Marketing 101: Sampling Plan

In the last Marketing 101 post we examined common Contact Methods for acquiring Primary Data.  I listed three traditional methods: telephone, mail, and focus groups.  The fact of the matter is that online technologies have completely changed how we as marketing directors and CMO's do our jobs.  I truly believe this is for the better.  It so so much easier to collect the Primary Data we need via online methods, and it tends to be more cost effective than offline methods.  However there are also challenges to online methods, and some of the same issues exist when it comes to the reliability of the data we collect.

Whether it's online or offline, if we're not doing focus groups, we're usually using surveys to collect Primary Data.  Surveys give us the opportunity to draw conclusions about different groups of consumers by studying a small statistical sample of the total consumer population.  The "sample" is the key.  A sample is usually defined as a segment of the population selected for our research that will represent the larger population as a whole.  Whether or not a sample is good enough to make observations with, depends on how we've designed it.

Designing a sample is a three step process:
1) Decide who you are going to survey
2) Decide how many you are going to survey
3) Decide how you are selecting the participants in the sample

Let's examine each of these three steps a little more.

1) Decide who you are going to survey
First, you have to decide who you are actually going to survey.  In more statistical terms, we are asking "what is the sampling unit"?  Any group of people can be used as a sampling unit.  What I mean here is children, adult women, men, etc.  Your sampling unit should be determined by the target groups in your survey, and the data you have about your target customers. If you don't know who your target customer is, then you have some research to do first.  Choosing the wrong sampling unit will waste your time and your money.  It will give you data that you cannot use, because the results from that group will be irrelevant.

2) How many should be surveyed (what is the sample size)
When we are asking ourselves "how many should be surveyed", what we are saying here is "what is the sampling size?"  Sample sizes that contain more people usually give us increased accuracy. For you statistical junkies, there are certain facts of mathematical statistics that describe this, such as the law of large numbers and the central limit theorem.  To keep this simple for our discussion, larger samples will give you more statistically reliable results than smaller sample sizes.  However, larger sample sizes will cost you more money.  Do not assume that you need to attempt to sample an entire population segment (which would take forever, and be almost impossible).  Usually less than 1 percent of a population segment will provide statistically reliable results.  There is a down-side to Probability Samples: cost.  Depending on your Contact Method, larger samples will result in drastically higher costs.  When cost is a factor, then researchers turn to Non-Probability samples.

3) How should the people in the sample be selected?
What we are asking here is, "What is the sampling procedure we are going to follow?"  There are two different types of samples we can choose from: Probability Samples, and Non-Probability Samples.  Probability Samples give each population member (a.k.a. a potential participant) a possible chance of being included in the sample.  Because you are not sampling the entire population, probability samples will always contain margin for error.  The larger the margin of error, the less trust you can place in the data you have that is supposed to represent your "population".  Larger samples give you less margin of error, and less margin of error lets you trust your data more.

There are three different types of Probability Samples:
Simple Random Sample
Every member of the population has a known and equal chance of selection.

Stratified Random Sample
The population is divided into mutually exclusive groups (such as age and race) and random samples are drawn from each group.  Basically, you are splitting your population into defined groups, and then sampling each of those groups.

Cluster (area) Samples
The population is divided into mutually exclusive groups (such as blocks, and they are relatively homogeneous) and the researcher draws a simple random sample of each group.

Non-probability sampling is much less expensive than doing Probability Sampling, but the results are of limited value, because the data is less reliable.  Non-probability samples should be used with caution. Non-probability sampling techniques cannot be used to deduce generalizations from the sample to the general population. Any generalizations created from a non-probability sample MUST be filtered through the researcher's knowledge (and yours) of the customer population being studied.

There are three different kind of Non-probability samples:

Convenience Sample
In a Convenience Sample, the researcher selects the "easiest", most convenient to locate member from the immediate population to obtain research data from.  I would consider this one of the most hap-hazard methods.  There is practically nothing you can generalize about the data you obtain, other than considering it a "snapshot" of a a particular group, at a particular time, at a particular place.

Judgment Sample
In a Judgment Sample, the researcher will use his/her judgement to select the the people sampled.  Immediately you have to ask...how good is their judgment in selecting a good candidate?  Again, the data that you obtain from this sort of sampling is just not reliable for generalized conclusions, but it may be interesting to use as a "snapshot".

Quota Sample
Probably the worst method I can think of, a Quota Sample is simply a researcher grabing enough people to meet a quota requirement for sampling participants.  Stay away from this sort of methodology.  Your data is practically useless.

Never select a sampling method without taking the time (as you always should) to weigh the needs you have when collecting Primary Data.  Always take into consideration your time-frame and your budget, and always try to be as objective as possible when you are evaluating the Primary Data you have obtained.



Follow @macdailybites

Marketing 101: Primary Data - Contact Methods

In my last Marketing 101 piece, I spent some time introducing the Research Methods that we typically use in Primary Data collection.  Remember that Research Methods consist of surveys, experimentation and observation.  Surveys are the workhorse of Primary Data collection.  They tend to give us the bulk of our information related to customer trends and buying behaviors.  In order to conduct these surveys, information is collected in a variety of manners.  Typically these Contact Methods include mail, telephone, focus groups, and various other online technologies.

Mail
The mailed questionnaire is a classic primary data collection method.  It is very valuable, because it can be used to collect massive amounts of primary data for a very low cost per respondent.  We're talking the cost of paper and postage.  (Remember that you do need to calculate the labor costs of crafting the survey and processing the data once it comes back to you)  The data that you can collect from mail methods is usually considered very good for a few reasons.  First, there is little chance for "interviewer bias", because there is no live person there to ask the questions in a manner that could influence a person to respond in a manner different than they normally would.  Second, because they are not being interviewed in person, the respondents are usually more willing to give more honest responses.  And third, because you are not relying on the interviewer to record responses, no interviewer bias is introduced to the answers.  

However there are downsides to using mail as a contact method.  First, mail-based surveying is not very flexible, because all respondents are required to approach their surveys in the same way.  Second,  collecting primary data via mail is very slow.  It can take months before a reasonable amount of your sample sends the questionnaires back to you for processing.  Third, because written surveys usually take longer to complete, the response rate trends lower - simply because it takes more work.  The response rate is actually considred to be very fair.  It's harder to control the sample, beacuse you don't know which households will respond, let alone who at the residence will respond. 

Telephone
Telephone has always been a fairly good method of collecting Primary Data.  First, it is possible to collect massive amounts of data very quickly by using multiple people at the same time to call and conduct phone interviews everyday.  Second, telephone interviews allow for more flexibility, because your interviewers have the opportunity to provide clarity about any questions that respondents don't understand.  Third, you have excellent control of the sample, because interviewers can screen out callers before an interview is conducted. Fourth, with the right incentives, typically the response rate is actually very good.  

There are problems with collecting Primary Data via telephone as well.  First, the quality of the data you collect can only be considered fair at times, because the interviewer can inadvertently introduce bias into the answers based on how the questions are asked.  Second, because the respondents are interacting with a live person, they may not want to provide completely honest answers to questions that they may consider too private.  Third, telephone surveys are more expensive, because they require more labor.

Focus Groups
Focus Groups are a Primary Data collection standard.  Focus Groups have become a leading method for gaining valuable insight into consumer thoughts and feelings and their buying behaviors.  Traditionally focus groups consist of a moderator leading six to ten people.  However technology has allowed focus groups to be conducted through video conferencing and webinars via the internet, which allows people from different locations to be connected together which can improve sampling. These groups will participate in discussions about products, advertisements, services, and even organizations.  The focus group attendees are usually paid a small sum for attending.  The moderator will attempt to lead an easy and free flowing discussion hoping that free honest responses will be given.  Data is usually recorded by the moderator, however sometimes focus groups are observed by staff members via cameras or through one-way windows.  

Focus groups also have their issues.  First, focus groups use much smaller sample sizes in order to control cost and keep their sizes manageable.  Second, because sample sizes are so small, it is hard to reliably statistically generalize the results.  Third, attendees of focus groups are not always candid and honest.  The phyiscal and sociological environment of the focus group can create peer pressure, which leads attendees to alter their results in order to "fit in" with the people surrounding them. This is being combated by using environments that are relevant to the products and services being studied in order to get more relevant and open responses.  Fourth, focus groups cost much much more to conduct due to the costs of time, labor, location, and data acquisition.  Only use focus groups when it is appropriate and you are looking for specific types of data that you cannot reliably acquire with other Contact Methods.

Online Methods
The internet has single-handedly changed the Primary Data landscape.  Researchers are no longer confined to using mail, telephone, or physically location-bound focus groups.  There are many electronic alternatives to all three primary contact methods.

Email surveys and survey research websites are very affordable alternatives to direct mail and telephone interviews.  Because they are electronic, they are much less expensive to conduct, and data is instantly stored into a database that can be manipulated and analyzed. It is also quicker to create a large sampling, because your contact list can be created by interfacing with your existing customer database, or by purchasing lists of consumers from secondary data companies.  As with mail, the quality of responses tends to be very good, because it is an impersonal process and respondents feel more open to share more "private" information.

Another alternative to the telephone or physical focus group collection methods is Skype, or any other video conferencing type of technology.  Because Skype and services such as Oovoo are available for free or very little cost, it is much less expensive to conduct focus group research when the researcher needs to observe the reactions of the attendees.  These services will usually have the ability to record online "meetings", which allows you to store and refer back to interviews easily.


No matter what contact method you choose to use in your Primary Data collection process, it is important to spend extensive time up front evaluating the type of data you need, and which methods fit your required data types, cost, and schedule.


Follow @macdailybites