next step?
A. Remove all application-level items to avoid cultural bias.
B. Revise the flagged items to include diverse cultural contexts while maintaining the same cognitive level.
C. Increase the percentage of comprehension items to reduce reliance on application items.
D. Conduct a differential item functioning (DIF) analysis to determine if the items function differently across
cultural groups.
Correct Answer: D. Conduct a differential item functioning (DIF) analysis to determine if the items function
differently across cultural groups.
Rationale: A DIF analysis is the most appropriate step to empirically determine whether the flagged items exhibit
bias (i.e., function differently for different cultural groups after controlling for ability). Revising items (B) may be
premature without evidence of DIF. Removing items (A) or altering the blueprint (C) would compromise content
validity without addressing the underlying issue.
Page 4
Analytics (PADB) | 2026/2027 Edition | 150 Verified Questions
WGU D293 Pre-Assessment 2026-2027 QUESTIONS AND ANSWERS ALREADY GRADED
A+. 100% Verified Solutions | Updated Per Latest Guidelines | Graded A+
This comprehensive exam prep document for WGU D293 Assessment and Learning Analytics (PADB)
features 150 verified questions with detailed answers and rationales. Designed to mirror the
pre-assessment format, it covers key competencies including assessment design, data-driven
instruction, and learning analytics. Each question is aligned with the latest WGU curriculum for the
2026/2027 academic year, ensuring relevance and accuracy. Ideal for students seeking to master the
core concepts and achieve a high score on the pre-assessment.
Key Features:
Assessment design principles and frameworks
Data collection and analysis methods
Learning analytics tools and applications
Ethical considerations in assessment
Interpretation and use of assessment data
Alignment of assessments with learning objectives
Updates for 2026:
- Updated to reflect the latest WGU D293 course objectives for 2026/2027
- Added new questions on emerging learning analytics technologies
- Revised rationales to include more detailed explanations
- Enhanced coverage of ethical and privacy issues in assessment
- Improved alignment with competency-based education models
Abstract:
This document provides a rigorous preparation resource for the WGU D293 Pre-Assessment in Assessment and
Learning Analytics (PADB). It comprises 150 verified questions that systematically address the core competencies
of the course, including the design and implementation of assessments, the application of learning analytics to
improve instruction, and the ethical use of student data. Each question is accompanied by a correct answer and a
detailed rationale that explains the underlying concepts and reasoning. The content is organized by key content
areas, allowing for targeted study. Updated for the 2026/2027 academic year, this resource reflects the most
current standards and practices in educational assessment and analytics. It is an essential tool for students aiming
to demonstrate mastery and achieve a high score on the pre-assessment.
Keywords:
WGU D293, Assessment and Learning Analytics, PADB, Pre-Assessment, Verified Questions, Data-Driven
Instruction, Educational Assessment, Learning Analytics
Answer Format:
Each question is presented in multiple-choice format with four options. The correct answer is indicated, followed
by a rationale that explains why it is correct and why the other options are incorrect. Distractors are analyzed to
clarify common misconceptions.
Compliance Checklist:
All questions are verified against WGU D293 course objectives
Rationales are aligned with current assessment and learning analytics theories
Content reflects the latest 2026/2027 curriculum updates
Page 1
, Questions are formatted to match the pre-assessment style
Ethical guidelines and privacy considerations are addressed
Content Area Overview:
Content Area Questions Key Topics Weight
Foundations of Assessment 1-30 Assessment types, validity, reliability, bias 20%
Designing Assessments 31-60 Learning objectives, item writing, rubric 20%
development
Data Collection and Analysis 61-90 Quantitative and qualitative data, statistical 20%
measures, data visualization
Learning Analytics 91-120 Analytics tools, dashboards, predictive 20%
modeling, intervention strategies
Ethics and Data Privacy 121-150 FERPA, informed consent, data security, 20%
ethical decision-making
Page 2
,Q1. A university is implementing a learning analytics dashboard that tracks student engagement metrics
(login frequency, time on task, discussion posts) to predict at-risk students. The system uses a logistic
regression model trained on historical data. Which of the following is the most critical validity concern for
using this model to issue early alerts?
A. The model may have high sensitivity but low specificity, leading to over-identification of at-risk students.
B. The model's predictors may lack construct validity as measures of meaningful engagement.
C. The logistic regression assumption of linearity between predictors and log-odds may be violated.
D. The model may exhibit algorithmic bias if historical data reflects systemic inequities.
Correct Answer: D. The model may exhibit algorithmic bias if historical data reflects systemic inequities.
Rationale: Algorithmic bias is the most critical concern because if historical data reflects inequities (e.g., lower
engagement due to socioeconomic factors), the model may unfairly label students from marginalized groups as
at-risk, perpetuating discrimination. While construct validity (B) is important, bias directly impacts fairness and
ethics. Sensitivity/specificity (A) and linearity (C) are technical issues but less central to ethical validity.
Why Wrong:
A - High sensitivity with low specificity is a performance trade-off, but it does not address the fundamental
fairness issue.
B - Construct validity is important but secondary to the ethical imperative of avoiding bias.
C - Violation of linearity can be mitigated with transformations or non-linear models; it is not the most
critical validity concern.
Reference: Slade, S., & Prinsloo, P. (2013). Learning analytics: Ethical issues and dilemmas. American Behavioral
Scientist, 57(10), 1510-1529.
Q2. An instructor designs a multiple-choice test to measure critical thinking in biology. Item analysis reveals
that for one item, the point-biserial correlation is -0.12 and the difficulty index is 0.95. Which of the following
is the most appropriate interpretation and action?
A. The item is too easy and has negative discrimination; it should be revised or removed.
B. The item is too difficult and has positive discrimination; it should be retained but reworded.
C. The item has high discrimination and moderate difficulty; it is functioning well.
D. The item has low discrimination but appropriate difficulty; it can be kept with minor revision.
Correct Answer: A. The item is too easy and has negative discrimination; it should be revised or removed.
Rationale: A difficulty index of 0.95 means 95% of students answered correctly, indicating the item is very easy. A
negative point-biserial correlation (-0.12) means that students who scored low on the overall test were more likely
to answer correctly than high-scoring students, indicating poor discrimination. Such an item does not differentiate
between high and low achievers and should be revised or removed.
Why Wrong:
B - The difficulty index of 0.95 indicates an easy item, not difficult; the correlation is negative, not positive.
C - High discrimination requires a positive point-biserial near 0.3 or above; -0.12 is negative and low.
D - Low discrimination combined with very low difficulty makes the item ineffective; minor revision is
insufficient.
Reference: Crocker, L., & Algina, J. (2006). Introduction to Classical and Modern Test Theory. Cengage Learning.
Q3. A school district implements a computer-adaptive test (CAT) for mathematics. The test uses a
3-parameter logistic (3PL) item response theory model. Which of the following is the primary advantage of
using the 3PL model over the 1PL (Rasch) model for this assessment?
A. The 3PL model assumes equal discrimination across all items, simplifying calibration.
B. The 3PL model includes a guessing parameter, which is important for multiple-choice items.
C. The 3PL model requires smaller sample sizes for accurate parameter estimation.
D. The 3PL model provides a single parameter for item difficulty, making it easier to interpret.
Page 3
, Correct Answer: B. The 3PL model includes a guessing parameter, which is important for multiple-choice
items.
Rationale: The 3PL model includes a pseudo-guessing parameter (c-parameter) that accounts for the probability of low-ability
students guessing correctly on multiple-choice items. This is a key advantage over the 1PL (Rasch) model, which does not
model guessing and can therefore overestimate the ability of low-performing students. The other options are incorrect: 3PL
does not assume equal discrimination (A), requires larger sample sizes (C), and includes three parameters, not one (D).
Why Wrong:
A - The 3PL model estimates discrimination (a-parameter) freely, not assuming equality.
C - The 3PL model typically requires larger sample sizes (e.g., >500) for stable estimation compared to 1PL.
D - The 3PL model includes difficulty, discrimination, and guessing parameters, not a single parameter.
Reference: Hambleton, R. K., & Swaminathan, H. (1985). Item Response Theory: Principles and Applications. Springer.
Q4. A researcher conducts a study to compare the predictive validity of two learning analytics models: Model
A uses clickstream data from a learning management system (LMS), and Model B uses a combination of
clickstream data and demographic variables. The area under the receiver operating characteristic curve
(AUC) for Model A is 0.72, and for Model B is 0.78. Which of the following conclusions is most justified?
A. Model B is significantly better than Model A because the AUC difference is 0.06.
B. Model A is more interpretable and should be preferred despite lower AUC.
C. The AUC difference may not be statistically significant; a confidence interval or test should be computed.
D. Model B should be rejected because including demographics raises ethical concerns about fairness.
Correct Answer: C. The AUC difference may not be statistically significant; a confidence interval or test
should be computed.
Rationale: An AUC difference of 0.06 may or may not be statistically significant depending on sample size and
variability. Without a statistical test (e.g., DeLong test) or confidence intervals, it is premature to conclude
superiority. Option A is incorrect because significance is not determined by the magnitude alone. Option D is an
ethical consideration but not a methodological conclusion about predictive validity. Option B introduces a trade-off
not supported by the data.
Why Wrong:
A - Statistical significance requires hypothesis testing; the raw difference is insufficient.
B - Interpretability is a factor but not the primary conclusion from the AUC comparison.
D - Ethical concerns are valid but not directly about the predictive validity comparison.
Reference: DeLong, E. R., DeLong, D. M., & Clarke-Pearson, D. L. (1988). Comparing the areas under two or
more correlated receiver operating characteristic curves. Biometrics, 44(3), 837-845.
Q5. A test blueprint for a final exam in a psychology course specifies that 30% of items should measure
knowledge, 40% comprehension, and 30% application, according to Bloom's taxonomy. The instructor
writes 50 items. After the exam, a bias review panel flags that items measuring application disproportionately
contain examples from Western cultures. Which of the following is the most appropriate next step?
A. Remove all application-level items to avoid cultural bias.
B. Revise the flagged items to include diverse cultural contexts while maintaining the same cognitive level.
C. Increase the percentage of comprehension items to reduce reliance on application items.
D. Conduct a differential item functioning (DIF) analysis to determine if the items function differently across
cultural groups.
Correct Answer: D. Conduct a differential item functioning (DIF) analysis to determine if the items function
differently across cultural groups.
Rationale: A DIF analysis is the most appropriate step to empirically determine whether the flagged items exhibit
bias (i.e., function differently for different cultural groups after controlling for ability). Revising items (B) may be
premature without evidence of DIF. Removing items (A) or altering the blueprint (C) would compromise content
validity without addressing the underlying issue.
Page 4
