Introduction to Market Research PDF

Introduction to Market Research 1 Learning Objectives After reading this chapter, you should understand: What market and marketing research are and how they differ. How practitioner and academ...

Introduction to Market Research 1 Learning Objectives After reading this chapter, you should understand: What market and marketing research are and how they differ. How practitioner and academic market(ing) research differ and where they are similar. When market research should be conducted. Who provides market research and the importance of the market research industry. Keywords Full service and limited service providers Market and marketing research Syndicated data 1.1 Introduction When Toyota developed the Prius a highly fuel-efficient car using a hybrid petrol/electric engine it took a gamble on a grand scale. Honda and General Motors’ previous attempts to develop frugal (electric) cars had not worked well. Just like Honda and General Motors, Toyota had also been working on developing a frugal car but focused on a system integrating a petrol and electric engine. These development efforts led Toyota to start a project called Global Twenty-first Century aimed at developing a car with a fuel economy that was at least 50% better than similar-sized cars. This project nearly came to a halt in 1995 when Toyota encoun- tered substantial technological problems. The company solved these problems, using nearly a thousand engineers, and launched the car, called the Prius, in Japan in 1997. Internal Toyota predictions suggested that the car was either going to be an instant hit, or that the take-up of the product would be slow, as it takes time M. Sarstedt and E. Mooi, A Concise Guide to Market Research, 1 Springer Texts in Business and Economics, DOI 10.1007/978-3-642-53965-7_1, # Springer-Verlag Berlin Heidelberg 2014 [email protected] 2 1 Introduction to Market Research to teach dealers and consumers about the technology. In 1999, Toyota made the decision to start working on launching the Prius in the US. Initial market research showed that it was going to be a difficult task. Some consumers thought it was too small for the US and some thought the positioning of the controls was poor for US drivers. There were other issues too, such as the design, which many thought was too strongly geared toward Japanese drivers. While preparing for the launch, Toyota conducted further market research, which could, however, not reveal who the potential buyers of the car would be. Initially, Toyota thought the car might be tempting for people concerned with the environment but market research dispelled this belief. Environmentalists dislike technology in general and money is a big issue for this group. A technologically complex and expensive car such as the Prius was therefore unlikely to appeal to them. Further market research did little to identify any other good market segment. Despite the lack of conclusive findings, Toyota decided to sell the car anyway and to await public reactions. Before the launch, Toyota put a market research system in place to track the initial sales and identify where customers bought the car. After the formal launch in 2000, this system quickly found that the car was being bought by celebrities to demonstrate their concern for the environment. Somewhat later, Toyota noticed substantially increased sales figures when ordinary consumers became aware of the car’s appeal to celebrities. It appeared that consumers were willing to purchase cars endorsed by celebrities. CNW Market Research, a market research company specialized in the automo- tive industry, attributed part of the Prius’s success to its unique design, which clearly demonstrated that Prius owners were driving a different car. After substan- tial increases in the petrol price, and changes to the car (based on extensive market research) to increase its appeal, Toyota reached total sales of over three million and is now the market leader in hybrid petrol/electric cars. This example shows that while market research occasionally helps, sometimes it contributes little or even fails. There are many reasons why the success of market research varies. These reasons include the budget available for research, support for market research in the organization, implementation, and the research skills of the market researchers. In this book, we will guide you through the practicalities of the basic market research process step by step. These discussions, explanations, facts, and methods will help you carry out market research successfully. 1.2 What Is Market and Marketing Research? Market research can mean several things. It can be the process by which we gain insight into how markets work, a function in an organization, or it can refer to the outcomes of research, such as a database of customer purchases or a report including recommendations. In this book, we focus on the market research process, starting by identifying and formulating the problem, continuing by determining the research design, determining the sample and method of data collection, collecting [email protected] 1.3 Market Research by Practitioners and Academics 3 the data, analyzing the data, interpreting, discussing, and presenting the findings, and ending with the follow-up. Some people consider marketing research and market research to be synony- mous, whereas others regard these as different concepts. The American Marketing Association, the largest marketing association in North America, defines marketing research as follows: The function that links the consumer, customer, and public to the marketer through information information used to identify and define marketing opportunities and problems; generate, refine, and evaluate marketing actions; monitor marketing perfor- mance; and improve understanding of marketing as a process. Marketing research specifies the information required to address these issues, designs the method for collecting infor- mation, manages and implements the data collection process, analyzes the results, and communicates the findings and their implications (American Marketing Association 2004). On the other hand, ESOMAR, the world organization for market, consumer and societal research, defines market research as: The systematic gathering and interpretation of information about individuals or organizations using the statistical and analytical methods and techniques of the applied social sciences to gain insight or support decision making. The identity of respondents will not be revealed to the user of the information without explicit consent and no sales approach will be made to them as a direct result of their having provided information (ICC/ESOMAR international code on market and social research 2007). Both definitions overlap substantially but the definition of the AMA focuses on marketing research as a function (e.g., a department in an organization), whereas the ESOMAR definition focuses on the process. In this book, we focus on the process and, thus, on market research. 1.3 Market Research by Practitioners and Academics Both practitioners and academics are involved in marketing and market research. Academic and practitioner views of market(ing) research differ in many ways, but also have many communalities. A key difference is the target group. Academics almost exclusively conduct research with the goal of publishing in esteemed journals. Highly esteemed journals include: the Journal of Marketing, Journal of Marketing Research, Journal of the Academy of Marketing Science, and the International Journal of Research in Marketing. Practitioners’ target group is the client, whose needs and standards include: relevance, practicality, generalizability, and timeliness. Journals, on the other hand, frequently emphasize methodological rigor and consistency. Academic journals are often difficult to read and understand, while practitioner reports should be easy to read. Academics and practitioners differ substantially in their use of and focus on methods. Practitioners have adapted some of the methods, such as cluster [email protected] 4 1 Introduction to Market Research analysis and factor analysis that academics have developed or refined.1 Developing methods is often a goal in itself for academics. Practitioners are more concerned about the value of applying specific methods. Standards also differ. Practitioners’ data collection methods are mostly guided by clear principles and professional conduct as advocated by ESOMAR and the AMSRS (see https://www.esomar.org/ knowledge-and-standards/codes-and-guidelines.php and http://www.amsrs.com.au/ documents/item/194, for examples). Universities or schools sometimes impose data collection and analysis standards on academics, but these tend to be general. Interestingly, many practitioners claim that their methods meet academic standards, but academics never claim that their methods are based on practitioner standards. Besides these differences, there are also many similarities. For example, good measurement is paramount for academics as well as practitioners. Furthermore, academics and practitioners should be interested in each others’ work; academics can learn much from the practical issues faced by practitioners while practitioners can gain much from understanding tools, techniques, and concepts that academics develop. The need to learn from each other was underlined by Reibstein et al. (2009) who issued an urgent call for the academic marketing community to focus on relevant business problems.2 1.4 When Should Market Research (Not) Be Conducted? Market research serves a number of useful roles in organizations. Most importantly, market research can help organizations by providing answers to questions firms may have about their customers and competitors; answers that could help such firms increase their performance. Specific questions related to this include identifying market opportunities, measuring customer satisfaction, and assessing market shares. Some of these questions arise ad hoc, perhaps due to issues that the top management, or one of the departments or divisions have perceived. Much of the research is, however, programmatic; it arises because firms systematically evaluate elements of the market. An example of this type of research is conducted by Subway, the restaurant chain, which systematically measures customer satisfaction. This type of research does not usually have a distinct beginning and end (contrary to ad hoc research) but is executed continuously over time and leads to daily, weekly, or monthly reports. The decision to conduct market research may be taken when managers face an uncertain situation and when the costs of undertaking good research are (much) lower than the expected benefits of making good decisions. Researching trivial issues or issues that cannot be changed is not helpful. Other issues to consider are the politics within the organization; if the decision to go ahead has already been made (as in the Prius example in the introduction), market research is unnecessary. If it is conducted and supports the decision, it is of 1 Roberts et al. (2014) explore the impact of marketing science tools on the practice of marketing. 2 See Lee and Greenley (2010) for a further discussion. [email protected] 1.5 Who Provides Market Research? 5 little value (and those undertaking the research may be biased towards supporting the decision), while market research is ignored if it rejects the decision. Moreover, organizations often need to make very quick decisions, for example when responding to competitive price changes, unexpected changes in regulation or the economic climate. In such situations, however, market research may only be included after decisions have already been made. Therefore, when urgent decisions have to be made, research should mostly not be undertaken. 1.5 Who Provides Market Research? Many organizations have people, departments, or other companies working for them to provide market research. In Fig. 1.1, we show who these providers of market research are. Most market research is provided internally through specialized market research departments or people tasked with this function. It appears that about 75% of organizations have at least one person tasked with carrying out market research. This percentage is similar across most industries, although it is much less in government sectors and, particularly, in health care (Churchill and Iacobucci 2009). In larger organizations, internally provided market research is usually undertaken by a sub department of the marketing department. Sometimes this sub department is not connected to a marketing department but is connected to other organizational functions, such as corporate planning or sales (Rouziès and Hulland 2014). Many large organizations even have a separate market research department. This system of having a separate market research department or merging it with other departments seems to become more widespread with the marketing function increasingly devolving into other functions within organizations (Sheth and Sisodia 2006). The external providers of market research are a powerful economic force. In 2012, external providers had a turnover of about $18.70 billion collectively (Honomichl 2013). The market research industry has also become a global field with companies such as The Nielsen Company (USA), Kantar (UK), GfK Providers of market research Internal External Full service Limited service Syndicated data Customized services Segment specialists Field service Specialized service Fig. 1.1 The providers of market research [email protected] 6 1 Introduction to Market Research (Germany), and Ipsos (France) playing major roles outside their home markets. External providers of market research are either full or limited service providers. Full service providers are large market research companies such as The Nielsen Company (http://www.nielsen.com), Kantar (http://www.kantar.com), and GfK (http://www.gfk.com). These large companies provide syndicated data as well as customized services. Syndicated data are data collected in a standard format and not specifically collected for a single client. These data, or analyses based on the data, are then sold to multiple clients. Syndicated data are mostly collected by large marketing research firms, as they have the resources to collect large amounts of data and can spread the costs of doing so over a number of clients. For example, The Nielsen Company collects syndicated data in several forms: Nielsen’s Netratings, containing information on digital media; Nielsen Ratings, which details the type of consumer who listens to the radio, watches TV, or reads print media; and Nielsen Homescan, which consists of panel information on the purchases consumers make. These large firms also offer customized services by conducting studies for a specific client. These customized services can be very specific, such as helping a client with carrying out specific analyses. The Nielsen People Meter Measuring TV audiences is critical for advertisers. Yet, measuring the number of viewers per program has become more difficult as households nowadays have multiple TVs and may have different viewing platforms. In addition, “time shift” technologies such as Video-on-demand and the TIVO have further complicated the tracking of viewer behavior. Nielsen has measured TV, and other media use for over 25 years using a device called the People Meter. This device measures usage of each TV viewing platform and instantly transmits the results back to Nielsen, allowing for instant mea- surement. These devices are installed in over 20,000 households in the US. In the following video, leaders and experts from The Nielsen Company discuss how the People Meter works. https://www.youtube.com/watch?v=jYrVijea0UM [email protected] Review Questions 7 Compared to full service providers, which undertake nearly all market research activities, limited service providers specialize in one or more services and tend to be smaller companies. In fact, many of the specialized market research companies are one-man businesses with the owner, after (or besides) a practitioner or academic career, offering his or her specialized services. Although there are many different types of limited service firms, we only discuss three of them: those focused on segmentation, field service, and specialized services. Segment specialists concentrate on specific market segments. An example of such specialists is Skytrax which focuses on market research in the airline and airport sector. Other segment specialists do not focus on a particular industry but on a type of customer. Ethnic Focus (http://www.ethnicfocus.com/), a UK-based market research firm, for example, focuses on understanding ethnic minorities. Field service firms, such as Survey Sampling International (http://www. surveysampling.com/), focus on executing surveys, for example, determining samples, sample sizes, and collecting data. Some of these firms also deal with translating surveys, providing addresses and contact details. Specialized Service firms are a catch-all term for firms that have specific technical skills, only focusing on specific products, or aspects of products such as market research on taste and smell. Specialized firms may also concentrate on a few highly specific market research techniques, or may focus on one or more highly specialized analysis techniques, such as time series analysis, panel data analysis, or quantitative text analysis. A prominent example of a specialized service firm is Envirosell (http://www.envirosell.com), a research and consultancy firm that analyzes consumer behavior in commercial environments. The choice between these full service and limited service market research firms boils down to a tradeoff between what they can provide (if it is highly specialized, you may not have much choice) and the price of doing so. In addition, if you have to combine several studies to gain further insight, full service firms may be better than multiple limited service firms. Obviously, the fit and feel with the provider are highly important too! Review Questions 1. What is market research? Try to explain what market research is in your own words. 2. Imagine you are the head of a division of Procter & Gamble. You are just about ready to launch a new shampoo but are uncertain about who might buy it. Is it useful to conduct a market research study? Should you delay the launch of the product? 3. Try to find the websites of a few market research firms. Look, for example, at the services provided by GfK and the Nielsen Company and compare the extent of [email protected] The Market Research Process 2 Learning Objectives After reading this chapter, you should understand: – How to determine a research design. – The differences between, and examples of, exploratory research, descriptive research, and causal research. – What causality is. – The market research process. Keywords Causal research Descriptive research Ethnographies Exploratory research Focus groups Hypotheses Interviews Lab and field experiments Observa- tional studies Scanner data Planning a successful market research process is complex as Best Western, a worldwide association of hotels headquartered in Phoenix, Arizona, discovered. When they tried to expand the Best Western brand, they planned a substantial research process to find answers to seven major marketing questions. Answer- ing these questions required involving several research firms, such as PriceWaterhouseCoopers. These firms then collected data to gain insights into customers, non-customers, and influencers in nine different countries. How do organizations plan for market research processes? In this chapter, we explore the market research process and various types of research. M. Sarstedt and E. Mooi, A Concise Guide to Market Research, 11 Springer Texts in Business and Economics, DOI 10.1007/978-3-642-53965-7_2, # Springer-Verlag Berlin Heidelberg 2014 [email protected] 12 2 The Market Research Process Identify and formulate the problem Determine the research design Design the sample and method of data collection Collect the data Analyze the data Interpret, discuss, and present the findings Follow-up Fig. 2.1 The market research process 2.1 Introduction Executing professional market research requires good planning. In this chapter, we introduce the planning of market research projects, starting with identifying and formulating the problem and ending with presenting the findings and the follow-up (see Fig. 2.1). This chapter is also an outline for the chapters to come. 2.2 Identify and Formulate the Problem The first step in setting up a market research process involves identifying and formulating the research problem. Identifying the research problem is valuable, but also difficult. To identify the “right” research problem, we have to first identify the marketing symptoms or marketing opportunities. The marketing symptom is a problem that an organization faces. Examples of a marketing symptom include declining market shares, increasing numbers of complaints, or new products that consumers do not adopt. In some cases, there is no real existing problem but rather a [email protected] 2.3 Determine the Research Design 13 marketing opportunity, such as potential benefits offered by new channels and products, or emerging market opportunities that need to be explored. Organizations should identify the marketing problem or marketing opportunity, if they want to undertake market research. The marketing problem or marketing opportunity explores what underlies the marketing symptom by asking questions such as: – Why is our market share declining? – Why does the number of complaints increase? – Why are our new products not successful? – How can we enter the market for 3D printers? Marketing problems can be divided into three categories: – Ambiguous problems – Somewhat defined problems, and – Clearly defined problems. Ambiguous problems occur when we know very little about the issues important to solve them. For example, the introduction of radically new technologies or products is often surrounded by ambiguity. When Amazon started selling products online, critical but little understood issues arose, such as how to deal with the (return) logistics and encouraging customers to purchase. When we face somewhat defined problems, we know the issues (and variables) that are important for solving the problem, but not how they are related. For example, when an organization wants to export products, it is relatively easy to obtain all sorts of information, for example, on market sizes, economic develop- ment, and the political and legal system. However, how these variables impact exporting success may be very uncertain. When we face clearly defined problems, both the issues and variables that are important, and their relationships are clear. However, we do not know how to make the best possible choice. Thus, we face a problem of how to optimize the situation. A clearly defined problem may arise when organizations want to change their prices. While organizations know that increasing (or decreasing) prices generally results in decreased (increased) demand, the precise relationship (i.e., how many units do we sell less when the price is increased by $1?) is unknown. 2.3 Determine the Research Design The research design is related to the identification and formulation of the problem. Research problems and research designs are highly related. If we start working on an issue that has never been researched before, we seem to enter a funnel where we initially ask exploratory questions because we as yet know little about the issues we face. These exploratory questions are best answered using an exploratory research design. Once we have a clearer picture of the research issue after exploratory research, we move further into the funnel. Typically, we want to learn more by describing the research problem in terms of [email protected] 14 2 The Market Research Process Ambiguous problems: Exploratory research design Somewhat defined problems: Descriptive research design Clearly-defined problems: Causal research design Fig. 2.2 The relationship between the marketing problem and the research design Ambiguous Somewhat Clearly defined problems defined problems problems Exploratory Descriptive Causal research research research Understand structure Describe customers or Uncover causality competitors Formulate problems Understand the precisely Understand market performance effects of size marketing mix Uses Generate hypotheses Segment markets elements Develop Measure performance measurement scales (e.g., share of wallet, brand awareness) Fig. 2.3 Uses of exploratory, descriptive, and causal research descriptive research. Once we have a reasonably complete picture of all the issues, it may be time to determine exactly how key variables are linked. Thus, we move to the narrowest part of the funnel. We do this through causal (not casual!) research (Fig. 2.2). Each research design has different uses and requires the application of different analysis techniques. For example, whereas exploratory research can help to formu- late problems exactly or structure them, causal research provides exact insights into how variables relate. In Fig. 2.3, we provide several examples of different types of research, which we will discuss in the following. [email protected] 2.3 Determine the Research Design 15 2.3.1 Exploratory Research As its name suggests, the objective of exploratory research is to explore a problem or situation. As such, exploratory research has several key uses in solving ambigu- ous problems. It can help organizations formulate their problems exactly. Through initial research, such as interviewing potential customers, opportunities and pitfalls may be identified that help to determine or refine the research problem. It is crucial to discuss this information with the client to ensure that your findings are helpful. Such initial research also helps establish priorities (what is nice to know and what is important to know?) and to eliminate impractical ideas. For example, market research helped Toyota dispel the belief that people concerned with the environment would buy the Prius, as this target group has an aversion to high technology and lacks spending power. 2.3.2 Uses of Exploratory Research Exploratory research may be used to formulate problems precisely. For example, depth interviews, focus groups, projective techniques, observational studies, and ethnographies are often used to achieve this. In the following, we briefly introduce each technique but provide more detailed descriptions in Chap. 4. Depth interviews consist of interviewer asking an interviewee a number of questions. Depth interviews are unique in that they allow for probing on a one-to-one basis, fostering interaction between the interviewer and the respondent. Focus groups usually have between 4 and 6 participants who, led by a modera- tor, discuss a particular subject. The key difference between an interview and focus group is that focus group participants can interact with one another (e.g., “What do you mean by...?”, “How does this differ from....”), thereby providing insight into group dynamics. Projective techniques present people with pictures, words, or other stimuli to which they respond. For example, a researcher could ask what people think of BMW owners (“A BMW owner is someone who....”) or could show them a picture of a BMW and ask them what they associate the picture with. Moreover, when designing new products, market researchers can use different pictures and words to create analogies to existing products and product categories, thus making the adoption of new products more attractive (Feiereisen et al. 2008). Observational studies are frequently used to refine research questions and clarify issues. Observational studies require an observer to monitor and interpret participants’ behavior. For example, someone could monitor how consumers spend their time in shops or how they walk through the aisles of a supermarket. These studies require the presence of a person, camera or other tracking devices, such as radio frequency identification (RFID) chips, to monitor behavior. Other observational studies may consist of click stream data that tracks information on the web pages people have visited. Observational studies can also be useful to under- stand how people consume and/or use products. Such studies found, for example, that 5% or more of baby food in Japan is eaten by the elderly. Clearly such insights help in a country where birth rates are dropping and manufacturers have responded [email protected] 16 2 The Market Research Process by labelling their produce as “food for ages 0–100” (Businessweek, January 26th, 2003). In their paper entitled “An Exploratory Look at Supermarket Shopping Paths,” Larson et al. (2005) analyze the paths taken by individual shoppers in a grocery store, as provided by RFID tags located on their shopping carts. The results provide new perspectives on many long-standing perceptions of shopper travel behavior within a supermarket, including ideas related to aisle traffic, special promotional displays, and perimeter shopping patterns. Ethnographies (or ethnographic studies) originate from anthropology. In ethno- graphic research a researcher interacts with consumers over a period to observe and ask questions. Such studies can consist of, for example, a researcher living with a family to observe how people buy, consume, and dispose products. For example, the market research company BBDO used ethnographies to understand consumers’ rituals. The company found that many consumer rituals are ingrained in consumers in certain countries, but not in others. For example, women in Colombia, Brazil, and Japan are more than twice as likely to apply make-up when in their cars than women in other countries. These findings can help marketers in many ways. Exploratory research can also help establish research priorities. What is impor- tant to know and what is less important? For example, a literature search may reveal that there are useful previous studies and that new market research is not necessary. Eliminating impractical ideas may also be achieved through exploratory research. Again, literature searches, just like interviews, may be useful to eliminate impractical ideas. Another helpful aspect of exploratory research is the generation of hypotheses. A hypothesis is a claim made about a population, which can be tested by using sample results. For example, one could hypothesize that at least 10% of people in France are aware of a certain product. Marketers frequently put forward such hypotheses because they help structure decision making processes. In Chap. 6, we discuss the nature of hypotheses and how they can be tested in further detail. Another use of exploratory research is to develop measurement scales. For example, what questions can we use to measure customer satisfaction? What questions work best in our context? Do potential respondents understand the [email protected] 2.3 Determine the Research Design 17 wording, or do we need to make changes? Exploratory research can help us answer such questions. For example, an exploratory literature search may contain measure- ment scales that tell us how to measure important variables such as corporate reputation and service quality. 2.3.3 Descriptive Research As its name implies, descriptive research is all about describing certain phenom- ena, characteristics or functions. It can focus on one variable (e.g., profitability) or on two or more variables at the same time (“What is the relationship between market share and profitability?” and “How does temperature relate to sales of ice cream?”). Such descriptive research often builds upon previous exploratory research. After all, to describe something, we must have a good idea of what we need to measure and how we should measure it. Key ways in which descriptive research can help us include describing customers, competitors, market segments, and measuring performance. 2.3.4 Uses of Descriptive Research Market researchers conduct descriptive research for many purposes. These include, for example, describing customers or competitors. For instance, how large is the UK market for pre-packed cookies? How large is the worldwide market for cruises priced $10,000 and more? How many new products did our competitors launch last year? Descriptive research helps us answer such questions. For example, the Nielsen Company has vast amounts of data available in the form of scanner data. Scanner data are mostly collected at the checkout of a supermarket where details about each product sold are entered into a vast data- base. By using scanner data, it is, for example, possible to describe the market for pre-packed cookies in the UK. Descriptive research is frequently used to segment markets. As companies often cannot connect with all (potential) customers individually, they divide markets into groups of (potential) customers with similar needs and wants. These are called segments. Firms can then target each of these segments by positioning themselves in a unique segment (such as Ferrari in the high-end sports car market). There are many market research companies specializing in market segmentation, such as Claritas, which developed a segmentation scheme for the US market called PRIZM (Potential Ratings Index by Zip Markets). PRIZM segments consumers along a multitude of attitudinal, behavioral, and demographic characteristics and companies can use this to better target their customers. Segments have names, such as Up-and-Comers (young professionals with a college degree and a mid-level income) and Backcountry Folk (older, often retired people with a high school degree and low income). Another important function of descriptive market research is to measure perfor- mance. Nearly all companies regularly track their sales across specific product categories to evaluate the firm, managers, or specific employees’ performance. Such descriptive work overlaps the finance or accounting departments’ [email protected] 18 2 The Market Research Process responsibilities. However, market researchers also frequently measure performance using measures that are quite specific to marketing, such as share of wallet (i.e., how much do people spend on a certain brand or company in a product category?) and brand awareness (i.e., do you know brand/company X?), or the Net Promotor Score, a customer loyalty metric for brands or firms. 2.3.5 Causal Research Market researchers undertake causal research less frequently than exploratory or descriptive research. Nevertheless, it is important to understand the delicate relationships between important marketing variables. Causal research is used to understand the effects of one variable (e.g., the wording in advertising) on another variable (e.g., understanding as a result of advertising). It provides exact insights into how variables relate and may be useful as a test run for trying out changes in the marketing mix. The key usage of causal research is to uncover causality. Causality is the relationship between an event (the cause) and a second event (the effect), when the second event is a consequence of the first. To claim causality, we need to meet the following four requirements: – Relationship between cause and effect, – Time order, – Control for other factors, and – Availability of theory. First, the cause needs to be related to the effect. For example, if we want to determine whether price increases cause sales to drop, there should be a negative relationship or correlation between price increases and sales decreases (see Chap. 5). Note that people often confuse correlation and causality. Just because there is some type of relationship between two variables does not mean that the one caused the other (see Box 2.1). Second, the cause needs to come before the effect. This is the requirement of time order. Obviously, a price increase can only have a causal effect on sales if it occured before sales decrease. Third, we need to control for other factors. If we increase the price, sales may go up because competitors increase their prices even more. Controlling for other factors is difficult, but not impossible. In experiments, we design studies so that external factors’ effect is nil, or as close to nil as possible. This is achieved by, for example, conducting experiments in labs where, environmental factors such as conditions are constant (controlled for). To control for other factors, we can also use statistical tools that account for external influences. These statistical tools include analysis of variance (see Chap. 6), regression analysis (see Chap. 7), and structural equation modeling (see end of Chap. 8). Fourth, an important criterion is that there needs to be a good explanatory theory. Without theory our effects may be due to chance and no “real” effect may be present. For example, we may observe that when we advertise, sales decrease. Without any good explanation for this (such as that people dislike the advertise- ment), we cannot claim that there is a causal relationship. [email protected] 2.3 Determine the Research Design 19 Box 2.1 Correlation does not imply causation Correlation between two variables does not automatically imply causality. For example, in Fig. 2.4 US fatal motor vehicle crashes (per 100,000 people) are plotted against the harvested area of melons (in 1,000 acres) between 1996 and 2005. Clearly, the picture shows a trend. If the harvested area of melons increases, the number of US fatal motor vehicle crashes increases. This is a correlation and the first requirement to determine causality. Where the story falls short in determining causality is explanatory theory. What possible mechanism could explain the findings? Other examples of spurious correlations not implying causality include the following: – As ice cream sales increase, the rate of drowning deaths increases sharply. Therefore, ice cream causes drowning. – As the number of pirates decreased, so did global temperatures increase. Therefore, global warming is caused by a lack of pirates. If the above facts were to be presented, most people would be highly skeptical and would not interpret these facts as describing a causal mechanism. For other mechanisms, the situation is much less clear-cut. Think of claims that are part of everyday market research, such as “The new advertisement cam- paign caused a sharp increase in sales,” “Our company’s sponsorship activities helped improve our company’s reputation,” or “Declining sales figures are caused by competitors’ aggressive price policies.” Even if there is a correlation, the other requirements to determine causality may not be met. Causal research may help us to determine if causality really exists in these situations. Fig. 2.4 Correlation and causation. The data were taken from the NHTSA Traffic Safety Facts, DOT HS 810 780, and the United States Department of Agriculture, National Agricultural Statistics Service (continued) [email protected] 20 2 The Market Research Process Box 2.1 (continued) Some of the above and additional examples can be found in Huff (1993) or on Wikipedia. Furthermore, check http://www.tylervigen.com/ for some entertaining examples of spurious correlations. http://en.wikipedia.org/wiki/Correlation_does_not_imply_causation 2.3.6 Uses of Causal Research Experiments are a key type of causal research and come in the form of either lab or field experiments. Lab experiments are performed in controlled environments (usually in a com- pany or academic lab) to gain understanding of how changes in one variable (called stimulus) cause changes in another variable. For example, substantial experimental research is conducted to gain understanding of how changing websites helps people navigate better through online stores, thereby increasing sales. Field experiments are experiments conducted in real-life settings where a stim- ulus (often in the form of a new product or changes in advertising) is provided to gain understanding of how these changes impact sales. Field experiments are not set up in controlled environments (thus eliminating some of the causality claim’s strength), but their realism makes them attractive for market research purposes. Field experiments are conducted regularly. For example, Procter & Gamble conducted a substantial number of field experiments to test the effects of different pricing strategies to help ease challenges and brand loyalty issues related to promotional pricing (see mobile tag and URL in Box 2.2 for more information). We discuss experimental set-ups in more detail in Chap. 4. Test markets are a particular form of field experiments in which organizations in a geographically defined area introduce new products and services, or change the marketing mix to gauge consumer reactions. For example, Acxiom and GFK’s Behaviorscan provide test market services. Picking a controlled and geographically [email protected] 2.6 Analyze the Data 21 Box 2.2 Procter & Gamble’s value pricing strategy http://www.zibs.com/neslin.shtml defined test market is difficult. Test markets help marketers learn about consumer response, thus reducing the risks associated with a nationwide rollout of new products/services or changes in the marketing mix. In Chap. 4, we discuss test markets in more depth. 2.4 Design the Sample and Method of Data Collection After having determined the research design, we need to design a sampling plan and choose a data-collecting method. This involves deciding whether to use existing (secondary) data or to conduct primary research. We discuss this in further detail in Chap. 3. 2.5 Collect the Data Collecting data is a practical but sometimes difficult part of the market research process. How do we design a survey? How do we measure attitudes toward a product, brand, or company if we cannot observe these attitudes directly? How do we get CEOs to respond? Dealing with such issues requires careful planning and knowledge of the marketing process. We discuss related key issues in Chap. 4. 2.6 Analyze the Data Analyzing data requires technical skills. We discuss how to enter, clean, and describe data in Chap. 5. After this, we introduce key techniques, such as hypothe- sis testing and analysis of variance (ANOVA), regression analysis, factor analysis, [email protected] 22 2 The Market Research Process and cluster analysis in Chaps. 6–9. In each of these chapters, we discuss the key theoretical choices and issues market researchers face when using these techniques. We also illustrate how researchers can deal practically with these theoretical choices and issues, using the market-leading software package IBM SPSS Statistics. 2.7 Interpret, Discuss, and Present the Findings When executing the market research process, one’s immediate goals are interpreting, discussing, and presenting the findings. Consequently, researchers should provide detailed answers and actionable suggestions based on data and analysis techniques. The last step is to clearly communicate the findings and recommendations to help decision making and implementation. This is further discussed in Chap. 10. 2.8 Follow-Up Market researchers often stop when the results have been interpreted, discussed, and presented. However, following up on the research findings is important too. Implementing market research findings sometimes requires further research because suggestions or recommendations may not be feasible or practical and market conditions may have changed. From a market research firm’s perspective, follow-up research on previously conducted research can be a good way of entering new deals to conduct further research. Some market research never ends. For example, many firms track customer satisfaction over time. Even such research can have follow-ups, for example management may wish to know about drops in customer satisfaction. Review Questions 1. What is market research? Try to explain what market research is in your own words. 2. Why do we follow a structured process when conducting market research? Are there any shortcuts you can take? Compare, for example, Qualtrix’s market research process (http://www.qualtrics.com/blog/marketing-research-process/) with the process discussed above. What are the similarities and differences? 3. Describe what exploratory, descriptive, and causal research are and how these are related to one another. Provide an example of each type of research. 4. What are the four requirements for claiming causality? Do we meet these requirements in the following situations? [email protected]