.

Chapter Five
Processing and Analysis of Data

1
 Outlines

Quantitative Data Analysis

Data Management and Processing
Steps in Data preparation
Data Analysis
Qualitative Data Analysis

2
 Quantitative Data Analysis
Data Management and Processing
Data Preparation for Input
Once data are collected, process of analysis begins.
 Data have to be translated in an appropriate form. This process
is called Data Preparation.
Steps in Data Preparation
1)Questionnaire checking
2)Edit questionnaires
3)Code the questionnaires
4)Keypunch the data
5)Edit/Screen and Clean the data set
3
1) Questionnaire checking
 A questionnaire returned from the field may be
unacceptable for several reasons, for example:
o Parts of the questionnaire may be incomplete;
o One or more pages are missing…
2) Editing
Basic approaches:
i. Go back to the respondents for clarification;
ii .Discard the response altogether
4
3) Coding
Data entry refers to the creation of a computer file that holds the
raw data taken from all of the questionnaires deemed suitable for
analysis.
Coding means assigning a code, usually a number, to each possible
response to each question.
Codebook
Before you can enter the information from your questionnaire, into
SPSS, it is necessary to prepare a ‘codebook’.

5
 A Codebook contains coding instructions and the
necessary information about variables in the data set.
 Thus, a Data Codebook identifies all of the variable
names and code numbers associated with each possible
response to each question that makes up the data set.
 Preparing the codebook involves deciding (and
documenting) how you will go about:
o defining and labeling each of the variables
o assigning numbers to each of the possible responses.

6
 In your codebook you should list all of the variables in your
questionnaire, the abbreviated variable names that you will
use in SPSS and the way in which you will code the
responses (see Table 1).
Table 1: Example of a codebook
Variable SPSS variable name Coding instructions
Identification number ID Number assigned to each
survey
Sex Sex 1 = Male, 2 = Female
Marital status Marital 1 = Married, 2 = Single, 3 =
Divorced, 4 = Widowed
Service Quality scale items 1 - 5 sq1 to sq5 Enter the number circled
from 1(strongly disagree) to
5 (strongly agree) 7
4) Keypunch the Data/Data Transcription
Transcribing data is the process of transferring the coded data from
the questionnaire or coding sheets directly into computers .
5) Data Editing and Cleaning
Before you start to analyze your data, it is essential that you check
your data set for errors.
It is very easy to make mistakes when entering data, and
unfortunately some errors can completely mess up your analyses.

8
 The data editing/screening process involves a number of
steps:
Step 1: Checking for errors.
First, you need to check each of your variables for scores
that are out of range (i.e. not within the range of possible
scores.
When checking for errors, you are primarily looking for
values that fall outside the range of possible values for
a variable.
9
 For example, if sex is coded 1=male, 2=female, you should
not find any scores other than 1 or 2 for this variable. Scores
that fall outside the possible range can distort your statistical
analyses—so it is very important that all these errors are
corrected before you start.
Step 2: Finding and correcting the error in the data file.

 You need to find where in the data file this error occurred (i.e.
which case is involved) and correct or delete the value.

10
Data Analysis
 Quantitative data analysis involves the techniques by
which researchers convert data to numerical forms and
subject to statistical analyses.
 Once data have been collected they have to be analyzed.
 Three factors which affect how the data are analyzed
are:
1) The number of variables being examined;
2) The level of measurement of the variables;
3) Whether we want to use our data for descriptive or
inferential purposes. 11
1) The Number of Variables
Univariate, Bivariate and Multivariate Analyses
 Univariate Analysis is the analysis of a single variable.
 Since univariate analysis does not involve relationships between two
or more variables, its purpose is more toward descriptive rather than
explanatory. Example: Frequency distribution, percentage, Mean
 Bivariate analysis is concerned with the analysis of two variables at a
time
 If we are interested in two variables simultaneously we will use a
bivariate (two variable) method. For example, if we wanted to see the
relationship between employee’s satisfaction and organizational
performance.
12
 Exploring relationships between variables means searching for
evidence that the variation in one variable coincides with
variation in another variable.
 Multivariate analysis entails the simultaneous analysis of three
or more variables.
 If our research question makes use of three or more variables we
would use a multivariate technique.
 Ex.To study factors that affect individual income( determinants of
income, you have to use multivariate analysis
Income =f (Education ,Gender, Age, Experience )

13
 The method of analysis adopted depends on the
complexity of the research question. If the
research question involves only one variable, select
a method of analysis appropriate for univariate
analysis. If the question involves two variables use a
method designed for bivariate analysis and so on.
 Within each level of analysis (univariate, bivariate,
multivariate) there is a range of methods of analysis
(see Table 2 ).
14
Table 2: Some Methods of Survey Analysis

Univariate Bivariate Multivariate

methods methods methods

1. Frequency 1. Comparison of 1. Correlation

distributions Means 2. Multiple
2. Diagrams 2. Regression regression
3. Measures of 3. Correlation 3. Path analysis
central
tendency and
15
dispersion
2.Measurement of variables
The choice between methods is determined in part by the
level of measurement of the variables involved:
Ex. Nominal data can be analyzed with frequencies and
percentages.
Using various charts are appropriate for ordinal variables.
 Some methods of analysis are appropriate only for variables
measured at certain levels.
Having chosen an appropriate method of analysis, the choice
of statistics to be used with that particular method is affected
both by the method of analysis itself and the level of
measurement of the particular values.
16
3) Descriptive and Inferential Statistics
There are two basic types of statistics: descriptive and
inferential.
The choice of statistics is determined by different
previous decisions such as, level of measurement of the
variables and complexity of the research question
(univariate, bivariate or multivariate).

17
A) Descriptive Statistics
Descriptive statistics summarizes the characteristics of a
data set.
In descriptive statics you are not trying to infer properties
about a larger population.
One can present descriptive statistics in tables or graphs.
 Descriptive statistics frequently use the following Statistical
measures
Measures of central tendency = Mean, Median, Mode
Measures of Dispersion = Range, variance, Standard
18
deviation
B) Inferential Statistics
Typically, we are not interested simply in describing the attitudes
and characteristics of just the people in a sample. Rather, we want to
generalize the results from the sample to a wider population or to
test hypothesis
Inferential Statistics uses to make inferences from our data to
more general conditions.
The function of inferential statistics is to provide an idea about
whether the patterns described in the sample are likely to apply in
the population from which the sample is drawn /to check weather
the null hypothesis is true or false.
19
Errors in Statistical Hypothesis Testing (Type I Erriors
and Type II Erriors)
Since Ho must be ether true or false, there are two possible
correct outcomes
i. correct rejection of Ho when it is false and
ii. Retaining Ho when it is true.
Therefore ,There are two possible errors that can be made
type I an type II errior
Type I errior occurs when Ho is incorrectly rejected.
Type II errior occurs when Ho is incorrectly failed to
reject.

The probability depends on the source of data, sample

20
size, choosing appropriate design.
 During Hypothesis Testing Condition of null hypothesis may
be,

Possible
True False
action

Fail to reject Ho Correct action Type II error

Reject Ho Type I error Correct action

21
 The most common Methods in inferential statistics are
 Measures of Skewness
 Their fundamental task is to characterize the location and variability
of adata set.
Skewness is a measure of symmetry of adata set.
Adata set is symmetric if it looks the same to the left and the right of
the center point.
 Correlations analysis(used to describe the strength and direction of
the linear relationship between two variables).
 Coefficient of Correlation
 A measure of the strength of linear relationship between two variables.
 Represented by ‘r’. r lies between +1 to -1, i.e. -1 ≤ r ≤ +1.
 Strong correlation when r > 0.5 or r < -0.5,Moderate correlation when r=0.29 to 0.49 or r=-0.29 to
0.49 and Weak correlation when r=0.1 to 0.29 or r=-0.1 to-0.29

 Regression Analysis(Used to estimate/Predict the average effect of independent

variable on dependent variable).
22
Regression
The regression technique is primarily used to:
oEstimate the relationship that exists, on the average, between the
dependent variable and the independent variable.
oDetermine the effect of each of the independent variables on the
dependent variable, controlling the effects of all other independent
variables.
oPredict the value of the dependent variable for a given value of the
independent variable.

23
Types of Regression Analysis
Regression analysis is generally classified into two kinds: simple
and multiple regressions.
Simple regression involves only two variables, one of which is
dependent variable and the other is independent variable.
Multiple regression includes two and more number of independent
variables.

Utilize Computer for Data Processing (Using SPSS)

24
Qualitative Data Analysis
Qualitative Data Analysis (QDA) is the range of processes
and procedures whereby we move from the qualitative data
that have been collected into some form of explanation,
understanding or interpretation of the people and
situations we are investigating.
QDA is usually based on an interpretive philosophy. The idea is to
examine the meaningful and symbolic content of qualitative data.
QDA begins with more general open-ended questions, moving
toward greater precision as more information emerges.

.
25
Steps for Analysis of Qualitative Data
1.Prepare and organize Your data. Print out your transcripts,
gather your notes, documents or other materials
2.Review and explore the data
3.Create initial codes
4.Review those codes and revise or combine in to themes
5.Present themes in cohesive manner.

26
 Reading Assignment
Exercise how to use SPSS for quantitative data
Analysis.

Ethiopian Civil Service

University/Department of Public 27
Management