Ethics in Research: A contextual imperative

In today’s world of research, when the frequency of research has mushroomed, the question of ethics has come to the fore. We all learn ethics, sometimes at home, sometimes at educational institutions, sometimes even in course of social interactions. Ethics are broader, both in application and consideration, than laws; their implementation, however, becomes much more difficult. When it comes to research, the ethics angle becomes relevant for some reasons.

Research, in its implementation, aspires for perfection or prevention of error. For instance, any sample which is taken is aimed at representing the entire population. If at all, an ethical violation is committed in terms of fabrication or misrepresentation of data, not only does it violate ethical principles but also misappropriates the research results/findings.

Research also forms the foundation or basis for knowledge or further research; knowledge which is used or consumed by the society at large. For instance, the article in Harvard Business Review by a gentleman named Theodore Levitt, an article called “Marketing Myopia” became a cornerstone of not only for marketing but also for industrial analysis. The researcher therefore, has a fiduciary duty towards the public at large to not falsify such findings, simply because this misappropriation will propagate further misappropriations. From an economic and financial standpoint, it also makes sense to maintain ethical integrity in research. A client or the consumers of research are more likely to further or consume the research only if its integrity is maintained. This can especially be observed in case of market research agencies, for whom the acid test often becomes proving or ensuring the credibility of the research findings to prospective clients.

Research is rarely carried out in a compartmentalised fashion; there is always an element of cooperation between different entities across institutions and even geographical barriers. The upholding of ethical standards becomes almost an operational imperative in such cases. The ethical imperative becomes even more so in cases of life-concerning matters like medicine, defence etc.

Keeping in mind such problems, there are certain guidelines which should be kept in consideration while carrying any research initiative. First and foremost, ethics and economics are not always contraire aux each other; the economic feasibility should also be kept in mind while following ethics. This is after all a world of pragmatism, not altruism. Second, there’s no harm in sharing intellectual property and there’s no superiority in hiding it. There is a tacit notion that if one shares his research or acknowledges somebody else’s contribution explicitly, it would imply a shortcoming on the researcher’s part. On the contrary, a free flow of information is beneficial to everybody; the Internet thrives on its reputation as an information superhighway. There’s also a concretisation deficit; ethics as a discipline is not very concrete, which is why there is no firm consensus as to what is ethical and what is not. As research into ethics itself progresses, this matter will clear out the smoke. But most importantly, it is to be understood that research cannot be conducted at the cost of somebody’s free will and privacy.

In the words of German theologian Albert Schweitzer,

“Ethics is nothing else than reverence for life.”

After all, since research is nothing but an instrument of human inquiry, it should adhere to humanitarian ethics and there is no rationale grander than this.

Section B_Group 5_Jayesh Surisetti_13PGP082

Mixed Methods Research : Section (A) _Group 6_Gautam Gogada_Roll no (13PGP018)

 

Keep Calm and Use Mixed Methods Research

 

As a future marketing manager set upon conquering the corporate world, I am faced with a simple question. Which is the correct method of research for my product? Should I go for qualitative research or will quantitative research give me better insights? In the quest for an answer, I suddenly had a brainwave (or at least I thought I had, for almost a minute), why not use them both? I immediately turned to my uncle ‘Google’ for help and was surprised (and a little bit disappointed, or a lot), it’s already in use. But, lucky for me, in marketing, mixed methods research has received little coverage. So, I’ll give you an introduction and few leads, which if you follow will give you an insight so that you could get a little guidance in identifying design types appropriate for various rationales or research objectives and models of different design types that have been published in marketing journals.

 

First things first, you will also be hearing (or seeing) something called ‘Multi method’. But let’s not get confused, in the Handbook of Mixed Methods Research, distinctions have been made between these two terms:

(1)  Multi-method which involve multiple types of qualitative inquiry (e.g. case study and ethnography) or multiple types of quantitative inquiry (surveys and experiments); and

(2) Mixed methods which involve the mixing of the two types of data (Morse,    2003).

Mixed methods research is the type of research in which a researcher or team of researchers combines elements of qualitative and quantitative research approaches (e.g. use of qualitative and quantitative viewpoints, data collection, analysis, inference techniques) for the broad purpose of breadth and depth of understanding and corroboration (Johnson et al., 2007, p. 123).

 

Bookish things aside (they are boring as such), let’s have a look at what mixed method research has got to offer us.

A non-judgmental comparison of qualitative and quantitative research methods

Let’s have a look at the following statements:

Pro-quantitative method student researcher: I don’t want to conduct qualitative research, I’m not convinced that it is science and besides, it’s a lot of work.

Pro-qualitative method student researcher: I don’t want to conduct quantitative research, I’ve always been bad at maths and I don’t like statistics, and besides, I am not convinced that quantitative research is an exhaustive approach.

Do they sound familiar?

Let’s face it – it is natural for a young person to be protective of what they know and what they feel comfortable with, but can you really assign the terms ‘good’ or ‘bad’ to research methods?

Ponterotto and Grieger (1999) provided us with a non-judgmental comparison of qualitative and quantitative research. According to them, employing a qualitative approach to a research issue involves looking at it from a human science perspective in which the researcher aims to describe and understand meaning derived from the data in order to generate a theory from their analysis. On the other hand, employing a quantitative approach involves looking at the issue from a natural science perspective, focusing on the quantification of observed laws and causes when testing a theory or hypothesis. Considering this, one can conclude that both quantitative and qualitative research approaches are very different. Thus, there is no straightforward way of comparing them. In fact, both approaches are highly valued by researchers from various fields and that many of them suggest a mixed methods approach involving both qualitative and quantitative measures, whenever feasible, as a valuable option (Hanson, Creswell, Clark, Petska, & Creswell, 2005).

Conquering insecurities – no room for excuses!

Now let’s have a look at the some of the common complaints about the choice of a research method, and what I have come to understand through my research experience.

“Qualitative research is not science”

According to Morgan (1998), “a science must use procedures for gathering data that are reliable across observers; and when scientists have disagreements they must know, at least in principle, how to decide the issue by data.” Therefore, in my opinion, qualitative research can be very scientific by, for example, involving independent raters to back up one’s analysis. In addition, qualitative researchers may administer standardised tests to their participants in order to enrich their analysis. To illustrate, when interviewing individuals about their experiences in relation to stress (which seems to be a common focus of many qualitative student projects), a researcher can choose to take a stress measure and to separate their participants into two groups, making it possible to compare their scores using a simple independent samples t-test.

“Qualitative research is a lot of work”

Of course it is! All researches involve hard and diligent working. I admit that I was intimidated by the lengthy transcription process of interview materials when I conducted my undergraduate research (Ouzia, 2011). This is why I chose to have my participants answer questions in writing when I conducted my research. In this way, I was able to include a qualitative component into my research while avoiding from running out of time because of transcription commitments.

It is undeniable that both statistical and qualitative data analyses can take a long time. Furthermore, student research projects are assignments with a strict deadline. Thus, choosing two very different methods for the purpose of answering one question can be a scary endeavour that is reliant on the researcher’s awareness of her own limits. Nonetheless, by taking up the challenge of research rigour and time limitation, mixed method can teach us to think more creatively, so that we can come up with a more temporally feasible approach to our research, while at the same time, produces rich and well-rounded research findings.

“Quantitative research involves math, and I don’t like math”

In my opinion and experience, statistics is a theoretical phenomenon in its own right. Statistics drive our thought process when we are drawing up a research design, for example, the question of how international university students’ anxiety affects their concentration calls for a correlation analysis. What comes after the analysis is crucial in my opinion – the discussion. Correlation analysis is the researcher’s statistical tool of choice to help her make sense of what is going on in her data, but she still has to understand why that has happened. After all, the discussion section is where all the aspects of a research project (theoretical background, methodology, results, interpretation and future direction) come together. Here, it is important to note that a qualitative research aspect can help – rather than making assumptions about the underlying reasons of a finding (i.e. anxiety correlates with concentration and is mediated by student status/ being and international student), it would enrich the analysis greatly to evaluate how participants view the effect of their fears on their concentration.

“Quantitative research is not an exhaustive approach”

I’ve saved the best for last!

I have to admit that I agree with this notion but I also want to argue that this applies to both quantitative AND qualitative research. While quantitative research often does not tap into the experiences of the participant that are relevant to what is being tested, qualitative research often fails to deliver results that are generalisable to a wider population. I think I have argued that this is the key to a mixed methods approach in depth so far – so what do you think?

In my personal experience, employing a mixed methods approach has paid off for me; while my quantitative analysis did not reveal any significant results, my qualitative analysis revealed interesting aspects regarding how siblings of autistic children’s experiences differ from siblings of typically developing children (Ouzia, 2011).

Thematic analysis – quantifying qualitative analysis

Most psychology students will come into contact with some form of education on qualitative and quantitative research methods throughout their degree. One of the qualitative analysis techniques that were addressed in my undergraduate degree was thematic analysis. This type of analysis involves the evaluation of reoccurring themes from the source of interest (i.e. interview transcript, diary, or questionnaire). A much related analysis method is content analysis, where themes or categories are predefined and looked for in the data (Subvista, 2010). The beauty of the types of analyses is that they can deliver the best of both worlds – an opportunity to evaluate personal experience and to quantify it. Not only can a researcher show that certain themes occur, but they can count them, correlate them and compare them. This is related to what I was saying earlier; statistics is a tool that can be used in many creative ways and the way I see it is as long as you know what you want to get out of your analysis, you will find a way to conduct it.

A final note – what I am NOT saying

Mixed methods approaches come in a variety of forms and provide countless exciting possibilities. I have to admit that my current research endeavours do not include qualitative research methods because of the nature of my area. A mixed methods approach is by far not the answer to all questions. Sometimes, involving a qualitative or a quantitative component in your research will not be feasible.

 

Refer these links for awesome articles on mixed methods research

http://obssr.od.nih.gov/scientific_areas/methodology/mixed_methods_research/section2aspx#When%20should%20mixed%20methods%20be%20used

http://www.emeraldinsight.com/journals.htm?issn=09600035&volume=42&issue=8/9&articleid=17062822&show=html

 

References

Hanson, W. E., Creswell, J. W., Clark, V. L. P., Petska, K. S., & Creswell, J. D. (2005). Mixed methods research designs in counselling psychology. Journal of Counselling Psychology, 52, 224-235. doi: 10.1037/0022-0167.52.2.224.

Morgan, M. (1998). Qualitative research … Science or pseudo-science? The Psychologist, 11(10). 481-483.

Ouzia, J. (2011). Siblings of children with autistic spectrum disorders: experiences of stress, day-to-day life, sibling relationship and family life. (Unpublished Bachelors Dissertation). Anglia Ruskin University.

Ponterotto, J. G., & Grieger, I. (1999). Merging qualitative and quantitative perspectives in a research identity. In M. Kopala & L. Suzuki (Eds.), Using qualitative methods in psychology (pp. 49-62). Thousand Oaks, CA: Sage.

Subvista (2010, March 25). The process of thematic analysis. Retrieved fromhttp://subvista.wordpress.com/2010/03/25/new/

Exploring the process behind research methodology (Session 1)

Research involves questioning what you do. It comprises systematic observation of information to find the answers with an objective of bringing appropriate changes that will increase the effectiveness of professional service.

Recent trends in research can be seen in field of marketing. To name a few are:

Gamification: the use of game mechanics for a non-gaming context to engage the end users. This can be applied to increase user engagement, timeliness, learning, record user response etc. Users can be encouraged by giving virtual currencies, leader boards etc. Gamification can be seen extensively being used in social networking sites to encourage user participation.

Eye Tracker: This involves tracking the eye of a user for the point of gazing. This methodology is used in visual systems, product design etc. A heat map is generated based on the visual exploration pattern. Hot zone being the area where the user focuses its gaze more frequently

Fig 1.1 Heat map generated for web page.

Research comprises of following steps:

1. Analyse/Process
2. Observation
3. Interpretation/Enquiry
4. Strategy

Analyse and process being two different terms. Analyse refers to application of mind to identify the trends occurring in a given data set, whereas Process means application of statistical tool to transform data from one form to the other.

Acquisition of data from primary and secondary source is observation. Primary source is when data is recorded from the personal experience of the respondent and secondary data is when data already exists. Observation is necessary to formulate the hypothesis. Key to observation is that it should be free from any bias. Intuition and biases play a key role. Intuition is something that can be gained through experience whereas biases is inclination. Intuition can be applied while conducting research process.

Observations can be of types:

• Structured – for descriptive research
• Unstructured—for exploratory research
• Participant Observation
• Non- participant observation
• Disguised observation

Next step is interpreting the collected data which may then be followed by the strategy to draw the hypothesis.

“The formulation of a problem is often more essential than its solution”

Steps in research process:

I.            Problem discovery

II.            Research method

III.            Research design

IV.            Sampling

V.            Data gathering

VI.            Data processing and analysing

VII.            Conclusion and report

Above steps can be divided in two phases. Phase one consists of steps 1-3 and phase two consists of steps 4-7. Phase one should be allotted 70 % of the time and phase two consists of 30% of time allotted for the research process.

Problem discovery: It is the most crucial step. It determines what you want to find. Careful analysis may reveal the difference between a problem and a symptom. The way we formulate the problem determines the consecutive steps. Stakeholders can be included in order to come up with an effective problem.

The methods employed to carry out the research encompass this step can be descriptive or quantative. Research design is the conceptual design how the research will proceed. Few points that may be included:

1. Objectives of the research study.

2. Method of Data Collection to be adopted

3. Source of information—Sample Design

4. Tool for Data collection

5. Data Analysis– qualitative and quantitative

Sampling consists of who will be surveyed, how many will be surveyed, how will be sample selected etc. Samples can be probability or non-probability samples. Next step is to collect the data from which the inference has to be drawn from.

Processing and analysing data involves set of operations that can be used to summarize the collected data. Operations can be editing, classification, tabulation etc. based on the sample size data can be analysed either manually or using computer. After this all the findings has to be documented.

Section (A) _Group5_JayantPaul_13pgp024

Other members : Aashwij , Bhanupriya Gupta , Sukrit Singh , Lohita Chouhan , Jasleen Kaur Bhatia , Parthasarathi Nr

Research Methods_SectionB_Group8_AnuradhaSrivastava_RollNo(13PGP065)

“All progress is born of inquiry. Doubt is often better than over-confidence, for it leads to inquiry, and inquiry leads to invention.”

-Hudson Maxim

The word research is one which challenges easy definitions. It is defined as diligent inquiry or examination to seek or revise facts, principles, theories, or applications. It has to be systematic process of collecting, collating, analyzing and interpreting information to increase our understanding of the phenomenon under study. In simple terms, research is a serious mental adventure which is driven by intellectual curiosity. Research is a way of thinking.

Research methods are the methods which are used in performing research operations. There is mainly two research philosophies- Positivistic and Phenomenological approach. Positivistic approaches are founded on a belief that the study of human behavior should be conducted in the same way as studies conducted in the natural sciences. This approach uses methods like surveys, experiments etc. Phenomenological approaches are particularly concerned with understanding behavior from the participants’ own subjective frames of reference. Case studies, ethnography and action research is preferred method is this approach.

Broadly, research methods are classified under the following types:

SURVEY METHOD

The survey is a non-experimental, descriptive research method. Surveys involve selecting a representative and unbiased sample of subjects drawn from the group under consideration. Surveys can be classified as: descriptive survey (identifying and counting frequency of response for example how many vehicles use toll ways in a month) or analytical survey (analyze relationship between different variables for example which routes toll ways are most preferred). Surveys can also be classified as structured or unstructured and qualitative (open-ended questions) or quantitative (closed ended questions) depending on the list of questions. Survey research may be direct (questions about behaviors and thoughts) or indirect (questions revealing not the number of people but type of people).

 

Surveys can be conducted by following methods:

Mail Questionnaires:

Advantages of using mail questionnaires are:

• Large amounts of data can be collected at a low cost per respondent.
• Honest answers can be expected on condition of anonymity.
• No bias involved from interviewer side as well as respondent side.
• Good way to reach people who are not always accessible.

Disadvantages:

• Takes lot of time.
• Response rate is often very low.
• Flexibility is less.

Telephonic Interview:

Advantages:

• Quick response using this method.
• Flexible as interviewer can explain the incomprehensible questions.
• Allows greater control on sample population.
• Response rate is high.

Drawbacks:

• Cost per respondent is comparatively higher.
• Getting response to personal questions is difficult.
• Interviewer’s way of talking influences respondent’s answers.
• Interpretation of response also varies with interviewers.

Personal Interviews:                                      

Advantages:

• Very flexible and large amounts of information can be collected.
• Trained interviewers are can hold the respondent’s attention and are available to

clarify difficult questions.

• Interviews can be guided and responses can be effectively recorded.
• Can be conducted fairly quickly.
• Reactions and behaviors can be recorded.

It can be conducted in two ways:

For Individual- Intercept interviewing

For group – Focus group interviewing

Intercept interviewing: This allows researcher to reach known people in a short period of time. It involves talking to people at office, home, shopping malls, on streets etc. The time involved ranges from a few minutes to several hours.

Focus Group Interviewing: It is usually conducted by inviting a group of people together for a few hours  with a trained moderator to talk about the topic of research. It is an effective tool to understand people’s thoughts and feelings. The moderator should have objectivity, knowledge of the subject and industry, and some understanding of group and consumer behavior.

Observation Method

This method is used primarily to study behavioral sciences. Data is collected by investigator’s own direct observation of relevant people, actions and situations. The researcher observes the conditions in their natural state. Actual behavior of people is usually the observed one not the one which is judged by surveys. For example, In a survey many people can accept that they are health- conscious but this data can be believed only when they are observed doing exercise or eating healthy food. Following type of Observation methods are there:

1.   Direct or indirect

2.  Structured (for descriptive research) or  Unstructured (for exploratory research)

3. Participant or Non- participant observation

4. Disguised observation

5. Obtrusive or non-obtrusive

 

Experimental research

This method of research is also called Empirical Research or Cause and Effect Method. It is a data-based

research, which comes up with conclusions which can be verified with observation or experiment. It is appropriate when proof is sought that certain variables affect other variables in some way. Example increase in volume of traffic has increased air pollution – this can be easily proved through experimental research.

The experimenter controls the variables under study and manipulates one of them to study its effects.

In such a research, it is necessary to get at facts first hand, at their source, and actively go about doing certain things to stimulate the production of desired information.

 

-Researcher must provide self with a working hypothesis.

– Then , he/she should work to get enough facts (data) to prove or disprove the hypothesis.

-Experimental designs are set up which he thinks will manipulate the persons or the materials concerned so as to bring forth the desired information.

Usually, evidence gathered through experimental and empirical studies are considered to be the most powerful support possible for a given hypothesis.

Conclusion:

The various research methods discussed above are used for research depending on the situations. Each set of methods has its own flaws and its own advantages. The researcher must take a wise decision regarding methodology to reach to a informative and constructive conclusion.

– Submitted By: Anuradha Srivastava(13PGP065)

 

Are projective techniques reliable, valid and useful? SectionA_Group9_Shaily Agarwal_13PGP051

Often the people who are researched hide their true feelings and thoughts due to embarrassment and fear when asked direct questions. Projective techniques are mechanisms where people unconsciously attribute their own negative trait to others. The common variants of projective techniques are:

• Rorschach
• Holtzman Inkblot Test
• Thematic apperception test
• Draw-A-Person test
• Animal Metaphor Test
•  Sentence completion test
• Picture Arrangement Test
• Word Association Test
• Graphology

Projective techniques can be used in a variety of market research situations as well as in social and educational research and these do not have to be aiming at uncovering aspects of personality of any great depth. However the reliability and validity of these techniques is a matter of debate. There are many controversies regarding whether different researcher draw the same conclusion from the same set of results and whether their research actually measures truly what it claims to measure. Subjectivity of the researcher make the use of this technique unreliable because the researchers are able to obtain similar responses from those who are researched but their interpretation greatly varies due to different skills being possessed by different researchers. In a 1996 paper on projective and enabling techniques, Will et al. doubted the ability of the projective techniques to tap into the consumers’ subconscious. He said that these techniques just created grounds for open and uninhibited discussion. However most of the reports by market research practitioners praised these techniques for their ability to help researchers get valuable psychological information from the research participants which the participants otherwise would not have shared or they themselves are consciously unaware of.

Eye Tracking technique for marketing research- Is it really worth it? SectionA_Group4_Kratika Lakhani_13PGP121

The most intriguing thing which stuck my mind till the end of the class was the application of Eye Trackers!

Eye tracking has become an increasingly popular method that answers array of endless questions of the researchers in the area of market research, usability testing, advertising research, neuroscience and sports research. It uses eye tracking visualizations such as gaze plots, heat maps and area of interest analysis to evaluate how consumers experience and perceive different media and communication messages.

Particularly in the area of Market research, Physical shelf -tests allows the utmost realism. Here, the testing takes place directly at the point of the sale. Places where POS is not possible, virtual test-studios are created to perform the evaluations. This also makes it possible to test a relatively high number of different design alternatives efficiently at a low cost. Then there is a mobile eye-tracking system which allows you to divert attention to the most relevant areas in POS thus making it possible to test the shopper’s orientation at the point of sale in an optimum fashion.

Many times we happen to encounter displays, posters, danglers, shelf branding, shelf talkers etc in front of a shop. These are either tested directly or via physical mock-ups at the point of sale. Eye tracking plays a vital role here to test how often people take a view of these, at what points and for how long.

At the early stage of a project, marketers usually organize concept workshops to ensure that the right target audience has been targeted. Various advertising campaigns are analyzed be it print, television or online media and with this analysis using  eye tracker technique, it is ensured whether the right target audience is being getting addressed and what are the points on which the audience focuses on. This information majorly helps them to modify and refine the ad structure of the company. Websites of the companies as well as e-commerce sites share the similar need to identify where the information is presumed to be, which page grabs attention/distraction and which information is perceived and understood.

Social media has become lifeline for online advertising with 1.5 billion people users being on facebook alone. Surprisingly 58% of the total population on internet use social media. This makes it an important platform for not only providing opportunities for classical advertising but also a good interacting medium for a company with its target group. Eye tracking here gives us the evaluated feedback by determining the distinctiveness, attractiveness and the tendency of any post /ad to get chosen by the target user.

However there are many limitations of eye tracking technique. It is found to be misleading in some cases since it does not capture our peripheral vision which constitutes 98% of our vision field. This is an important aspect since it’s the peripheral region which helps us to decide where to fixate our fovea next. Fixation doesn’t represent attention or understanding nor it conveys any meaning. Considering the high cost, complexity and the effort that it requires, many people argue it to be a not-so-worthy process. Eye tracking is not the essential process but if you can afford it and know its effective use, it is definitely worth it!!

Big Data – A market research perspective by SectionA_Group4_Teja_13PGP045

One of the most common statement we hear from marketers is “consumers don’t know what they want”. If this statement is considered true which is in most cases, surveys and similar research methods might take a back seat on various occasions. Then the most common question which arises is what are our next alternatives ?

Big Data, the next frontier for innovation, competitive advantage and productivity, according to a research report from the McKinsey Global Institute. Big data is the term for collection of data sets so large and complex which are  difficult to process using on-hand database management tools or traditional data processing application. The sources of data sets for market research about the consumers include weblogs, social media, smartphone analytics, POS (Point of sale) and even medical records.

Shah Rukh Khan-starrer Chennai Express, one of the biggest Bollywood grossers on 2013, used Big Data & Analytics solutions by IT services firm Persistent Systems to drive social media and digital marketing campaigns. “Chennai Express related tweets generated over 1 billion cumulative impressions and the total number of tweets across all hashtags was over 750 thousand over the 90-day campaign period,” Persistent Systems claimed in a release.

GSK, which owns brands from Sensodyne to Lucozade, is already tracking consumers online and repurposing the data to benefit particular brands. The company identifies people mentioning about their brands on public domains on social media and uses this information to build the customer profile .Some online businesses, such as Amazon, are already leading the field in this area. The site uses collaborative filtering technology, which allows it to develop automatic recommendations for customers based on their purchase history data.

Also in the B2B sector, Microsoft is using customer sentiment data to gain extra insights. Microsoft UK’s insight manager for the developer and platform evangelism team, Maxine Cook, says her brand can discover via the many online IT forums how the trade is reacting to a piece of technology and its competitors.

Retail is one sector that has great potential for big data. Its customer transactions, both on- and offline, conversations and intentions can all be brought together so that brands can better understand how to reach shoppers.

With trillions of bytes of information available for companies to collect about their customers, suppliers and operations, the brands that invest in big data now are likely to see big rewards.

 

 

 

 

Section (B) _Group 8_Sushant Singh_Roll no(13PGP115)

Title: Research:Definition and business perspective

 “Research is to see what everybody else has seen, and to think what nobody else has thought.” 

Albert Szent-Gyorgyi

Introduction:

Research ,the word comprises of prefix ‘re’ and the verb search. If we look at each of these components individually ,then ‘re’ means again and ‘search’ means to examine carefully ,to test ,try and probe. Thus the basic idea of research is to try and find answers to the questions. But before finding an answer to a question ,its important to look out for a question.

There are so many questions unanswered all round us. For example, ‘why do I have black eyes and somebody else has brown’ ,’what makes popcorn pop’ and many more. We just need to be an astute observer and enquire for the answers in a systematic way. One of the classic examples of observation and enquiry is ‘laws of gravitation’. Sir Isaac Newton’s great sense of observation and aptitude of enquiry changed the course of human civilization.

Definition:

Formally research can be defined as creation of knowledge in a new and creative way as to generate new concepts. It includes analysis of previous research which might lead to something new and creative outcomes. Finding of any previous research result is not sacrosanct. They can always be improved further.

Basic vs Applied:

The difference between basic and applied research seems is that applied research has “real world” application. ‘Basic’ researchers face questions such as “How real world their efforts are going to help th?”

• Basic Research

Basic research explores the fundamental bases of behavior, irrespective of the fact that  how those bases are manifested in the real world. It tries to explain, predict, and describe fundamental bases of behavior. There is a memory procedure which asks people to respond to words on a computer screen as quickly as they can. Such researches can help to understand about how information in memory is linked to other information .But such procedures happen rarely in real life  except when we are playing some computer game.

• Applied Research

Applied research addresses real-world problems. Topics such as persuasion, eyewitness memory, clinical treatments of psychological disorders, behavioral interventions for children with autism decision making, etc. are covered in applied research.

Deductive vs Heuristic:

Research can be either deductive or heuristic. A deductive research has hypotheses which describes the status quo. Such hypotheses  are based on previous experiences or  hypotheses. The objective of such an endeavor is to accept or reject hypotheses. But in a heuristic research such kind of hypotheses is not necessary .Here the approach is ‘discovery approach’. In heuristic research, sometimes the question is too general ,then it becomes imperative to have a focused research question or hypotheses.

 

Business research

Business research is a field of practical study in which a company obtains data and analyzes it in order to better manage the company. Business research can include financial data, consumer feedback, product research and competitive analysis. Executives and managers who use business research methods are able to better understand their company, the position it holds in the market and how to improve that position.

Financial Data

Financial data takes qualitative information–such as sales reports, revenues and cost reports–to see what areas make money and what costs money. By reviewing data, managers can find the products, staff and departments that are most efficient and determine areas of unnecessary costs.

Consumer Feedback

Understanding what the public says about the products and services a company provides is essential to making sure the company is meeting consumer needs. Customer feedback includes case studies, focus groups, customer surveys and questionnaires.

Product Research

Product research seeks to improve the product to meet the needs of consumers. This may include technological advancements, improved customer service or access to the product through a variety of distribution channels.

Competitive Analysis

Competitive analysis is when one company compares its products and services to those of another company. This can be done to improve the product, create a niche or determine a more attractive price point to lure customers.

Industry Data

Using research tools such as the information compiled by Dun & Bradstreet can help a company to understand how the industry as a whole is doing. This can help executives make decisions based on economic factors affecting their industry that are not limited to their own products.

Human Resource

Recently a lot of stress has been put on understanding the organizational behavior and human resource development.Companies have been investing a lot in research to find methods to employ various theories in motivating and mobilizing their employees. Research has helped to understand the job attitude and ways to increase employee involvement.

Problem discovery:

Problem discovery is the initial but paramount step to start any research. Quality of problem discovery determines the quality of research. Its important to segregate the problem from its symptoms otherwise course of the research can take wrong direction. If a product is not selling in the market then it might be symptom of wrong targeting or incorrect pricing.  Sometimes difference between problem and subtle so we must be careful in segmentation. The essence of this issue is very well captured by iceberg principle.

Iceberg Principle: Observation that in many (if not most) cases only a very small amount (the ‘tip’) of information is available or visible about a situation or phenomenon, whereas the ‘real’ information or bulk of data is either unavailable or hidden.

http://www.businessdictionary.com

Before starting any research we need to address the following issues:-

Need for research:

• Identify the stakeholders and benefits they will receive from the research. An easy way to identify need for research is to keep on asking ‘why’ questions(i.e. why we are doing the research).But be careful and limit yourself after certain ‘why’s otherwise we  might broaden the scope of the problem.

Research Problem:

• Define the problem clearly and succinctly. A vague statement might lead the researcher in direction and a lot of effort might end up being futile. Be careful that problem definition does end up being too narrow.

Research objective:

• Break the research into smaller objectives such that sum total of efforts put in achieving these objectives leads to completion of project. There are objectives which are generic to all the researches and some are very specific to a research.

Conclusion:

Research is all about observation and enquiry. It is way forward and prevents the stagnation of human civilization. Creative capability of humans can be harnessed by the systematic approach of research. It helps in enhancement of existing and genesis of new.

 

Section A_ Group 2 _Ruchi Sao(13PGP048)

PROPORTIONATE HAZARD ANALYSIS

Proportionate hazard analysis (PHA) is a subtype of survival analysis in statistics introduced in 1972. Survival analysis is the study of observation and its subsequent event. The event can be disease, death, recovery or relapse. Earlier the scope of study was limited to event being death but now the wide scope expanded to mechanical failure of machine, crashing of stock market, onset of disease etc. In medicine survival analysis is used to study

• Leukemic patients and time in remission
• Time for developing heart disease for normal individuals
• Elderly population and time till death
• Heart transplants and time till death

Survival models can’t be done through simple multiple regression because of 2 reasons:

• Dependent variable may not be normally distributed which violates multiple regression assumptions
• Censoring issue- It occurs when we have some information about individual survival time, but we do not know the survival time exactly

PHA is one such regression model where no assumption regarding the nature of shape of distribution is made. This models assumes:

• Hazard rate (Hazard ratio corresponding to situation. For example, equipment may fail twice at the rate per unit time as well maintained equipment. Twice indicates higher probability of failure) is a function of independent variable

The model could be represented from the following equation:

Where:

•  is the resultant hazard in given values of m independent variables in given cases of x1, x2,…, xm and in respective time period.
•  is baseline hazard is that hazard of individual when all independent variables are zero.

This equation is valid under 2 conditions:

• Hazard functions is not time dependent
• Log linear relationship between independent variable and hazard function

So the modified equation for considering time function is:

Here: h(t) is the function of baseline hazard, independent variable (x) and x times the log of time. 5.4 is for scaling purpose.

Practical application of PHA:

1)      Stock market: Survival analysis is used to analyse the stock survival time using PHA. This study was conducted for shanghai stock exchange to find out the main factors that influence performance of the quoted companies. They ignored all macro factors and concentrated just on the financial data. Stock survival time is the duration when the stock price reached its highest and dropped to 40% below of that value. They considered following 6 factors:

• Net Asset Per Share (NAPS)
• Cash Flow Per Share (CFPS)
• Growth Rate Of Operating Profit (GROP),
• Earnings Per Share (EPS),
• Return On Equity (ROE)
• Percentage Of Released Non Floating Share (RNF)

Industry was divided into 14 sectors and one such sector was considered along with a dummy variable. Above 6 factors were regressed through PHA and concluded that RNF and ROE does not contribute to stock prices whereas NAPS, CFPS and GROP have positive effect on stock survival times. It was also concluded that high liquidity and growth rate earning capacity contribute to make stoke survive longer.

2)      Equipment failure: PHA is used to analyse the risk of failure of machines considering the effect of human participants. The study also develop a cost benefit analysis to help in identifying optimal course of action for revenue maximization. Considering operator related factors and working age of machine hazard rate was calculated. The baseline hazard was a function of age of equipment and the independent variable included the human related functions. Expected machine uptime and probability of failure was calculated given the learning curves of operator and their reduction in human error over time (compute through historical data). Expected machine uptime along with production forecasting at various skill levels of operator give us the expected production output. This study also helps in predicting the minimum level of skills required by operator to operate profitably.

3)      Medicine: Digoxin is used to treat heart patients and slow down the heart rate of atrial fibrillation (heart rhythm disorder) sufferers. In 2011 the medicine was said to increase mortality rate but the reason behind it was unclear i.e. whether the medicine increased the mortality rate or the medicine was prescribed to patients which were suffering from serious ill. So a study was conducted to test the dependency of mortality on digoxin medicine. Two kinds of data were collected one with patients taking medicine and other not undertaking digoxin. This data was fit into PHA model. This study was also conducted on gender basis. From the result of regression it was concluded that the medicine was associated with rise in mortality in both men and women. This study further raise the usage of medicine.

To conclude PHA is an important tool to study the impact of independent variables on dependent variables in many areas. Earlier the model was only used in medicine but now the scope widen and research is being done to expand it horizon to new areas.

Reference:

1)      http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3227332/

2)      http://www.bsu.edu/libraries/virtualpress/mathexchange/06-01/Jiayi.pdf

3)      https://tspace.library.utoronto.ca/bitstream/1807/35863/11/Kiassat_Ashkan_Corey_201306_PhD_Thesis.pdf

4)      http://eurheartj.oxfordjournals.org/content/early/2012/11/14/eurheartj.ehs348.long

What’s the difference between Intuition and Bias and some insights on Socio Economic classification by Section A_Group _4_Abhijeet Kumar_13PGP001

One of the interesting question that popped out during the class discussion was – what was the difference between intuition and bias?

Let’s first understand independently what exactly intuition and bias are.

As per free dictionary, intuition can be simply defined as ‘The act or faculty of knowing or sensing without the use of rational processes’.

And at the same time, bias is ‘A preference or an inclination, especially one that inhibits impartial judgment’.

As per Nobel-winning psychologist Daniel Kahneman — author of the indispensable Thinking, Fast and Slow, intuition is a subset of bias and explains the same as : ‘One of the most fascinating examples of heuristics and biases is what we call intuition — a complex cluster of cognitive processes, sometimes helpful but often misleading. He notes that thoughts come to mind in one of two ways: Either by “orderly computation,” which involves a series of stages of remembering rules and then applying them, or by perception, an evolutionary function that allows us to predict outcomes based on what we’re perceiving. (For instance, seeing a woman’s angry face helps us predict the general sentiment and disposition of what she’s about to say.) It is the latter mode that precipitates intuition.’

The same time there isn’t much concrete research to clearly differentiate between intuition and bias.  Thus a perfect research topic for a psychology student..!!

One among the many other interesting discussed topics included the Socio Economic classification. This is used by most media researchers and brand managers to understand the Indian consuming class.

Originally developed by IRMB International as a way of understanding market segments, and consumer behavior it was standardized and adopted by Market Research Society of India in mid-1980 as a measure of socio economic class and is now commonly used a market segmentation tool in India.

In the older version, the SEC Classification consists of two grids-

ü  The Urban SEC Grid, which uses Education levels and Occupational criteria of the Chief Wage Earner (CWE) of a household as measures to determine socio-economic classification, and segments urban India into 7 groups (A1 to E2) and

ü  The Rural SEC Grid, which uses Education and Type of House (pucca, semi-pucca, and katcha) as measures of socio-economic class, and segments rural India into 4 groups (R1,R2,R3,R4).

The older SEC classification is based on the assumption that higher education leads to higher income thus higher consuming potential. But we know that this may not be true always. A trader or a retailer with no qualification can earn more income than a Post graduate executive, but SEC will categorize the traders/retailers not as SEC A1or A2.

To address this concern the Government came up with a new classification method that is based on two variables:

ü  Education of the Chief Earner

ü  The number of Consumer durables (pre-decided from a list) owned by the family. The list has 11 items ranging from “electricity and agricultural land” to cars and air conditioners.

The detailed new SEC classification can be found at : http://www.mruc.net/new-demographic-map-of-india.pdf

Section A_Group _4_Abhijeet Kumar_13PGP001. 

 -Session 2.