1. DATA ANALYSIS PROCESSING DATA Editing Data Process for coding 2.

1

LECTURE 11

2

OUTLINE

DATA ANALYSIS PROCESSING DATA Editing Data Process for coding

3

OUTLINE

DATA ANALYSIS PROCESSING DATA Editing Data Process for coding

4

DATA ANALYSIS

Ways to use/organize/manipulate data in order to reach research conclusions.

5

PROCESSING DATA

1. EDITING DATA2. CODING DATA3. DEVELOPING A FRAME OF ANALYSIS4. ANALYSING DATA

6

EDITING DATA Data Cleaning

Checking the completed instruments; to identify and minimize

errors incompleteness inconsistencies misclassification etc. (illegible writing)

7

CODING DATA

2 Considerations for Coding:Measurement of a variable (scale?,

structure – open/closed ended?).

Communication of findings about a variable (measurement scale?, type of statisitical procedures?) (e.g., Ratio scale – mean, mode, median)

8

PROCESS FOR CODING: For analysis using computer, data must

be coded in numerical values. The coding of raw data involves 4 steps:

Developing a code book (master-code book)Pre-testing the bookCoding the data; and Verifying the coded data.

9

DEVELOPING A FRAME OF ANALYSIS Develop from beginning of research

and evolve continuously to end.

Frame of analysis: Identify variable to analyseDetermine method to analyseDetermine cross-tabulations needed Determine which variable to combine for

constructing major concepts or develop indices

Identify which variable for which statistical procedures

10

ANALYZING DATA

11

LEVEL OF ANALYSIS

1. UNIVARIATE ANALYSIS2. BIVARIATE ANALYSIS3. MULTIVARIATE ANALYSIS

12

UNIVARIATE ANALYSIS Is the examination of the distribution

of cases on only one variable at a time.

Distributions Central tendency Dispersion

Can be generated thro’ Descriptive statistics in the SPSS.

Purpose of univariate analysis is purely descriptive.

13

The full original data usually difficult to interpret.

Data reduction is the process of summarizing the original data to make them more manageable; while maintaning the original data as much as possible.

14

DISTRIBUTIONS Attribute of each each case under study

in terms of the variable in question. Reporting marginals E.g., how many respondents, what % of

them fall under a certain variable.500 of 1000 FEM students have

CGPA = 3.5 & above.50% of 1000 FEM students.

15

FREQUENCY DISTRIBUTION

Shows the number of cases having each of the attributes of a given variable.

16

CENTRAL TENDENCY

Reporting summary In term of averages

Mode (most frequent attribute)Mean (arithmetic mean)Median (middle attribute)

17

WHICH MEASURE OF CENTRAL TENDENCY TO USE?

Measure Level of Measurement

Examples

Mode Nominal Eye color, party affiliation

Median Ordinal Rank in class, birth order

Mean Interval & ratio Speed of response, age in years

18

DISPERSION

Spread of raw data/info of a variable. Detailed information of distribution of a

variable.Range (simplest measure)PercentileStandard deviation (more sophisticated)

19

Range: distance separating the highest from the lowest value.

(e.g., the respondents mean age is 22.75 with a range from 20 to 26).

20

PERCENTILE A number or score indicating rank by

telling what percentage of those being measured fell below that particular score.

e.g., scored 75th percentile, means 75% of the other people scored below your score and 25% scored at or above your score.

21

STANDARD DEVIATION

Is a measure of the average amount the scores in a distribution deviate from average (mean) of the distribution.

Observation near mean, small SD. Observation far from mean, large SD.

22

BIVARIATE ANALYSIS Focuses on the relationships/association

between two variables.

Among the many measures of bivariate association are eta, gamma, lambda, Pearson’s r, Kendall’s tau, and Spearman’s rho.

23

MULTIVARIATE ANALYSIS Is a method of analyzing the

simultaneous relationships among several variables and may be used to understand the relationship between two variables more fully.

e.g., multiple regression, factor analysis, path analysis, discriminant analysis.