Scribd
Upload
99 views31 pages

Data Preparation and Preliminary Data Analysis

The document discusses key steps in data preparation and preliminary data analysis for marketing research: 1. After fieldwork and data collection, researchers edit, code, and enter the data to prepare it for analysis. This involves detecting errors, assigning codes to responses, and inputting data into statistical software. 2. Researchers then conduct preliminary descriptive analyses to understand the characteristics of the data and check assumptions like normality. 3. Hypothesis testing is also covered, where researchers formulate hypotheses, select tests, and compare calculated and critical values to interpret results. The overall process moves from data collection and preparation to preliminary descriptive analyses and hypothesis testing to evaluate the data.

Uploaded by

fiko
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
99 views31 pages

Data Preparation and Preliminary Data Analysis

The document discusses key steps in data preparation and preliminary data analysis for marketing research: 1. After fieldwork and data collection, researchers edit, code, and enter the data to prepare it for analysis. This involves detecting errors, assigning codes to responses, and inputting data into statistical software. 2. Researchers then conduct preliminary descriptive analyses to understand the characteristics of the data and check assumptions like normality. 3. Hypothesis testing is also covered, where researchers formulate hypotheses, select tests, and compare calculated and critical values to interpret results. The overall process moves from data collection and preparation to preliminary descriptive analyses and hypothesis testing to evaluate the data.

Uploaded by

fiko
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 31

Data preparation and

preliminary data
analysis

CHAPTER 7
Chapter Summary
01

Survey fieldwork and


02 data collection

CONTENTS Nature and scope of


03 data preparation

04 Preliminary data
analysis
Assessing for normality
05 and outliers

Hypothesis testing
07

CONTENTS Conclusion
08
01
Chapter Summary
Add You Text Here Add You Text Here
After developing an appropriate questionnaire and pilot
testing the same, researchers need to
undertake the field study and collect the data for analysis.
In this chapter, we shall focus on
the fieldwork and data collection process
02
Survey fieldwork and data
Add You Text Here Add You Text Here
collection
In the field of
marketing (especially in the case of
corporate research) primary data is rarely
collected by the
person who designed the research. It is
generally collected by the either people in
the research
department or an agency specialising in
fieldwork
Four Stages of the process of data collection

1 2 3 4

selection of training of supervision of evaluation


fieldworkers
Welcome to download this fieldworkers
Welcome to download this Welcomefieldworkers
to download this of fieldwork
Welcome and
to download this
Welcome to download this Welcome to download this Welcome to download this Welcome tofieldworkers.
download this
guidelines for fieldworkers in asking questions

a. Be thoroughly familiar with the questionnaire.


b. Ask the questions in the order in which they appear in the ques
tionnaire.
c. Use the exact wording given in the questionnaire
d. Read each question slowly.
e. Repeat questions that are not understood.
f. Ask every applicable question.
g. Follow instructions and skip patterns, probing carefully.
several probing techniques

a. Repeating the question


b. Repeating the respondents’ reply
c. Boosting or reassuring the respondent
d. Eliciting clarification
e. Using a pause (silent probe)
f. Using objective/neutral questions or comments
03
Nature and scope of data preparation
Add You Text Here Add You Text Here
Once the data is collected, researchers’ attention turns to data analysis. If the project
has been
organized and carried out correctly, the analysis planning is already done using the pi
lot test
data. However, once the final data has been captured, researchers cannot start analy
sing them
straightaway. There are several steps which are required to prepare the data ready fo
r analysis.
The steps generally involve
1. data editing and coding
2. data entry, and
3. data cleaning
Editing
The usual first step in data preparation is to edit the raw data collec
ted through the
questionnaire. Editing detects errors and omissions, corrects them
where possible, and
certifies that minimum data quality standards have been achieved.
The purpose of editing is to
generate data which is: accurate; consistent with intent of the ques
tion and other information
in the survey; uniformly entered; complete; and arranged to simplif
y coding and tabulation.
When responses are inappropriate or missing, the researcher ha
s three choices:
(a) Researcher can sometimes detect the proper answer by revie
wing the other information in the schedule.
(b) Researcher can contact the respondent for correct informatio
n
(c) Researcher strike out the answer if it is clearly inappropriate.
Coding
Coding involves assigning numbers or other symbols to answers
so the responses can be grouped into a limited number of classe
s or categories. One of the easiest ways to develop coding struct
ure for the questionnaire is to develop a
codebook.
Data entry
Once the questionnaire is coded appropriately, researchers input the data in
to statistical software package.
There are various methods of data entry.
Manual data entry or keyboarding remains a mainstay for researchers who
need to create a
data file immediately and store it in a minimal space on a variety of media.
Many large scale studies now involve optical
character recognition or optical mark recognition wherein a questionnaire is
scanned using optical scanners and computer itself converts the questionna
ire into a statistical output. Such
methods improve the overall effectiveness and efficiency of data entry.
Data cleaning
Data cleaning focuses on error detection and consistency checks
as well as treatment of missing responses. The first step in the da
ta cleaning process is to check each variable for data
that are out of the range or as otherwise called logically inconsist
ent data.
four options for treating missing values
(a) substituting missing value with a neutral value (generally mean value for the va
riable);
(b) substituting an imputed response by following a pattern of respondent’s other r
esponses;
(c) casewise deletion, in which respondents with any missing responses are discar
ded from the analysis and
(d) pairwise deletion, wherein only the respondents with complete responses for th
at specific variable are included.

The different procedures for data cleaning may yield different results
and therefore, researcher should take utmost care when cleaning the data. The dat
a cleaning should be kept at a minimum if possible.
04
Preliminary data analysis
Add You Text Here Add You Text Here
data analysis is mostly concerned with descriptive statistics.Descriptive
statistics, as the name suggests, describe the characteristics of the dat
a as well as
provide initial analysis of any violations of the assumptions underlying t
he statistical
techniques. It also helps in addressing specific research questions. Thi
s analysis is important
because many advance statistical tests are sensitive to violations in the
data. The descriptive
tests provide clarity to the researchers as to where and how violation is
occurring within the
dataset.
Descriptive statistics include the mean, standard deviation, range
of scores, skewness
and kurtosis. This statistics can be obtained using frequencies, d
escriptives or explore
command in SPSS. To make it clear, SPSS is one of the most us
ed statistical software
packages in the world. There are several other such software pac
kages available in the market
which include, Minitab, SAS, Stata and many others
Programmes such as SPSS can provide descriptive statistics
for both categorical and
continuous variables.
05
Assessing for normality and outliers
Add You Text Here Add You Text Here
To conduct many advance statistical techniques, researchers have to
assume that the data provided is normal (means it is symmetrical on
a bell curve) and free of outliers.
07
Hypothesis testing
Add You Text Here Add You Text Here
Hypothesis is an empirically testable though yet unproven statem
ent developed in
order to explain a phenomena. Hypothesis is generally based on
some preconceived notion of
the relationship between the data derived by the manager or the r
esearcher.
Generic process for hypothesis testing
1. Formulate the hypothesis
2. Select an appropriate test
3. Select desired level of significance
4. Compute the calculated difference value
5. Obtain the critical value
6. Compare the calculated and critical values
7. Marketing research interpretation
08
Conclusion
Add You Text Here Add You Text Here
• three aspects of marketing research process: data collection, da
ta preparation and preliminary data analysis.
• Once the data is collected using fieldwork, the next stage for the
researcher is to edit and code the data.
• The clean data is then used for analysis purposes by researche
rs.
• After the preliminary data is analysed for normality, researchers
undertake hypothesis testing.
THANKS
company is an association or collection of individuals,
whether natural persons, legal mixture of both.

You might also like