Mba 2 Sem Research Methodology (Bangalore University) (5)

8/8/2019 Mba 2 Sem Research Methodology (Bangalore University) (5)

1/21

Processing of dataProcessing of data

MODMOD -- 0505


2/21

INTRODUCTIONINTRODUCTION

Data processing is an intermediary stage of work betweenData processing is an intermediary stage of work between

data collection and data interpretation.data collection and data interpretation.

The data gathered from in the form of questionnaires..... IsThe data gathered from in the form of questionnaires..... Is

mostly in the form of a large volume of research variables.mostly in the form of a large volume of research variables.

The various steps in processing of data may be stated as:The various steps in processing of data may be stated as:

Identifying data structuresIdentifying data structures

Editing the dataEditing the data

Coding & classifying the dataCoding & classifying the data

Tabulation of dataTabulation of data


3/21

EDITINGEDITING

Editing is the a process of checking to detectEditing is the a process of checking to detect

and correct errors and omission.and correct errors and omission.Data editing happens at two stage :Data editing happens at two stage :

one at the time of recording the data.one at the time of recording the data.

second at the time of analysis of data.second at the time of analysis of data.


4/21

Contd:Contd:--

The editing step checks for the completeness,The editing step checks for the completeness,

accuracy and uniformity of the data set created byaccuracy and uniformity of the data set created by

the researcherthe researcher

Completeness :Completeness :-- the first step of editing is to checkthe first step of editing is to check

whether there is an answer to all thewhether there is an answer to all the

question/variable set out in the data set. If therequestion/variable set out in the data set. If there

were any omission, the researcher sometime wouldwere any omission, the researcher sometime would

be able to deduce the correct answer from otherbe able to deduce the correct answer from other

related data on the same instrument.related data on the same instrument.


5/21

Contd:Contd:--

Accuracy:Accuracy:--

Apart from checking for omission, the accuracy ofApart from checking for omission, the accuracy of

each recorded answer should be checked.each recorded answer should be checked.

A random check process can be applied to traceA random check process can be applied to trace

the errors at this step.the errors at this step.

Consistency in response can also be checked atConsistency in response can also be checked atthis step.this step.


6/21

CONTD :CONTD :--

Uniformity :Uniformity :-- In editing data sets, another keenIn editing data sets, another keenlook out should be for any lack of uniformity inlook out should be for any lack of uniformity in

interpretation of questions and instructions by theinterpretation of questions and instructions by thedata recorders.data recorders.

While interpreting the answers, care should beWhile interpreting the answers, care should be

taken as to record the answer as a positivetaken as to record the answer as a positive

question response or as a negative questionquestion response or as a negative question

response.response.


7/21

Contd:Contd:--

The final point in the editing of the data setsThe final point in the editing of the data sets

is to maintain a log of all corrections thatis to maintain a log of all corrections that

have been carried out at this stage. Thehave been carried out at this stage. The

documentation of these corrections help thedocumentation of these corrections help the

researcher to retain the original data set.researcher to retain the original data set.


8/21

CODINGCODING

The edited data are then subject to coding .

Coding process assign numerals or other symbols to the

several responses of the data set.

At the recording stage itself , if some codification weredone to the responses collected, it would be useful in the

data analysis.

Coding gives a benefits a research, by verification and

editing of recordings & further contact with therespondents can be achieved without any difficulty.

The codification can be made at the time of distribution of

the primary data sheet itself.


9/21

Methods of codingMethods of coding

Numeric codingNumeric coding::-- coding has to be numeric, when thecoding has to be numeric, when the

variable is to be subject to further parametric analysis.variable is to be subject to further parametric analysis.

Parametric

A test that involves metric data (i.e. data from interval or

ratio scales that can be analyzed statistically)

All parametric test are based on the assumption of normality

i.e. population is considered to be normally distributed.


10/21

EXAMPLEEXAMPLE

Policies in your organization :Policies in your organization :

Leave arrangementLeave arrangement

Are you aware of this polices Do you feel this policy areAre you aware of this polices Do you feel this policy are

important in organizationimportant in organization

Yes NO IMP V.IMP UN IMP V.UNIMPYes NO IMP V.IMP UN IMP V.UNIMP

CareerCareer

StudyStudy

ReligiousReligious

trainingtraining


11/21

CONTD:CONTD:--

Alphabetic coding:Alphabetic coding:--

Amere tabulation or frequency countAmere tabulation or frequency countor graphical representation of theor graphical representation of the

variable may be given an alphabeticvariable may be given an alphabetic

coding.coding.


12/21

ExampleExample

A.A. Policies in your organization :Policies in your organization : LeaveLeave

arrangementarrangement

B. Parenting related issuesB. Parenting related issues

C Flexible work arrangementC Flexible work arrangement

D. Additional work provisionD. Additional work provision


13/21

Contd :Contd :--

Zero coding:Zero coding:-- coding of zero has tocoding of zero has toassigned carefully to a variable.assigned carefully to a variable.

In many instance , when manual analysisIn many instance , when manual analysisis done, a code of 0 would imply a nois done, a code of 0 would imply a noresponse from the respondents.response from the respondents.

There will be a tendency to give a code ofThere will be a tendency to give a code of0 to a no response0 to a no response


14/21

Examples of codingExamples of coding

Question NoQuestion No VariableVariable Response categoryResponse category codecode

1.11.1 organizationorganization PrivatePrivate

GovtGovt

PtPt

GoGo

1.21.2 Owner of vehicleOwner of vehicle YesYes

nono

22

11

2.12.1 VehicleVehicle

performanceperformance

ExcellentExcellent

GoodGood

badbad

33

22

11

2.22.2 occupation Salaried

Professional

Business

others

S

P

B


15/21

classificationclassification

When openWhen open--ended responses have been received,ended responses have been received,

classification is necessary to code the response.classification is necessary to code the response.

The scheme of classification should be there ie categoryThe scheme of classification should be there ie category

for every response.for every response.

The inclusion of classification others tends to fill in theThe inclusion of classification others tends to fill in the

cluttered, but few responses from the data sheet.cluttered, but few responses from the data sheet.


16/21

ExampleExample

Mention the items which you bought recentlyMention the items which you bought recently

Durables ..Durables ..

Non durables ..Non durables .. Groceries & food items ..Groceries & food items ..

Fashion & health products ..Fashion & health products ..

Others (plse specify) ..Others (plse specify) ..

The classification others will be very useful whenThe classification others will be very useful whenminority of responses in the data set give varyingminority of responses in the data set give varyinganswer.answer.


17/21

TabulationTabulation

The transcription of data can be used toThe transcription of data can be used to

summarize and arrange the data in a compactsummarize and arrange the data in a compact

form for further analysis . The process is calledform for further analysis . The process is calledtabulation.tabulation.

Tabulation is a process of summarizing raw dataTabulation is a process of summarizing raw data

and displaying them on compact statistical tablesand displaying them on compact statistical tables

for further analysis.for further analysis.

It involves counting the number cases falling intoIt involves counting the number cases falling into

each of the categories identified by the researcher.each of the categories identified by the researcher.


18/21

Methods of tabulationMethods of tabulation

Manual tabulation : frequency tableManual tabulation : frequency table

Computerized tabulation : SPSS Software.Computerized tabulation : SPSS Software.

E.g.E.g. EASY TO IMPLEMENTEASY TO IMPLEMENT--1010Question A Year 5 4Question A Year 5 4 3 2 13 2 1

Is it easy to get things doneIs it easy to get things done

in your working group / team?(C) 2009 24 54 7 10 4in your working group / team?(C) 2009 24 54 7 10 4


19/21

Contd:Contd:--

EASY TO IMPLEMENTEASY TO IMPLEMENT--1010

Question B Year 5 4 3 2 1Question B Year 5 4 3 2 1

Are decisions implementedAre decisions implemented

quickly enough in yourquickly enough in your

Company ? 2009 14 43 15 19 9Company ? 2009 14 43 15 19 9


20/21

Graphs and chartsGraphs and charts

Simple line graphSimple line graph

Market line graphMarket line graph

HistogramHistogram

Vertical / horizontal gar chartVertical / horizontal gar chart

Pie chartPie chart


21/21

EXAMPLESEXAMPLES

0

1020

30

40

50

6070

80

90

1st Qtr 2nd Qtr 3rd Qtr 4th Qtr

East

West

North

Mba 2 Sem Research Methodology (Bangalore University) (5)

Documents