MAR3616 - Final Exam

Data Matrix

Table of data.

• Each row — represents one record/item.

  • Example: Record or item may be states.

• Each column | represents one characteristic or observation.

  • Example: Average age per state, population of state.

• Should be ready by the end of the data preparation stage.

File

The entire dataset, aka everything put together in one.

Record

A summary of all the information about one individual’s responses.

Variable

A type of information about the response.

• Example: Age, Gender, Income.

What are two MINOR issues researchers should be aware of in the cleaning stage?

1. Ambiguities (Example: Vague responses to open-ended questions).

2. Inconsistencies (Example: Contrasting answers to questions in the survey).

What are two MAJOR issues researchers should be aware of in the cleaning stage?

1. Missing values (They can partly be avoided by using the “Force Question” option on each question).

2. Unreliable responses or respondents (Respondents may not understand the questions or take them seriously).

How to fix missing values?

1. Leave the response blank and let Excel identify it as a missing value.

2. Use the sample mean to substitute for the missing value (RECOMMENDED).

3. Discard (RECOMMENDED).

Unreliable responses or Respondents

• Create an intentional or unintentional response error that is difficult to eliminate.

• Must be DISCARDED if the respondent did not take it seriously.

Descriptive Data Analysis

Rearranging, ordering, or manipulating the data to generate descriptive information that is easy to understand and interpret.

What are the three types of Descriptive Data?

1. Counting Noses (Frequency, Percentage)

2. Central Tendency (Median, Mean, Mode)

3. Variation (Range, Standard Deviation)

Frequency

The number of times a response shows up in the data.

• Mainly used for nominal and ordinal data.

• Bar graph.

Percentage

Proportion of responses in the data.

• Mainly used for nominal and ordinal data.

• Formula: Frequency / Sample Size

• Pie Graph.

Central Tendency

Central or typical value for the sample data. It tells you where the bulk of the data is.

• Mean

• Mode

• Median

Mean

Average value of the sample.

• Most representative and frequently used in Descriptive data.

Median

The middle value of the sample data.

• You have to rank the data from smallest to largest to find it.

Mode

The value that occurs most frequently in the sample data.

Variation

Measures how dispersed or spread out the sample data is.

Range

The difference between the maximum value and the minimum value.

• Formula: Maximum Value - Minimum Value

Standard Deviation

The average deviation from the sample mean. Aka, how far, on average, your values are from the mean.

How to find Standard Deviation:

1. Find the mean.

2. Subtract the mean from all the values.

3. Square each value.

4. Add them altogether.

5. Divide by Number of Values - 1

6. Square root the whole thing.

7. Final Answer.

What are the two types of data that can be analyzed with any method?

• Ratio

• Interval

Best methods to summarize Interval and Ratio Data:

• Mean

• Standard Deviation

Best methods to summarize Nominal and Ordinal Data:

• Frequency

• Percentage

Central Tendency methods to measure Nominal Data:

Mode

Central Tendency methods to measure Ordinal Data:

• Mode

• Median