ITBAN 3 - Fundamentals of Analytics Modelling Data Preprocessing

Data preprocessing is not necessary before data analysis.

Incomplete data with lacking attribute values does not affect data quality.

Noise in data refers to errors or outliers.

Data inconsistency is not a concern in data preprocessing.

Quality decisions can be made based on poor quality data.

Data preprocessing involves tasks such as filling in missing values and identifying outliers.

Data transformation in preprocessing involves randomizing the data for better analysis results.

Data reduction in preprocessing aims to increase the volume of data for more accurate analytical results.

Missing data in a dataset can occur due to equipment malfunction or intentional removal of valuable information.

Data preprocessing may involve inferring missing data based on the available information.

Handling missing data is not a crucial step in the data preprocessing process.

Equal-width partitioning divides the range into N intervals of different sizes.

Equal-depth partitioning divides the range into N intervals with different sample quantities.

Binning methods for data smoothing involve sorting data only.

Linear regression is used to fit data into regression functions.

Cluster analysis involves detecting and removing outliers.

Semi-automated methods combine computer and human inspection to only detect suspicious values.

Ignoring the tuple is always an effective method when the class label is missing in a classification task.

Filling in missing values manually is a quick and efficient process.

Using a global constant like 'unknown' to fill in missing values introduces a new class.

Filling in missing values with the attribute mean improves data quality.

Using the attribute mean for all samples of the same class to fill in missing values is not a smarter approach.

Noise in data is usually caused by consistent and accurate measurements.

Data cleaning is one of the steps involved in preprocessing the data.

Data integration involves combining data from a single source into a coherent store.

Schema integration in data preprocessing refers to resolving conflicts between different data types.

Detecting and resolving data value conflicts is a part of the data integration process.

Incomplete data with lacking attribute values does not impact data quality during preprocessing.