Cluster Analysis in Marketing Research

Cluster Analysis in Marketing Research Q5. Describe cluster analysis with 2 examples related to marketing research? Ans: Cluster Analysis: It is the task of grouping a set of objects in such a way that objects in the same group are more similar to each other than to those in other groups. Example 1: Type of customers choose the restaurant Family, Entertainers, Singles etc Example 2: Type of customers that choose the restaurant based on their food choice. Vegetarian/Non vegetarian Mexican, Indian, South Indian, Fast food etc What are three characteristics of a good quality clustering analysis? Ans: The reason for asking question â€Å"Q: Type of customers that choose the restaurant based on their food choice. (Vegetarian/Non vegetarian)† Collection process of data objects. It helps me to understand the of customer’s food choice. Analysis of similarities between data objects Based on the data we can analyze which type of customers on their food choice â€Å"veg/non veg†. Veg is one group and non-veg is another. Can come up with good implementation of analysis (e.g. problem solving) Answer to the Survey can help us to understand the market demand and we can provide the similar food at the restaurant based on data gathered. Example: Q6. Describe Qualitative and quantitative research methods with one advantage and disadvantage of each. Ans: Qualitative research: The information gathered is non-numerical and might include responses to an open ended survey question, dialogue from a focus group, the answer to an essay question, a term paper, or ideas brainstormed by a group. Qualitative data is not limited to words, however, and could include the contents of an art or design portfolio. Qualitative research uses observation as the data collection method. Observation is the selection and recording of behaviors of people in their environment. Observation is useful for generating in-depth descriptions of organizations or events, for obtaining information that is otherwise inaccessible, and for conducting research when other methods are inadequate. Example: Why you like our restaurant, describe? Advantage of Qualitative research: Respondents are free to answer any way they would like comment/answer. One advantage of the qualitative approach is that contextual information is gathered when the data is collected. In other words, â€Å"why† is automatically answered/provided in the data. Qualitative research is useful on early stage when we are not sure about what to study. Disadvantage of Qualitative research: It is expensive and time consuming. It can take a long time to collect and analyze the data. For Interviews it would take 10+ hours to have hour long interviews with around 10 people and that does not include the time needed to schedule the interviews. Time taken for 1 interview = time taken for interview + time taken to schedule interview + time to analyze data (recordings and notes etc). Quantitative research All of the data collected would be counted or quantified. Example: Someone’s age, income, height or weight would be quantitative data Number of hits on a website The number of correct responses on a driving test The number of minutes per week Car fuel efficiency in KM. Advantage of Quantitative research: It is less expensive and an efficient method for gathering information especially for large groups of people. Online surveys are easy way to collect data from large groups of people. In restaurant we have large database of users through data collection. It is easy and cost effective to send and collect feedback through online surveys. The USA government collects Census information every 10 years. The government doesn’t try to interview everyone in the USA instead they mail out surveys to be completed a very efficient form of data collection. Disadvantage of Quantitative research It generally does not include an explanation of ‘why.’ For example, respondents are asked to â€Å"Rate the quality of staff services at the restaurant† using the following scale: â€Å"Excellent† , â€Å"Good† ,†Fine†, â€Å"Fair† ,or â€Å"Poor.† That question would generate quantitative data because we could count the number of people who selected each of the four response options. But knowing how many people found a quality of staff as â€Å"Excellent† does not provide any insights into why it is excellent. Also respondents are limited to set of options to respond and they may not feel that any of the options best describes their experience. Q7: Qualitative research. a) Depth Interview: Interviewing is a method ofqualitative researchin which the researcher asks open-ended questions orally and records the respondent’s answers. Example: Face to face / telephonic Job Interviews can be depth interviews. Interviewer starts with greeting by asking familiar set of general questions to create comfort level for interviewee/respondent. Q: How are you? Q: Where are you from? Q: Can you please describe yourself? Advantage: Accurate results. Better rapport. More productive asCompared with non-response among focus group members Flexible and continuous Disadvantage: It is costly and time consuming. Less structured. b) Focus Groups: Itis a form ofqualitative researchin which a group of people are asked about their perceptions, opinions, beliefs, and attitudes towards a product, service, concept, advertisement, idea, or packaging. One focus group watches another focus group and discusses the observed interactions and conclusion. Example: It is useful in marketing as important tool to acquiringfeedback regarding product/services. In social science it helps Interviewers to study people in a more natural conversation pattern than typically occurs in a one-to-one interview. Advantage: The face to face involvement of a moderator can ensure things on track. As everybody is under observation, so it is easy to make everybody fully engage even during free time. Disadvantage: Can be Biased [discussion can be dominated by a few people.] Group discussions can be difficult to steer and control. c) Projective Techniques: Originally developed to use in psychology. The use of vague, ambiguous, unstructured stimulus objects or situations in which the subject â€Å"projects† his or her personality, attitude, opinions and self-concept to give the situation some structure. Example: A personality test. Photo language Test. (using pictures). Advantage: Personality test is cost effective. (Only use paper and can be scored by hand or using a machine, can be taken home and returned later) Personality test is Objectivity (questions are mostly true/false) . Disadvantages: à ¯Ã¢â‚¬Å¡Ã‚ · Sheer length. Untruth (e.g: With personality test objective, there is always possibility that test taker never tell the truth.) d) Random probability sampling: Example: Advantage: Disadvantage: Q8: Quantitative research. a) Face to Face interview: In person interaction between two or more persons. Face to face interviews are characterised by synchronous communication in time and place. Example: Surveys of product and services. Job Interviews are mostly face to face. Interviewer starts with greeting and then asks familiar set of general questions to create comfort level for interviewee/respondent. [Sample set of questions for survey] Q: hi Mam/Sir, How are you? [Greeting question] Q: Where are you from? [Greeting question] Q: How do you like our restaurant food? [Aimed Question] Advantage: High responsive, there is no significant time delay between question and answerà ¯Ã‚ ¼Ã…’the interviewer and interviewee can directly react on what the other says or does. The answer of the interviewee/respondent is more spontaneous. Interviewer can formulate questions depending upon response from interviewee. Recorded, can be used later if required. Disadvantage: Time Consuming. Expensive. Difficult to locate respondent. b) Telephone interview: Telephonic interviews are characterised by asynchronous communication for place. Example: Surveys Job Interviews. Telephone interviewsare often conducted by employers in the initial interview round of thehiring process. Starts with greeting then main set of questions related to product/service etc. [Sample set of questions for survey] Q: Am I speaking to Ajit? Q: Is it right time to talk? Q: I have few questions about Chawala’s Indian restaurant? Q: How do you like our restaurant staff? Advantage: It is a cost-effective. Saves time. Extendedaccess to participants The telephone interview allows both interviewee/respondent and interviewer to be in a morerelaxed state as compared with face to face. Wide geographical access. It enables researchers to contact populations that might be difficult to work with on an face to face basis for example mothers at home with small children, shift workers, computer addicts and people with disabilities. Disadvantage: Difficult to locate person. Difficult to see the reaction of the interviewee/respondent. No view on the situation in which the interviewee is situated. Disconnection due to technology issues. c) Computer Assisted Personal Interviewing: It is an interviewing technique in which the respondent or interviewer uses a computer to answer the questions. Example: Job interviews. Psychometric tests. [Sample set of questions for survey] Q: What is your age? Q: Male or female? Q: Rate of restaurant staff services? [Rate from 1[lower] to 5[higher]] Advantage: Cost effective and time saving. Respondents are able to fill in the questionnaires themselves Attractinga worldwide audience. Disadvantage: Surveysare only for computer savvy people. (Potential bias to the survey) Quality is missing (a question that should be interpreted in a particular way, but could also be interpreted differently) People don’t know or dislike typing. [Leave subjective questions unanswered] d) Web based Questionnaire: AWeb-based surveyis the collection of data through a self administered electronic set of questions on the Web Example: Many companies use survey monkey to get feedback for their product. Survey monkey is one of the sites which help in creating web based questionnaire. (https://www.surveymonkey.com/) [Sample set of questions for survey] Q: How old are you? Q: Are you male or female? Q: Do you like our restaurant? Advantage: It is cost effective and time saving. Large set of responses can be handled easily. Easy to create/manage (sites are self explanatory, eg: survery monkey). Disadvantage: Resources may not be available to everybody (computer, mobile, internet etc) Not everybody is aware of technology. People don’t know or dislike typing. [Leave subjective questions unanswered] Formulation of questions required lot of time, expertise and knowledge. Q1: How would you apply measurement method to this situation? A variable measured on a nominal scale is a variable that does not really have any evaluative distinction. Example: Would you like to recommend the restaurant to your friends? Yes/No The answer to the question has no evaluative distinction. How would you apply scaling methods to this situation? By using ordinal measurement scaling method to scale the situation. Ordinal: The ordinal scale has the property of both identity and magnitude Example: How would you rate the quality/taste of our food and drinks? (Rate from 1 – 5) 1 (Really Bad) 2 (Poor) 3 (Average) 4 (Good) 5 (Excellent) By asking this question I would be able to know the quality of the food provided at the restaurant. Q3: Primary Scales of measurement that that are used in Statistical analysis Nominal Ordinal Interval Ratio scales Nominal: The nominal scale of measurement only satisfies the identity property of measurement Example: What is your country of citizenship? The Country that someone was born in has no inherent order so it can only be a nominal scale. Ordinal: The ordinal scale has the property of both identity and magnitude. Example: Identify the scale of measurement for the following: Information Technology Company Organisation Titles – (1) CEO, (2) Manager, (3) Project Lead and (4) Team Lead. The scale is ordinal. There is an inherent ordering in that a CEO is higher than a Manager, which is higher than a Project Lead, which is higher than Team Lead. CEO > Manager > Project Lead > Team Lead Designation has Rank orders. Interval: The interval scale of measurement has the properties of identity, magnitude, and equal intervals. Example: Question: Time of the day. The difference between 4 and 5is equal to the difference between 18 and 19. Ratio Scales: The ratio scale of measurement satisfies all four of the properties of measurement: identity, magnitude, equal intervals, and a minimum value of zero. Example: What is Income earned last year? It has equal intervals weekly, biweekly and monthly etc. Salary can be zero. (For unemployed) Q4:Difference between comparative scaling and not comparative scaling techniques in the marketing research. Comparative Scaling: The items are directly compared with each other. Paired comparison: It is sometimes the case that marketing researchers wish to find out which are the most important factors in determining the demand for a product Example: Which restaurant/Food do you prefer? Dominos or Pizza hut Italian pizza or Cheese Pizza By asking this question first I would be able to analyze the choice of user. First the type of restaurant than the type of pizza. By asking this able to analyze the demand of product. Dollar Metric Comparisons This type of scale is an extension of the paired comparison method in that it requires respondents to indicate both their preference and how much they are willing to pay for their preference The Unity-sum-gain technique A common problem with launching new products is one of reaching a decision as to what options, and how many options one offers Example: Rate the mobile products (from 1 to 5): (1 is lower and 5 is higher) Apple Samsung Nokia LG Motorola By this I would be able to know which company is most preferred by the user and at what lever and help us is launching new product. Non Comparative scaling techniques: Each item is scaled independently of the others. Continuous rating scales: The respondents are asked to give a rating by placing a mark at the appropriate position on a continuous line. How would be rate our staff services? 1 (Really Bad) 2 (Poor) 3 (Average) 4 (Good) 5 (Excellent) By asking this question I would be able to understand get the rating on quality from 1 to 5. 1 is lower and 5 is higher. Line marking scale Itemised rating scales : With an itemised scale, respondents are provided with a scale having numbers and/or brief descriptions associated with each category and are asked to select one of the limited number of categories, ordered in terms of scale position, that best describes the product, brand, company or product attribute being studied. Example: How would you rate the price of food items in the menu ? Very Expensive Expensive Very good Good Cheap By asking this question to customer of the restaurant I would be able to analyze the rate of food listed in the menu.