Scribd
Upload
4 views5 pages

Data Science

The document contains a series of questions and answers related to data analysis concepts, statistical methods, and machine learning techniques. Key topics include data preparation, regression analysis, and the CRISP-DM framework. Each question addresses specific terminology or principles within the field of analytics and statistics.

Uploaded by

rounak.kr123321
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views5 pages

Data Science

The document contains a series of questions and answers related to data analysis concepts, statistical methods, and machine learning techniques. Key topics include data preparation, regression analysis, and the CRISP-DM framework. Each question addresses specific terminology or principles within the field of analytics and statistics.

Uploaded by

rounak.kr123321
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Q1 Garbage in garbage out

Answer: Data Preparation

Q2 R factor baseline
Answer: East

Q3 Invalid R variable name


Answer: [Link]

Q4 Analytics vs Statistics
Answer: Analytics = certainty, Statistics = inference

Q5 BMI creation step


Answer: Construct Data

Q6 Goal Seek setup


Answer: Profit=0 by changing sales

Q7 Mixed dataset structure


Answer: Data Frame

Q8 aggregate function
Answer: Mean age by sex

Q9 Association rule support/confidence


Answer: Depends on support

Q10 Skewed distribution


Answer: Mean > Median

Q11 Regression slope meaning


Answer: Sales increase per ■1 lakh ad spend

Q12 Nominal data averaging issue


Answer: Cannot average categories
Q13 Random Forest concept
Answer: Multiple trees + averaging

Q14 CRISP-DM monitoring


Answer: Plan monitoring & maintenance

Q15 R '+' prompt


Answer: Waiting for completion

Q16 Regression p-values


Answer: Only significant predictors matter

Q17 Adjusted R² drop


Answer: Added variables are not useful

Q18 Threshold change


Answer: More recall, more false positives

Q19 Market basket rule


Answer: Bundle products

Q20 Excel data table


Answer: One output only

Q21 [Link] behavior


Answer: TRUE for NA and NaN

Q22 Hypothesis test


Answer: Fail to reject null

Q23 Validation need


Answer: Avoid overfitting

Q24 Data size estimate


Answer: Exabyte
Q25 Dummy variables
Answer: n-1 rule

Q26 Sensitivity analysis


Answer: Test input impact

Q27 Moore’s Law


Answer: Processing cost decreases

Q28 Dummy variables cities


Answer: 3 dummies

Q29 Sensitivity scenario


Answer: Sensitivity Analysis

Q30 Moore’s Law analytics


Answer: Cheaper computing

Q31 PCA Kaiser


Answer: 3 components

Q32 Time series first step


Answer: Visualization

Q33 Scaling methods


Answer: Std vs MinMax

Q34 DIKW
Answer: Wisdom

Q35 Lift
Answer: Strong association

Q36 Excel 2 variable


Answer: Two-way table
Q37 Model evaluation
Answer: Overfitting risk

Q38 Correlation
Answer: Significant positive

Q39 Tree shallow


Answer: Underfitting

Q40 Scenario manager


Answer: Multiple inputs

Q41 Default prediction


Answer: Logistic regression

Q42 CRISP-DM nature


Answer: Iterative

Q43 Delay prediction


Answer: Predictive analytics

Q44 Boxplot
Answer: Outlier

Q45 MAE
Answer: Avg error ~5%

Q46 Missing skewed


Answer: Median

Q47 CRISP-DM step


Answer: Iterate back

Q48 KMO
Answer: Drop low MSA
Q49 R coercion
Answer: Character

Q50 Deep tree


Answer: Overfitting

You might also like