Data Intro (14)

Question 1

SPSS

Answer 1

Help us analyze data without the need of coding

Question 2

What is the main purpose of data preparation in marketing research?

Answer 2

To validate, clean, and format data so it can be properly analyzed using statistical tools.

Question 3

Why is SPSS preferred over Excel for data analysis in marketing research?

Answer 3

SPSS offers a user-friendly interface, handles large datasets more efficiently, is less prone to formula errors, and keeps a log of actions.

Question 4

Why not use Excel ?

Answer 4

1. Limited ability to handle large data
2. Prone to erros in formula
3. No running log of actions

Question 5

Data Processing Stages

Answer 5

1. Data Validation
2. Data Preparation
3. Data Analysis

Question 6

What happen in Data Validation ?

Answer 6

Confirm data collection occur as planned

Check for erros/problems

If possible adress or repair collection error

Question 7

Data Preparation

Answer 7

1. Data Entry - Convert data to electronic form
2. Data Coding - Group and assign codes to responses
3. Data Cleaning - Sort out errors and inconsistencies, add new variables

Question 8

Data Preparation - Data entry

Answer 8

1 row per participant

Variables as columns

Question 9

Data Preparation - Data Coding

Answer 9

Give variables meaningfull names

Group and assign numeric codes to any question responses that are open ended

Question 10

Example of coding scheme

Answer 10

Beauty on the inside = 1

Beauty is natural = 2

Beauty is an attitude = 3

Question 11

Dummy Coding

Answer 11

Yes = 1

No = 0

Question 12

Data Preparation - Data Cleaning

Answer 12

Chech for data entry errors or data entry inconcistencies

Question 13

Data Cleaning Assumption

Answer 13

Never erase or remove data . just flag in a new variable column - Poor data or similarly

Question 14

Missing Data

Answer 14

1. Missing Completely at Random (MCAR)
2. Missing At Random (MAR)
3. Missing not at Random (MNAR)

Question 15

What is MCAR (Missing Completely at Random)?

Answer 15

No pattern in what’s missing — it’s totally random.

Example: A random form was damaged.

Question 16

What is MAR (Missing at Random)?

Answer 16

Missingness is related to other known data, not the missing value itself.

Example: People with less education skip income.

Question 17

What is MNAR (Missing Not at Random)?

Answer 17

Missingness is caused by the value that’s missing.

Non-response error

Example: Low-income people don’t report income because it’s low.

Question 18

Options to Dealing with Missing Data

Answer 18

1. Litwise Deletion

2, Pairwise Deletioin

3. Recover the Values
4. Imputation

Question 19

Litwise Deletion

Answer 19

Delete all data from any participant with missing values

Only analyse cases with available data on each variable

Question 20

Pairwise deletion

Answer 20

Analyze all cases with variables present

Question 21

Recover the values

Answer 21

Administrator Surveys can catch this during survey completion

Question 22

Imputation

Answer 22

Replace Missing Values with substitute values.

Uses regression to predict

Question 23

Deletion

Answer 23

Mean exclusion in analysis, not actual deletion

Question 24

What are the three common strategies to handle missing data?

Answer 24

Listwise Deletion: Remove all data from a participant with any missing values.

Pairwise Deletion: Use available data for each analysis.

Imputation: Replace missing data with estimated values (mean, median, regression-based).

Question 25

What are the steps involved before actual data analysis begins?

Answer 25

Downloading data, validating it, identifying missing values, cleaning the data, and preparing it for statistical testing.

Question 26

What is data coding in qualitative research?

Answer 26

Transforming open-ended responses into numerical codes (e.g., "Beauty is Natural" = 2) for easier analysis.