Data Mining - Type and Quality of Data

Multiple Choice

The following statements regarding data are true, except:

• A dataset is a collection of objects with their properties or characteristics.

• An object or record is described by a set of attributes

• The same attribute always has the same attribute value

• Attributes are properties of an object

Time for Quiz

Some text here about the topic of discussion

Multiple Choice

The following attributes are qualitative or categorical attributes, except:

• NBI number of UNTAG student

• Age in years

• Ranks in the military

• The flight number of an airline

Multiple Choice

Density measured in grams per cubic centimeter is an attribute:

• nominal

• ordinal

• ratio

• interval

Multiple Choice

In a transaction dataset, there is a total_transaction attribute in rupiah. The properties of these attributes are as follows:

• Categorical, nominal, discrete

• Categorical, interval, continuous

• Numeric, interval, discrete

• Numerical, ratio, continuous

Time for Quiz

Some text here about the topic of discussion

Multiple Choice

The following datasets are record dataset types, except:

• data graph

• Matrix data

• Transaction data

• Document data

Multiple Choice

Data with the following characteristics is a scourge that will be avoided when we implement the clustering method

• high dimension data

• high sparsity data

• low dimension data

• high resolution data

time for quiz

Some text here about the topic of discussion

Multiple Choice

Data quality problems that arise at the time of data collection are as follows, except:

• Noise

• Outliers

• Missing value

• Duplicate data

Multiple Choice

The following is how to handle missing values, except

• estimate the missing value

• pay attention to missing values when doing analysis

• discard object with missing value

• replace with possible values with probability calculations