Q4. Chapter 3: Data Pre-processing [ PLO S3/CLO 2.1/502] [6.5 marks] Redundancy is an important issue...

Transcribed Image Text:

Q4. Chapter 3: Data Pre-processing [ PLO S3/CLO 2.1/502] [6.5 marks] Redundancy is an important issue in data integration. An attribute may be redundant if it can be "derived (obtained)" from another attribute or set of attributes. Some redundancies can be detected by correlation analysis between attributes. For nominal data, we use the 2 (chi-square) test which assesses how one attribute's values vary from those of another. x - -25600 25600 6 1. What hypothesis does the x2 (chi-square) test? 2. Considering the following table, compute the x2 value. Answer: Like science fiction Not like science fiction Sum(col) 121.904 Answer: Male Female 250 (90) 200 (360) 50 (210) 1000 (840) 1200 300 3. Explain the meaning of a large x2 value. Answer: Sum (row) 450 1050 1500 (Observed - Expected) Expected [1.5 marks] (Expected count) 200x130-90* 1500 160 (250+ 90) -210) 210 [2 marks] +(5/70 + -160 (200-360) 360 160 (1000-940) 840 576 121.90 71 mark] 4. What is the alternate name used by Rapid Miner software tool to designate a Boxplot diagram? [2 Marks] am and to elevant blem and t ir relevant te a comp computin rogram's Score Q4. Chapter 3: Data Pre-processing [ PLO S3/CLO 2.1/502] [6.5 marks] Redundancy is an important issue in data integration. An attribute may be redundant if it can be "derived (obtained)" from another attribute or set of attributes. Some redundancies can be detected by correlation analysis between attributes. For nominal data, we use the 2 (chi-square) test which assesses how one attribute's values vary from those of another. x - -25600 25600 6 1. What hypothesis does the x2 (chi-square) test? 2. Considering the following table, compute the x2 value. Answer: Like science fiction Not like science fiction Sum(col) 121.904 Answer: Male Female 250 (90) 200 (360) 50 (210) 1000 (840) 1200 300 3. Explain the meaning of a large x2 value. Answer: Sum (row) 450 1050 1500 (Observed - Expected) Expected [1.5 marks] (Expected count) 200x130-90* 1500 160 (250+ 90) -210) 210 [2 marks] +(5/70 + -160 (200-360) 360 160 (1000-940) 840 576 121.90 71 mark] 4. What is the alternate name used by Rapid Miner software tool to designate a Boxplot diagram? [2 Marks] am and to elevant blem and t ir relevant te a comp computin rogram's Score