Data Analysis and Research Methodology

8/12/2019 Data Analysis and Research Methodology

http://slidepdf.com/reader/full/data-analysis-and-research-methodology 1/23

Institute of Chartered Accountantsof India 1



DATA ANALYSIS



What is a Data Analysis…

Data analysis is a practice in which raw data is ordered and

organized so that useful information can be extracted from it.

It can also be said that Data Analysis is a process of inspecting,cleaning, transforming, and modeling data with the goal of

highlighting useful information, suggesting conclusions, andsupporting decision making.

Data analysis has multiple facets and approaches, encompassingdiverse techniques under a variety of names, in different business,

science, and social science domains.



Importance of Data Analysis…

No business can survive without analyzing available data.Whether one wants to arrive at some marketing decisions or fine-tune new product launch strategy, data analysis is the key to all theproblems.

Data analysis is not a decision making system, but decisionsupporting system.

Data analysis can offer the following benefits:

Structuring the findings from survey research or other means ofdata collection.

Break a macro picture into a micro one.Acquiring meaningful insights from the dataset.Basing critical decisions from the findings.Ruling out human bias through proper statistical treatment.



Process Data Analysis…

Initial data analysis 1 Quality of data2 Quality of measurements3 Initial transformations4 Did the implementation of the study fulfill the intentions of

the research design?

5 Characteristics of data sample6 Final stage of the initial data analysis7 Analyses

Main data analysis

1 Exploratory and confirmatory approaches2 Stability of results3 Statistical methods



Initial Data Analysis… Quality of data

Data quality can be assessed in several ways, using different types of analyses:frequency counts, descriptive statistics (mean, standard deviation, median),normality (skewness, kurtosis, frequency histograms, normal probability plots),associations (correlations, scatter plots).

Other initial data quality checks are:

Checks on data cleaning: The distribution of the variables before data cleaning iscompared to the distribution of the variables after data cleaning to see whether datacleaning has had unwanted effects on the data.

Analysis of missing observations: are there many missing values, and are the valuesmissing at random? The missing observations in the data are analyzed to seewhether more than 25% of the values are missing, whether they are missing atrandom (MAR), and whether some form of imputation is needed.

Analysis of extreme observations: outlying observations in the data are analyzed tosee if they seem to disturb the distribution.



Initial Data Analysis…Contd.

Quality of Measurement

The quality of the measurement instruments should only be checkedduring the initial data analysis phase when this is not the focus or researchquestion of the study.

One should check whether structure of measurement instruments

corresponds to structure reported in the literature.

There are two ways to assess measurement quality:

Confirmatory factor analysisAnalysis of homogeneity (internal consistency), which gives an indication

of the reliability of a measurement instrument. During this analysis, oneinspects the variances of the items and the scales.




Initial transformations

After assessing the quality of the data and of the measurements, one mightdecide to impute missing data, or to perform initial transformations of oneor more variables, although this can also be done during the main analysis

phase.[

Possible transformations of variables are:

Square root transformation (if the distribution differs moderately fromnormal)Log-transformation (if the distribution differs substantially from normal)Inverse transformation (if the distribution differs severely from normal)

Make categorical (ordinal / dichotomous) (if the distribution differsseverely from normal, and no transformations help)








Final stage of the initial data analysis

During the final stage, the findings of the initial data analysis aredocumented, and necessary, preferable, and possible corrective actions are

taken.

Also, the original plan for the main data analyses can and should bespecified in more detail and/or rewritten.

In order to do this, several decisions about the main data analyses can andshould be made:

In the case of non-normals: should one transform variables; make

variables categorical (ordinal/dichotomous); adapt the analysis method?In the case of missing data: should one neglect or impute the missingdata; which imputation technique should be used?In the case of outliers: should one use robust analysis techniques?In case items do not fit the scale: should one adapt the measurementinstrument by omitting items, or rather ensure comparability with other

(uses of the) measurement instrument(s)




Analyses

Several analyses can be used during the initial data analysis phase:

Univariate statistics

Bivariate associations (correlations)

Graphical techniques (scatter plots)



Main Analysis…

Exploratory and confirmatory approaches

In the main analysis phase either an exploratory or confirmatory approach can beadopted. In an exploratory analysis no clear hypothesis is stated before analyzingthe data, and the data is searched for models that describe the data well. In aconfirmatory analysis clear hypotheses about the data are tested.

Exploratory data analysis should be interpreted carefully. When testing multiple

models at once there is a high chance on finding at least one of them to besignificant, but this can be due to a type 1 error.

One should not follow up an exploratory analysis with a confirmatory analysis in thesame dataset. An exploratory analysis is used to find ideas for a theory, but not totest that theory as well. When a model is found exploratory in a dataset, thenfollowing up that analysis with a confirmatory analysis in the same dataset could

simply mean that the results of the confirmatory analysis are due to the same type 1error that resulted in the exploratory model in the first place. The confirmatoryanalysis therefore will not be more informative than the original exploratory analysis



Main Analysis…Contd.

Stability of results

It is important to obtain some indication about how generalizable theresults are. While this is hard to check, one can look at the stability of theresults. Are the results reliable and reproducible? There are two main waysof doing this:

Cross-validation: By splitting the data in multiple parts we can check ifanalyzes (like a fitted model) based on one part of the data generalize toanother part of the data as well.

Sensitivity analysis: A procedure to study the behavior of a system ormodel when global parameters are (systematically) varied. One way to dothis is with bootstrapping.



Main Analysis…Contd.

Statistical methods

A lot of statistical methods have been used for statistical analyses. A verybrief list of four of the more popular methods is:

General linear model: A widely used model on which various statisticalmethods are based (e.g. t test, ANOVA, ANCOVA, MANOVA). Usable for

assessing the effect of several predictors on one or more continuousdependent variables.

Generalized linear model: An extension of the general linear model fordiscrete dependent variables.

Structural equation modelling: Usable for assessing latent structures frommeasured manifest variables.

Item response theory: Models for (mostly) assessing one latent variablefrom several binary measured variables (e.g. an exam).



RESEARCH METHODOLOGY



What is research…

Research in common parlance refers to a search for knowledge.

Once can also define research as a scientific and systematic search forpertinent information on a specific topic.

In fact, research is an art of scientific investigation.

The Advanced Learner’s Dictionary of Current English lays down themeaning of

research as “a careful investigation or inquiry specially through searchfor new

facts in any branch of knowledge.”

Research is, thus, an original contribution to the existing stock ofknowledge making for its advancement. It is the pursuit of truth with thehelp of study, observation, comparison and experiment.



Characteristics of research…

-Controlled The concept of control implies that, in exploring causality in

relation to two variables (factors), you set up your study in a way that

minimizes the effects of other factors affecting the relationship.

Rigorous you must be scrupulous in ensuring that the proceduresfollowed to find answers to questions are relevant, appropriate and

justified. Again, the degree of rigor varies markedly between the physicaland social sciences and within the social sciences.

Systematic this implies that the procedure adopted to undertake aninvestigation follow a certain logical sequence. The different steps cannotbe taken in a haphazard way. Some procedures must follow others.

Valid and verifiable this concept implies that whatever you conclude onthe basis of your findings is correct and can be verified by you and others.

Empirical this means that any conclusion drawn are based upon hardevidence gathered from information collected from real life experiences orobservations.



Objectives of research…

The purpose of research is to discover answers to questions through theapplication of scientific procedures. The main aim of research is to find out

the truth which is hidden and which has not been discovered as yet.Though each research study has its own specific purpose, we may think ofresearch objectives as falling into a number of following broad groupings:

1. To gain familiarity with a phenomenon or to achieve new insights into it(studies with this object in view are termed as exploratory or formulative

research studies);2. To portray accurately the characteristics of a particular individual,situation or a group (studies with this object in view are known asdescriptive research studies);3. To determine the frequency with which something occurs or with whichit is associated with something else (studies with this object in view areknown as diagnostic research studies);4. To test a hypothesis of a causal relationship between variables (suchstudies are known as hypothesis-testing research studies).



The research process or methodology…

The research process is similar to undertaking a journey.

For a research journey there are two important decisions to make-1) What you want to find out aboutor what research questions (problems) you want to find answers to;2) How to go about finding their answers.

There are practical steps through which you must pass in your research journey in order to find answers to your research questions.The path to finding answers to your research questions constitutesresearch methodology.

At each operational step in the research process you are required to choose

from a multiplicity of methods, procedures and models of researchmethodology which will help you to best achieve your objectives.

This is where your knowledge base of research methodology plays a crucialrole.



The research process or methodology… Contd.

Steps in Research Process:

1. Formulating the Research Problem

2. Extensive Literature Review

3. Developing the objectives

4. Preparing the Research Design including Sample Design

5. Collecting the Data

6. Analysis of Data

7. Generalization and Interpretation

8. Preparation of the Report or Presentation of Results-Formal write ups ofconclusions reached.



The research methodology… A graphical example.



Institute of Chartered Accountantsof India 23

Documents

Data Analysis and Research Methodology