Prelims

Question 1

Methods of Data Collection:

Answer 1

Observation
Interview
Questionnaire

Question 2

Seeks to ascertain what people think and do by watching them in action as they express themselves in various situations and activities.

Answer 2

Observation

Question 3

Instead of writing the response the interviewee subject gives the needed information verbally face-to-face relationship.

Answer 3

Interview

Question 4

Provides speedy and simple technique gathering data about groups of individuals scattered in a wide and extended field.

A questionnaire form is sent usually by post / online

Answer 4

Survey Questionnaire

Question 5

Sampling Techniques

Answer 5

• Probability Random Sampling
• Non-Probability Non-Random Sampling

Question 6

Start with a complete sampling frame of all eligible individuals from which you select your sample. (unbiased)

Answer 6

Probability Sampling Method

Question 7

Probability Sampling Method

Answer 7

• Simple Random
• Systematic Sampling
• Stratified Sampling
• Clustered Sampling

Question 8

Each individual or unit in the population has an equal chance of being selected. Selection is done randomly. Ensuring unbiased representation.

using methods like a lottery system or a random number generator

Answer 8

Simple Random Sampling

Question 9

A method where elements are selected from an ordered population at regular intervals. The first sample is chosen randomly within the first interval, and subsequent samples follow a fixed pattern.

(e.g., every 5th or 10th individual).

Answer 9

Systematic Sampling

Question 10

Population is divided into distinct subgroups (strata) based on shared characteristics

(e.g., age, income level, education).

Answer 10

Stratified Sampling

Question 11

Population is divided into occurring groups (clusters).

(e.g., schools, neighborhoods, or companies. )

Answer 11

Clustering Sampling

Question 12

All members of the selected clusters are surveyed

Answer 12

one-stage cluster sampling

Question 13

random subset of individuals within selected clusters is surveyed

Answer 13

two stage cluster sampling

Question 14

Not all members of the population have an equal chance of being selected. Instead, selection is based on subjective judgment, convenience, or specific criteria set by the researcher.

Answer 14

Non-Probability Sampling

Question 15

Used in exploratory research, qualitative studies, or when probability sampling is impractical due to resource constraints.

Answer 15

Non-Probability Sampling

Question 16

Non-Probability Sampling

Answer 16

• Convenience Sampling
• Quota Sampling
• Purposive Sampling
• Snowball Sampling

Question 17

Participants are selected based on their availability, accessibility, and willingness to participate rather than random selection.

Answer 17

Convenience Sampling

Question 18

Used in pilot studies, exploratory research, or when time and resources

Answer 18

Convenience Sampling

Question 19

Researchers deliberately selected individuals who are most relevant to the researcher topic based on predefined criteria, expertise, or specific characteristics.

Answer 19

Purposive Sampling

Question 20

Commonly used in qualitative research.

Answer 20

Purposive Sampling

Question 21

Researchers divide the population into subgroups (quotas) and select participants from each subgroup to ensure representation based on characteristics like age, gender, or income. The selection process is not random, so not all population members have an equal chance of participating.

Answer 21

Quota Sampling

Question 22

Existing participants recruit future participants from their network, particularly useful for studying hard-to-reach or specialized populations.

Answer 22

Snowball Sampling

Question 23

Starts with few known individuals who refer others, creating a chain of referrals.

Answer 23

Snowball Sampling

Question 24

Methods in Data Presentation

Answer 24

• Textual Method
• Tabular Method
• Graphical Method

Question 25

Using written or descriptive explanations without tables or graphs. Involves narrating findings in sentences and paragraphs to convey insights.

Answer 25

Textual Method

Question 26

A structured ways of presenting data in rows and columns using table, organizes numerical or categorical data systematically for easy comprehension.

Answer 26

Tabular Method

Question 27

Visual representation of data using charts, graphs, or diagrams to simplify complex information and highlight trends, patterns, or relationships.

Answer 27

Graphical Method

Question 29

Question

Answer 29

Answer

Question 30

Data types

Answer 30

* numeric, categorical * static, dynamic (temporal)

Question 31

Other kinds of data

Answer 31

* distributed data * text, Web, meta data * images, audio/video

Question 32

missing attribute values, lack of certain attributes of interest, or containing only aggregate data | e.g., occupation=“”

Answer 32

incomplete data

Question 33

containing errors or outliers | e.g., Salary=“-10”

Answer 33

noisy data

Question 34

containing discrepancies in codes or names | Age=“42” Birthday=“03/07/1997” Was rating “1,2,3”, now rating “A, B, C”

Answer 34

inconsistent data

Question 35

Why is data Processing Important?

Answer 35

* No quality data, no quality mining results * Quality decision must be based on quality data * Duplicate or missing data may cause incorrect or even misleading statistics

Question 36

Multi-Dimensional Measure of Data Quality

Answer 36

* Accuracy * Completeness * Consistency * Timeliness * Believability * Value added * Interpretability * Accessibility

Question 37

Major Tasks in Data Processing

Answer 37

* Data Cleaning * Data Integration * Data Transformation * Data Reduction * Data discretion

Question 38

Fill in missing values, smooth noisy data, identify or remove outliers and noisy data, and resolve inconsistencies | number one problem in data warehousing

Answer 38

Data Cleaning

Question 39

Data Cleaning Tasks:

Answer 39

* Fill in Missing Values * Identify outliers and smooth out noisy data * Correct Inconsistent Data * Resolve Redundancy caused by data integration

Question 40

Data is not always available (many tuples have no recorded values for several attributes, such as customer income in sales data)

Answer 40

Missing Data

Question 41

Missing data causes:

Answer 41

* Equipment malfunction * Inconsistent with other recorded data and thus deleted * Data not entered due to misunderstanding * Certain data may not be considered important at the time of entry * Not register history or changes of the data

Question 42

Handling missing data

Answer 42

* Ignore the tuple * Fill in missing values manually: tedious and infeasible * Fill it automatically

Question 43

Fill missing data with

Answer 43

* A global constant e.g., unknown * The attribute mean * The most probable value:inferenced-based such as Bayesian formula, decision tree or EM algorithm

Question 44

Random error or variance in a measured variable

Answer 44

Noisy Data

Question 45

Incorrect attribute values may due to:

Answer 45

* Faulty data collection instruments * Data entry problems * Data transmission problems

Question 46

Handling Noisy Data

Answer 46

* Binning Method * Clustering * Combined computer and human inspection

Question 47

When reducing noise and trend analysis is needed

Answer 47

Smoothing by bin means

Question 48

When keeping real-world constraints and preserving limits is important

Answer 48

When keeping real-world constraints and preserving limits is important

Question 49

Detect and remove outliers, Data points inconsistent with the majority of data

Answer 49

Clustering

Question 50

Integration of multiple databases or files

Answer 50

Data Integration

Question 51

Integrate metadata from different sources Entity identification problem: identify real world entities from multiple data

Answer 51

Schema Integration

Question 52

Removing noise from data

Answer 52

Smoothing

Question 53

scaled to fall within a small, specified range

Answer 53

Normalization

Question 54

summarization

Answer 54

Aggregation

Question 55

concept hierarchy climbing

Answer 55

Generalization

Question 56

Normalization

Answer 56

* Min-max normalization * Z-score normalization * Normalization by decimal scaling

Question 57

Obtains reduced representation in volume but produces the same or similar analytical results. Data is too big to work with.

Answer 57

Data Reduction

Question 58

Data Reduction Strategies

Answer 58

* Dimension reduction—remove unimportant attributes * Aggregation and clustering * Sampling

Question 59

Feature selection (i.e., attribute subset selection): Select a minimum set of attributes (features) that is sufficient for the data mining task.

Answer 59

Dimension Reduction

Question 60

Popular reduction technique. Divide data into buckets and store average (sum) for each bucket

Answer 60

Histograms

Question 61

Choose a representative subset of data

Answer 61

Sampling

Question 62

Data discretion three types of attributes

Answer 62

* Nominal * Ordinal * Continuous

Question 63

# Data discretion three types of attributes values from an unordered set

Answer 63

Nominal

Question 64

# Data discretion three types of attributes values from an ordered set

Answer 64

Ordinal

Question 65

# Data discretion three types of attributes real numbers

Answer 65

Continuous

Question 66

Data discretion techniques

Answer 66

* Binning Method - equal-width, equal-frequency * Entropy-based (1) * Entropy-based (2)

Question 67

for bin width of e.g., 10:

Answer 67

Equi-width binning

Question 68

for bin density of e.g., 3

Answer 68

Equi-frequency binning

Question 69

Reduce the number of values for a given continuous attribute by dividing the range of the attribute into intervals. Interval labels can then be used to replace actual data values

Answer 69

Discretization

Question 70

Reduce the data by collecting and replacing low level concepts (such as numeric values for the attribute age) by higher level concepts (such as young, middle-aged, or senior)

Answer 70

Concept Hierarchies