Font size
WorksheetsThe Game is Over
Total questions: 91
Worksheet time: 3hrs 6mins
Which of the following tests is best used to compare two independent groups with ordinal data?
Wilcoxon Signed Rank Test
Kruskal-Wallis Test
Mann-Whitney U Test
ANOVA
What type of data do nonparametric tests often use?
Continuous and exact values
Ordinal or ranked data
Binary data only
Normal distribution data
What does the Hypothesis Matrix (H) show in MANOVA?
Variance between each group
Difference from overall mean
Sum of total errors
Number of dependent variables
Which test statistic in MANOVA is known to be most robust to non-normality?
Roy’s Maximum Root
Wilks’ Lambda
Hotelling-Lawley Trace
Pillai’s Trace
The Error Matrix (E) in MANOVA measures how different each group’s mean is from the overall mean.
True
False
A smaller value of Wilks’ Lambda means the groups are more likely different.
True
False
In regression formula, X is the thing we want to predict.
True
False
The accuracy of inferential statistics depends on how representative the sample is.
True
False
Discrete probability distributions can take infinite values.
True
False
Inferential statistics are useful when studying the entire population is not practical.
True
False
Choose the correct equation for Wilks Lambda.
Λ=∣H∣+∣E∣∣E∣
T02=trace(HE−1)
V=trace(H(H+E−1))
θ=maxeigenvalue(HE−1)
Choose the correct equation for the Hotelling-Lawley Trace.
Λ=∣H∣+∣E∣∣E∣
T02=trace(HE−1)
V=trace(H(H+E−1))
θ=maxeigenvalue(HE−1)
Choose the correct equation for Pillai’s Trace.
Λ=∣H∣+∣E∣∣E∣
T02=trace(HE−1)
V=trace(H(H+E−1))
θ=maxeigenvalue(HE−1)
Choose the correct equation for Roy’s Maximum Root.
Λ=∣H∣+∣E∣∣E∣
T02=trace(HE−1)
V=trace(H(H+E−1))
θ=maxeigenvalue(HE−1)
Using a two‑tailed t‑test at α=0.05 with critical values ±2.093 , a nutrition label claims a drink contains 200 calories. A sample of n=20 bottles has a sample mean of 193 calories and a sample standard deviation of 12 calories. Select the appropriate null and alternative hypotheses for testing whether the mean calories differ from 200.
H0: μ=200 ; H1: μ=200
H0: μ=200 ; H1: μ=200
H0: μ>200 ; H1: μ<200
H0: μ<200 ; H1: μ>200
Using two‑tailed test at α=0.05 , critical t=±2.093 ; n=20 , sample mean 193, sample standard deviation 12, test against population mean 200. What is the calculated t‑statistic (rounded to two decimals)?
−2.60
−2.09
−1.93
2.60
Using the same drink‑calorie context and the calculated t≈−2.60 compared to the critical values ±2.093 , what is the correct decision?
Reject the null hypothesis
Fail to reject the null hypothesis
Increase the sample size and retest instead of making a decision
Switch to a one‑tailed test
Two diets are tested with a two‑tailed t‑test at α=0.05 and critical values ±2.011 . Diet A: mean weight lost xˉ1=4.2 kg, s1=1.1 , n1=25 . Diet B: mean weight lost xˉ2=3.7 kg, s2=1.3 , n2=25 . Assume equal variances. Select the appropriate null and alternative hypotheses for testing whether the diets differ in effectiveness.
H0: μ1=μ2 ; H1: μ1=μ2
H0: μ1=μ2 ; H1: μ1=μ2
H0: μ1>μ2 ; H1: μ1<μ2
H0: μ1<μ2 ; H1: μ1>μ2
Using the diet context with equal variances: xˉ1=4.2 , s1=1.1 , n1=25 ; xˉ2=3.7 , s2=1.3 , n2=25 . What is the pooled‑variance two‑sample t‑statistic (rounded to two decimals)?
1.46
2.01
0.73
−1.46
Using the diet context and the calculated t≈1.46 compared to the critical values ±2.011 , what is the correct decision?
Fail to reject the null hypothesis
Reject the null hypothesis
Use a one‑tailed test instead of deciding
Conclude that Diet A is significantly better than Diet B
Why do some people use data marketplaces?
To find movies
To play games
To buy ready datasets
To rent equipment
What is one advantage of in-house data collection?
Very fast to use
No need for labeling
Full control over data
Data is always free
Which challenge involves privacy laws like GDPR?
Data Privacy and Security
Continual Retraining
Data Management
Quality Assurance
Which industry uses image annotation for tumor detection?
Retail
Healthcare
Agriculture
Education
Which tool is macOS-exclusive and supports video annotation?
LabelImg
RectLabel
Doccano
VOC XML
What is the main purpose of annotation tools?
To create games for machine learning models
To label data for training machine learning models
To write reports about machine learning models
To design user interfaces for machine learning models
Public datasets are always perfect and made only for your project.
True
False
Crowdsourcing is when many people help collect data online.
True
False
Properly labeled data increases model bias and reduces learning speed.
True
False
Polygons are used to include all objects in an image.
True
False
LabelImg allows users to export annotations in XML, CSV, or TXT formats.
True
False
RectLabel offers auto-labeling using Core ML models.
True
False
Crowdsourcing — choose the correct option
Text annotation tool for NLP tasks
Use human-in-loop systems
People label photos using MTurk
Use pandas or seaborn early
Analyze Before Modeling — choose the correct option
Text annotation tool for NLP tasks
Use human-in-loop systems
People label photos using MTurk
Use pandas or seaborn early
Continual Retraining — choose the correct option
Text annotation tool for NLP tasks
Use human-in-loop systems
People label photos using MTurk
Use pandas or seaborn early
Subjectivity — choose the correct option
Text annotation tool for NLP tasks
Use human-in-loop systems
People label photos using MTurk
Use pandas or seaborn early
Which factors should be considered when choosing the right annotation tool? Select all that apply.
Data type
Annotation task
Platform support
Project scope and collaboration
What does a “Gold Standard” provide in annotation?
A reference point for high-quality labeling
A tool for automatic model evaluation
A rule to remove duplicate annotations
A system to replace manual checks
What is Krippendorff’s Alpha mainly used for?
Measuring color intensity in images
Checking data agreement with missing values
Calculating the number of annotators needed
Comparing training speed of AI models
What does annotation consistency mean?
Applying labels randomly across data
Applying labels differently each time
Applying labels uniformly and reliably
Applying labels without clear rules
How can poor annotation tools cause inconsistencies?
They make annotation faster
They suggest incorrect labels
They reduce annotator bias
They improve annotation clarity
In medical imaging, annotated data mainly supports:
Cancer detection and organ identification
Buying medical tools for hospitals
Training doctors to use new equipment
Writing reports for insurance purposes
In retail and e-commerce, data annotation helps companies to:
Provide personalized shopping experiences
Increase the number of warehouse workers
Deliver products faster to all customers
Reduce the cost of building new stores
Cohen’s Kappa is used to measure agreement between more than three annotators.
True
False
Fleiss’ Kappa allows scenarios where each rater rates different items.
True
False
Well-defined labeling categories always confuse annotators.
True
False
Annotation consistency means that data labels change often to match new trends.
True
False
Data annotation in agriculture is used to separate crops from weeds.
True
False
Social media platforms use annotation to detect spam and trends.
True
False
Annotator Consensus — choose the correct option
Causes accidental mislabeling
Reviewers agree on labels, or discuss disagreements
Gives instructions on how to handle unusual data
Help create fairer models
Identify faces and monitor activities
Highlight Edge Cases — choose the correct option
Causes accidental mislabeling
Reviewers agree on labels, or discuss disagreements
Gives instructions on how to handle unusual data
Analyze player performance in games
Identify faces and monitor activities
Fatigue and human error — choose the correct option
Causes accidental mislabeling
Reviewers agree on labels, or discuss disagreements
Gives instructions on how to handle unusual data
Help create fairer models
Identify faces and monitor activities
Reduced bias — choose the correct option
Causes accidental mislabeling
Reviewers agree on labels, or discuss disagreements
Gives instructions on how to handle unusual data
Help create fairer models
Identify faces and monitor activities
Security and Surveillance — choose the correct option
Causes accidental mislabeling
Reviewers agree on labels, or discuss disagreements
Gives instructions on how to handle unusual data
Analyze player performance in games
Identify faces and monitor activities
Sports analytics — choose the correct option
Causes accidental mislabeling
Reviewers agree on labels, or discuss disagreements
Gives instructions on how to handle unusual data
Analyze player performance in games
Help create fairer models
Select the correct set to complete: The three pillars of telemetry are ________, ________, and ________.
logs, traces, metrics
metrics, latency, anomalies
logs, metrics, uptime
traces, models, backups
Select the correct set to complete: Monitoring helps detect ________ and prevent failures.
Anomalies
logs
uptime
traces
Select the correct set to complete: ________ stands for Application Performance Monitoring.
APM
KPI
SRE
SLA
Select the correct set to complete: Continuous monitoring ensures ________ over time.
Model Accuracy
Model Latency
Cost Savings
Uptime
Select the correct set to complete: ________ ensures the system remains accurate and reliable.
AI monitoring
Backup
Normalization
Query optimization
Select the correct set to complete: ________ uses data to prevent system breakdowns.
Predictive maintenance
Incremental backup
Adoption KPIs
Audit Trail
Select the correct set to complete: ________ measure how frequently users interact with AI systems.
Adoption KPIs
Business KPIs
Cost Savings KPIs
Uptime
Select the correct set to complete: Proprietary APMs provide ________.
cloud integration and vendor support
incremental backup
normalization
audit trail
Select the correct set to complete: ________ measure how AI affects organizational goals.
Business KPIs
Model Latency metrics
anomalies
Query optimization
Select the correct set to complete: ________ KPIs show the financial benefit of AI.
Cost Savings
Uptime
Adoption
Backup
Select the correct set to complete: ________ measures the percentage of system availability.
Uptime
Model Latency
logs
traces
Select the correct set to complete: ________ refers to response generation time.
Model Latency
Model Accuracy
Uptime
Cost Savings
Select the correct set to complete: Access logs record ________ the system and ________.
who used and when
CPU and memory
anomalies and exceptions
user frustration and session length
Select the correct set to complete: Error logs capture ________.
system failures and exceptions
user frustration
audit trail entries
backup status
Select the correct set to complete: System logs monitor ________, ________, and ________.
CPU, memory, and performance
adoption, uptime, anomalies
logs, traces, metrics
cost savings, vendor support, normalization
Select the correct set to complete: A very short session may suggest ________.
user frustration
uptime
backup
normalization
Select the correct set to complete: ________ finds unusual activity patterns.
Anomaly detection
Query optimization
Incremental backup
Audit Trail
Select the correct set to complete: A ______ record of all user activities for accountability.
Audit Trail
Backup
Adoption KPIs
Business KPIs
Select the correct set to complete: ________ ensures data recovery after system failure.
Backup
Incremental backup
Query optimization
Normalization
Select the correct set to complete: ________ is used for managing relational databases.
SQL
PostgreSQL
Regression testing
Query optimization
Select the correct set to complete: ________ reduces data duplication.
Normalization
Incremental backup
Regression testing
Adoption KPIs
Select the correct set to complete: ________ increases database efficiency.
Query optimization
Anomaly detection
Model Latency
Backup
Select the correct set to complete: ________ saves only changed data.
Incremental backup
Full backup
Audit Trail
Cloud integration
Select the correct set to complete: ________ example of a relational database.
PostgreSQL
SQL
Anomaly detection
Uptime
Select the correct set to complete: ______ automates building and testing updates.
Regression testing
Version control
rollback plan
Select the correct set to complete: ______ are urgent corrections applied live.
System updates
User feedback
Version control
Select the correct set to complete: A ______ restores a previous stable version.
Regression testing
Hotfixes
System updates
Select the correct set to complete: ______ tracks all code changes.
Hotfixes
System updates
Regression testing
Select the correct set to complete: ______ checks old features after updates.
System updates
Hotfixes
User feedback
Select the correct set to complete: ______ improve performance and security.
Regression testing
Hotfixes
Continuous integration
Select the correct set to complete: ______ stands for Net Promoter Score.
Feedback loops
User feedback
Regression testing
Select the correct set to complete: ______ helps focus resources on the changes that will have the greatest impact on user satisfaction and business goals.
Surveys
User feedback
Feedback loops
Select the correct set to complete: ______ guides updates and feature design.
Sentiment analysis
Surveys
Feedback loops
Select the correct set to complete: ______ ensure continuous system enhancement.
Sentiment analysis
Surveys
Continuous integration
Select the correct set to complete: ______ determines the tone of user comments.
Surveys
Regression testing
User feedback
Select the correct set to complete: ______ are a common feedback collection tool.
Sentiment analysis
Regression testing
User feedback
