Archive for June, 2010

No Money to Conduct Primary Research? You May Have Done a Lot of it Already!

June 8, 2010

Last week, I wrote about an entrepreneur who was conducting secondary marketing research so he could develop his business plan. This week, I am writing to talk about primary research – data your company generates on its own. Often, we think of surveys and focus groups when we hear “primary research.” And those methods can indeed be costly. However, your business is probably generating volumes of primary data right under your nose. You’re out to hear the voice of your customers and prospects when you do primary research, and primary data is coming to you at nearly every touch point you have with them. Think of these sources:

Customer Service Calls

When customers call for customer service, or prospects call for information, what are the most common things they ask about? If your business sells handbags, which ones are frequently inquired about? Are the handbags most inquired about those that are higher or lower priced? Are they new handbags you’ve introduced? Are they mostly imported handbags? Also, who is making the inquiries? Are they long-term customers? Prospects? If long-term customers are inquiring about one line of handbags and prospects about another, you can tailor your marketing messages to their interests.

Customer Complaints

Nobody likes to be on the receiving end of a complaint. But complaints can be a great source of information. They can alert you to product defects, service breakdowns, and even give you ideas for enhancing your product or service. They can even help you save a long-term relationship and avoid bad word-of-mouth press. If women are complaining that the strap on one of the handbags you sell is uncomfortable to hang over their shoulders, that can prompt you to look for alternatives, or contact the supplier with that information. If a customer complains about the treatment an employee gave him/her, you might use that as an opportunity to either train your staff on improved customer service or discipline that employee.

It’s often said that 96% of a business’ dissatisfied customers will not complain; 91% will quietly go away; and those silent dissatisfied customers will likely communicate their dissatisfaction to at least nine other people. Encourage your customers to speak up when they’re not happy. Complaints can be a rich source of research.

Your Salespeople

Your salespeople are out in the field. They see everything at the frontlines. What successes are they having? What gripes do they have? Let’s say that a salesperson occasionally sells handbags to men, who are buying it for their wives, girlfriends, or mothers. You might have them inquire about the occasion. Perhaps it’s a birthday. When you know  the buyer’s spouse or significant other’s birthday, you might send a personal message to the gentleman around the same time next year, encouraging him to buy a new handbag. Salespeople can also tell you that they’re losing business to competitors because the sales cycle is too long, or too complicated, or there’s too much administrative work. They might also tell you that they’ve lost sales because your business doesn’t accept credit cards. All of these insights can be very helpful. You should encourage your salespeople to engage the customers and prospects, and also encourage them – without judgment – to share their successes, failures, and challenges with you.

Your Competition

Your competitors can be a great resource for your marketing research. Check out their Websites from time to time; follow them on Twitter; “Like” them on Facebook; read their blogs; subscribe to their newsletter; buy their products from time to time; drop in on them if they are a retailer, restaurant, etc. These techniques can alert you to their promotion schedule, the types of customers they are pursuing; the products and/or services they are emphasizing most heavily, what markets they’re in, and so forth. You might also be able to pick up the phone and talk to your competitors directly. It may be that they serve a different niche and that there’s plenty of business to go around. Plus, the fact that you are in the same business gives you an affinity that encourages both your competitors and you to help each other out.

Warranty Cards

Encouraging your customers to fill out a warranty card can also provide useful information: contact information, birthdate, age, type of product purchased, and other kinds of information. This will give you an idea of the type of customer that buys your product. Also, if customers invoke the warranty at some point, you can also get some idea for the products that are having the issue, the types of customers it has been happening with, and the most frequently occurring defects.

Previous Promotions

Look back at some of the ads you ran. How did they perform? Did you test two types of ads? Which one did better? Knowing which promotional tactics work well and which don’t can ensure that you’re directing your marketing dollars more effectively.

This list is far from comprehensive. You can also obtain primary research from trade and professional associations in your industry, as well as from chambers of commerce. You can also get information from your suppliers/vendors. And just plain old networking can give you information.

Primary research is generally expensive, but there’s so much of it that you’re likely already doing, that you may have a wealth of research right within your walls. Mining that information is like mining gold!

Do you have a lot of information you’re collecting that you’re not using to generate new or repeat business? Are you collecting mountains of information but can’t make any sense of it? Would this kind of primary research be of valuable to you, but you just don’t know where to start? Analysights can get you on the right track. Call us at (847) 895-2565 or visit our website at www.analysights.com.

Advertisements

Forecast Friday Topic: Simple Regression Analysis (Continued)

June 3, 2010

(Seventh in a series)

Last week I introduced the concept of simple linear regression and how it could be used in forecasting. I introduced the fictional businesswoman, Sue Stone, who runs her own CPA firm. Using the last 12 months of her firm’s sales, I walked you through the regression modeling process: determining the independent and dependent variables, estimating the parameter estimates, α and β, deriving the regression equation, calculating the residuals for each observation, and using those residuals to estimate the coefficient of determination – R2 – which indicates how much of the change in the dependent variable is explained by changes in the independent variable. Then I deliberately skipped a couple of steps to get straight to using the regression equation for forecasting. Today, I am going to fill in that gap, and then talk about a couple of other things so that we can move on to next week’s topic on multiple regression.

Revisiting Sue Stone

Last week, we helped Sue Stone develop a model using simple regression analysis, so that she could forecast sales. She had 12 months of sales data, which was her dependent variable, or Y, and each month (numbered from 1 to 12), was her independent variable, or X. Sue’s regression equation was as follows:

Where i is the period number corresponding to the month. So, in June 2009, i would be equal to 6; in January 2010, i would be equal to 13. Of course, since X is the month number, X=i in this example. Recall that Sue’s equation states that each passing month is associated with an average sales increase of $479.02, suggesting her sales are on an upward trend. Also note that Sue’s R2=.917, which says 91.7% of the change in Sue’s monthly sales is explained by changes in the passing months.

Are these claims valid? We need to do some further work here.

Are the Parameter Estimates Statistically Significant?

Measuring an entire population is often impossible. Quite often, we must measure a sample of the population and generalize our findings to the population. When we take an average or standard deviation of a data set that is a subset of the population, our values are estimates of the actual parameters for the population’s true average and standard deviation. These are subject to sampling error. Likewise, when we perform regression analysis on a sample of the population, our coefficients (a and b) are also subject to sampling error. Whenever we estimate population parameters (the population’s true α and β), we are frequently concerned that they might actually have values of zero. Even though we have derived values a=$9636.36 and b=$479.02, we want to perform a statistical significance test to make sure their distance from zero is meaningful and not due to sampling error.

Recall from the May 25 blog post, Using Statistics to Evaluate a Promotion, that in order to do significance testing, we must set up a hypothesis test. In this case, our null hypothesis is that the true population coefficient for month – β – is equal to zero. Our alternative hypothesis is that β is not equal to zero:

H0: β = 0

HA: β≠ 0

Our first step here is to compute the standard error of the estimate, that is, how spread out each value of the dependent variable (sales) is from the average value of sales. Since we are sampling from a population, we are looking for the estimator for the standard error of the estimate. That equation is:

Where ESS is the error sum of squares – or $2,937,062.94 – from Sue’s equation; n is the sample size, or 12; k is the number of independent variables in the model, in this case, just 1. When we plug those numbers into the above equation, we’re dividing the ESS by 10 and then taking the square root, so Sue’s estimator is:

sε = $541.95

Now that we know the estimator for the standard error of the estimate, we need to use that to find the estimator for the standard deviation of the regression slope (b). That equation is given by:

Remember from last week’s blog post that the sum of all the (x-xbar) squared values was 143. Since we have the estimator for the standard error of the estimate, we divide $541.95 by the square root of 143 to get an Sb = 45.32. Next we need to compute the t-statistic. If Sue’s t-statistic is greater than her critical t-value, then she’ll know the parameter estimate of $479.02 is significant. In Sue’s regression, she has 12 observations, and thus 10 degrees of freedom: (n-k-1) = (12-1-1) = 10. Assuming a 95% confidence interval, her critical t is 2.228. Since parameter estimates can be positive or negative, if her t value is less than -2.228 or greater than 2.228, Sue can reject her null hypothesis and conclude that her parameter estimates is meaningfully different from zero.

To compute the t-statistic, all Sue needs to do is divide her b1 coefficient ($479.02) by her sb ($45.32). She ends up with a t-statistic of 10.57, which is significant.

Next Sue must do the same for her intercept value, a. To do this, Sue, must compute the estimator of the standard deviation of the intercept (a). The equation for this estimate is:

All she needs to do is plug in her numbers from earlier: her sε = $541.95; n=12; she just takes her average x-bar of 6.5 and squares it, bringing it to 42.25; and the denominator is the same 143. Working that all in, Sue gets a standard error of 333.545. She divides her intercept value of $9636.36 by 333.545 and gets a t-statistic of 28.891, which exceeds the 2.228 critical t, so her intercept is also significant.

Prediction Intervals in Forecasting

Whew! Aren’t you glad those t-statistics calculations are over? If you run regressions in Excel, these values will be calculated for you automatically, but it’s very important that you understand how they were derived and the theory behind them. Now, we move back to forecasting. In last week’s post, we predicted just a single point with the regression equation. For January 2010, we substituted the number 13 for X, and got a point forecast for sales in that month: $15,863.64. But Sue needs a range, because she knows forecasts are not precise. Sue wants to develop a prediction interval. A prediction interval is simply the point forecast plus or minus the critical t value (2.228) for a desired level of confidence (95%, in this example) times the estimator of the standard error of the estimate ($541.95). So, Sue’s prediction interval is:

$15,863.64 ± 2.228($541.95)

= $15,863.64 ± $1,207.46

$14,656.18_____$17,071.10

So, since Sue had chosen a 95% level of confidence, she can be 95% confident that January 2010 sales will fall somewhere between $14,656.18 and $17,071.10

Recap and Plan for Next Week’s Post

Today, you learned how to test the parameter estimates for significance to determine the validity of your regression model. You also learned how to compute the estimates of the standard error of the estimates, as well as the estimators of the standard deviations of the slope and intercept. You then learned how to derive the t-statistics you need to determine whether those parameter estimates were indeed significant. And finally, you learned how to derive a prediction interval. Next week, we begin our discussion of multiple regression. We will begin by talking about the assumptions behind a regression model; then we will talk about adding a second independent variable into the model. From there, we will test the model for validity, assess the model against those assumptions, and generate projections.

Doing Market Research for Your Business Plan Need not be Expensive

June 2, 2010

Every business needs to do market research. Whether your company is a Fortune 500 corporation or the neighborhood bar, understanding the market or markets in which you operate is critical to your company’s success. Would you invest money in an oil company that didn’t research the fields where it wanted to drill? Would you buy a house in a neighborhood without checking out the schools, crime rate, or housing market? Would you open a restaurant if you knew nothing about the location, the traffic around it, or the prospective customers? You can be sure that if you wanted to open a business, no banker will loan you money without you having done proper, thorough market research.

When one hears the phrase “market research,” most often he/she thinks about surveys and focus groups. These are the most common, yet often most expensive types of market research. Surveys and focus groups are primary research methods, since they are conducted from scratch. Most market research that small businesses need is secondary, that is, research that has already been conducted, published, and available to the public. Often, secondary research can be found in libraries, online, or through other published sources. Secondary research is also much less expensive – sometimes even free – to obtain; however, sifting through it for information relevant to your business’ needs and analyzing it properly can be very time-consuming. In this post, we will discuss how someone starting a business can do market research without breaking the budget.

First Step: Decide on the Information You Need

Tom Johnson has decided to fulfill his dream of starting a comedy club. He’s purchased a book on writing a business plan, and finds that one section of a typical business plan is “Market Analysis.” Tom realizes he must get this section down pat in order to determine the viability of his business and make projections of his first few years of revenues, and convince a banker to lend him money. Tom needs to ask himself several questions: What type of customers am I catering to? What locations are most convenient for attracting those customers? What are the traffic patterns in those locations? What other comedy clubs and entertainment venues are in the area? What do they charge? How do they promote their businesses? What types of promotions do my target customers respond to? Tom writes down all the questions he can think of that will help him analyze his market.

Census Bureau

The first place Tom turns to is the U.S. Bureau of the Census. The bureau’s Web site, www.census.gov, provides a wealth of info for him. He looks at the Web site for demographics, and plugs in the ZIP codes for the locations he is considering, along with their adjacent ZIP codes. The Web site provides great insights into the number of households in the ZIP code, the age ranges, income levels, racial composition, and other demographic factors. Also from the bureau’s Web site, Tom obtains the latest “Consumer Expenditure Survey,” and finds out what the average family spends on entertainment each year.

Tom then notices that the bureau also does an Economic Census of businesses every five years. He finds the Web page for County Business Patterns and looks to see how many entertainment establishments are within the ZIP codes he is considering. He gets good insights about the number of establishments, their employee size, revenues, and payrolls. Tom also finds other interesting facts from the Economic Census – particularly what percentage of revenues entertainment establishments typically spend on various categories: advertising, salaries, maintenance, etc.

Local Library

Tom realizes the Census Bureau has provided him with data that is summarized and aggregated. He needs more information about specific competitors and business patterns in the areas he is considering. So he visits his local library, which has access to several different databases of small businesses, like Dun & Bradstreet’s Hoover’s, and Million Dollar Database. These databases provide information on several individual establishments, including revenues, owner/officer information, employees, and location. Tom does a search of all entertainment establishments in his locations of interest.

Tom also searches through local newspapers of the past few weeks to see which entertainment venues were advertising, how often they were advertising, what they were offering in their ads, etc. He then goes to the Yellow Pages to see if those prospective competitors advertise there as well.

Chambers of Commerce

Tom then contacts different chambers of commerce around his locations of interest. He finds out when their functions are and attends some of them. The local chambers of commerce are great sources for identifying the similar businesses in his area, meeting their owners directly, and finding other businesses that can be help to Tom in opening his business. For example, Tom could meet the general manager of a local movie theater, and might learn from him that the area seems to be pressed for customers, or is impacted by some local ordinance; Tom might also meet a banker or an attorney who specializes in helping new businesses start. Still, he might meet people from a local corporation who are seeking to do events for employees, of which a comedy club can be a great option. Tom might also find information on the cost of labor in the area, as well as commercial real estate rents in various areas. Chambers of commerce are ideal for networking, news, assistance, prospective customers, and other information.

Getting Out There

Tom has now done a lot of secondary research, an exhaustive amount if you ask me! But there is also some primary research he can – and must – do. Tom should drive the areas near the proposed locations for his comedy club. He should check out the other entertainment places nearby: restaurants, jazz/dance clubs, movie theaters, other comedy clubs, karaoke bars, etc. That is, he should mystery shop. Tom should go into some of these competitors and get a feel for the type of clientele to which they cater, the prices they charge, the quality of service they deliver, and how busy they are. He can also see the décor of these venues, their peak times, the outdoor signage, and the traffic around them. All of these can yield valuable clues about the venue’s degree of competitive threat to Tom’s comedy club, and the viability of the location.

Putting it all Together

While there are countless many more sources Tom can turn to for market research, we see he’s done quite an impressive amount already. While most of his sources were free, or of minimal cost, Tom’s real expense was the time and legwork he put into it; he must now synthesize all this information and analyze it to see which locations provide the best mix of traffic, revenue potential, rental costs, and demographics, and then use that information to create forecasts. Once he’s done that, Tom can write the Market Analysis section.

PlanPro Makes the Market Analysis Section of Your Business Plan a Snap!

Chances are you don’t have the time Tom did to do all of that research. Finding all that secondary information and making heads or tails of it is probably something you’d rather delegate to a professional. With PlanPro, Analysights conducts all the secondary research you need for your business, and provides you with templates for the primary research you need to do. Once all the research is compiled, we will analyze it and provide you with the findings, so that you could write the Market Analysis section of your business plan with ease. All for a flat $495! For an extra $125, we will also write the Market Analysis section for you. This way, you can spend more time on the elements of your business plan that make the best use of your time. To learn more about PlanPro, visit: http://analysights.com/PlanPro.aspx or call Analysights at (847) 895-2565.

“Fat Tax” Experiment Results Must be Interpreted with Caution

June 1, 2010

The June 2010 issue of Men’s Health magazine displayed a brief on its “Nutrition Bulletin” page about an experiment researchers from the University of Buffalo did to test the effectiveness of a “fat tax” in combating obesity. According to the brief, researchers sent shoppers to a fake supermarket where unhealthy foods were assessed a 10% “fat tax”. The brief said the study found that shoppers were led to buy healthier items and that they carried away 6.5% fewer calories in their carts. The brief also claimed “other studies have reported similar effects in real-life situations.”

The brief reiterated something I already knew: the caution one must exercise when interpreting findings from an experiment. We must remember that experiments require subjects to be studied in a controlled environment. The more environmental factors we control for, the less realistic our findings. When designing an experiment, several details must be taken into account which, if ignored or done improperly, can greatly impact the results. There are a lot of questions we should ask about this “fat tax” test:

“Who funded the study?” This is perhaps the most important question. Whenever we hear a statistic, we must question the source. The study may have been funded by and carried out for a group, organization, or person with a vested financial or political interest in the outcome.

How were the research subjects selected?” The selection of participants – research subjects – is very important. How diverse is the subject pool? Where were they found? How many people were studied? Was their participation voluntary (as it should be in all experiments), and, if so, was there a way to measure if those who chose to participate are different in some way from those who chose not to? People who choose to participate in a survey or experiment can be fundamentally different from those who decline to participate. Participants who have a vested interest in the topic being measured can either consciously or unconsciously alter their behavior in a way that affects the experiment’s outcome. If participants are not selected randomly, the results of an experiment cannot be generalized to the population at-large. Furthermore, consumer behavior can be affected especially by cultural, ethnic, religious, socioeconomic, psychological, and sociological factors.

“What criteria were used to classify a food as ‘healthy’?” and “Who decided what was healthy or unhealthy?” are also very important considerations. Classifying food as “healthy” and “unhealthy” is subjective. Was the classification based on nutritional info, such as sugar, fat, sodium, and/or calorie content? Were all candy, cookies, sodas, pastries, cakes, potato chips, etc. classified as “unhealthy?” Were smaller-portion sizes given an exemption, but larger sizes imposed the tax? What about foods we generally think of as healthy, but can be heavily sweetened?

Take yogurt for example: plain yogurt is generally very healthy. A “cherry cheesecake” flavored yogurt is sweetened artificially. Cereal is another example: Cheerios is an unsweetened brand, but Lucky Charms is packed with sugar. In classifying yogurts and cereals, were all items in those categories classified as “healthy” or “unhealthy?” Or were some items within the same category assigned different classifications based on other criteria? Don’t laugh: here in Illinois – Land of the Jailed Governors – the state sales tax on candy is lower if the candy contains flour. Hence, a Milky Way bar is taxed at 2% while a Hershey bar is taxed at 9%! And chewing gum, which has fewer calories than candy is also taxed at 9%! Finally, the one who makes the decision about which foods are healthy or unhealthy is just as important as the person who funded the study, for the very same reason.

Other questions to ask include: “How long was the study conducted?” “Were the subjects required to do all their shopping at the fake store during the length of the experiment?” “In what ways were the subjects’ shopping cart items lower calorie?” Did the subjects have to use their own money in the store, or were they given money by the researchers?” Or, “Were the respondents given a set budget, and then told their carts would be examined after checkout?” “How did the researchers control for altered environments and behavior change?


As you can see, there’s a lot at play here. If participants know they are being monitored, they are likely to change their behavior. Also, people’s short-term behavior differs greatly from their long-term behavior. In addition, if subjects’ laboratory experiences are different from their daily uncontrolled experiences – e.g., they are given the money to shop, instead of using their own, or they are given an experimental shopping budget of $200, when their normal budget is $100 or $300 – their behaviors will be unrealistic. Finally, it’s important to see how the subjects reduced the calorie content of their purchases. Did they do it by buying fewer or no unhealthy items? Did they buy smaller sizes of unhealthy items? Or worse – did they substitute cheaper brands of healthier foods or get smaller sizes of them, so that they could still fit the higher-taxed healthier foods into their budgets? It is quite possible to reduce calories but still be eating junk.

I do not know how the University of Buffalo conducted the experiment nor am I saying they did it unprofessionally. I am merely saying that we must never accept statistics blindly and that we should challenge every fact that we are told, especially because the person giving us the information might have an ax to grind.