1 Chapter 06 – Sampling: Theory and Methods Chapter 6 Sampling: Theory and Methods Chapter Summary by Learning Objectives LO 06-01: Explain the role of sampling in the research process. Sampling uses a portion of the population to make estimates about the entire population. The fundamentals of sampling are used in many of our everyday activities. For instance, we sample before selecting a TV program to watch, test-drive a car before deciding whether to purchase it, and take a bite of food to determine whether our food is too hot or if it needs additional seasoning. The term target population is used to identify the complete group of elements (e.g., people or objects) that are identified for investigation. The researcher selects sampling units from the target population and uses the results obtained from the sample to make conclusions about the target population. The sample must be representative of the target population if it is to provide accurate estimates of population parameters. Sampling is frequently used in marketing research projects instead of a census because sampling can significantly reduce the amount of time and money required in data collection. LO 06-02: Distinguish between probability and nonprobability sampling. In probability sampling, each sampling unit in the defined target population has a known probability of being selected for the sample. The actual probability of selection for each sampling unit may or may not be equal depending on the type of probability sampling design used. In nonprobability sampling, the probability of selection of each sampling unit is not known. The selection of sampling units is based on some type of intuitive judgment or knowledge of the researcher. Probability sampling enables the researcher to judge the reliability and validity of data collected by calculating the probability the findings based on the sample will differ from the defined target population. This observed difference can be partially attributed to the existence of sampling error. Each probability sampling method, simple random, systematic random, stratified, and cluster, has its own inherent advantages and disadvantages. In nonprobability sampling, the probability of selection of each sampling unit is not known. Therefore, potential sampling error cannot be accurately known either. Although there may be a temptation to generalize nonprobability sample results to the defined target population, for the most part the results are limited to the people who provided the data in the survey. Each © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 2 Chapter 06 – Sampling: Theory and Methods nonprobability sampling method—convenience, judgment, quota, and snowball—has its own inherent advantages and disadvantages. LO 06-03: Understand factors to consider when determining sample size. Researchers consider several factors when determining the appropriate sample size. The amount of time and money available often affect this decision. In general, the larger the sample, the greater the amount of resources required to collect data. Three factors that are of primary importance in the determination of sample size are (1) the variability of the population characteristics under consideration, (2) the level of confidence desired in the estimate, and (3) the degree of precision desired in estimating the population characteristic. The greater the variability of the characteristic under investigation, the higher the level of confidence required. Similarly, the more precise the required sample results, the larger the necessary sample size. Statistical formulas are used to determine the required sample size in probability sampling. Sample sizes for nonprobability sampling designs are determined using subjective methods such as industry standards, past studies, or the intuitive judgments of the researcher. The size of the defined target population does not affect the size of the required sample unless the population is large relative to the sample size. LO 06-04: Understand the steps in developing a sampling plan. A sampling plan is the blueprint or framework needed to ensure that the data collected are representative of the defined target population. A good sampling plan for primary data collection will include, at least, the following steps: (1) define the target population, (2) select the data collection method, (3) identify the sampling frames needed, (4) select the appropriate sampling method, (5) determine necessary sample sizes and overall contact rates, (6) create an operating plan for selecting sampling units, and (7) execute the operational plan. The steps in designing a sampling plan for secondary data are: (1) Examine how the original primary data was collected to ensure it is considered to determine whether it is consistent with the purpose of the current project, (2) Were the researchers who completed the previously collected data considered competent and reputable? (3) Is the documentation for the original study sufficient to assess its reliability and validity? (4) When were the original primary data collected and were there any unique circumstances at that time that may have influenced the results? (5) Were the original primary data collected in a manner consistent with recommended social sciences standards? and (6) Are there more than one source for similar data and are the results of the multiple sources consistent in their findings? © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 3 Chapter 06 – Sampling: Theory and Methods Chapter Outline Opening Vignette: Mobile Device Interactions Explode The opening vignette in this chapter describes development of internet searches by mobile phone. There has been a vast increase in the use of mobile phones for content online but consumers still prefer a desktop or laptop for searches. If a marketing research study were conducted on mobile phone search adoption, following would be the key questions to answer. What respondents should be included in a study about consumer acceptance of mobile search? How many respondents should be included in each study? As you read this chapter, you will learn the importance of knowing which groups to sample, how many elements to sample, and the different methods available to researchers for selecting highquality, reliable samples. I. Value of Sampling in Marketing Research Sampling is a concept we practice daily. Making a good first impression in a job interview because based on the initial exposure (a sample), people often make judgments about you as a person. o Channel surfing is another example. o Previewing a book before reading it. o Test-driving a car before buying. A commonality in all these situations is that a decision is based on the assumption that the smaller portion, or sample, is representative of the larger population. o From a general perspective, sampling involves selecting a relatively small number of elements from a larger defined group of elements. o And expecting that the information gathered from the small group will enable accurate judgments about the larger group. A. Sampling as a Part of the Research Process Sampling is often used when it is impossible or unreasonable to conduct a census. With a census, primary data is collected from every member of the target population. o The best example is the U.S. Census, taking place every 10 years. It is easy to see that sampling is less time-consuming and less costly than conducting a census. It is easier for American Airlines to gather data from 2,000 American business travelers than to survey several million travelers. Regardless of the research design, decision makers are concerned about the time © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 4 Chapter 06 – Sampling: Theory and Methods and cost required—shorter projects fit better. Samples also play an important indirect role in designing questionnaires. Depending on the research problem and the target population, o Sampling decisions influence the type of research design the survey instrument the actual questionnaire II. The Basics of Sampling Theory A. Population A population is an identifiable group of elements (e.g., people, products, organizations) of interest to the researcher and pertinent to the information problem. Mazda could hire J.D. Power to measure customer satisfaction among automobile owners. o The population of interest would be all car owners. o J.D. Power is unlikely to draw a sample that would truly represent such a broad, heterogeneous population. o This lack of specificity is common in marketing research. Most businesses that collect data are not really concerned with total populations, but with a prescribed segment. o In this chapter, we use a modified definition of population: defined target population. A defined target population is the complete set of elements identified for investigation based on the objectives of the research project. A precise definition of the target population is essential and is usually done in terms of elements, sampling units, and time frames. Sampling units are target population elements actually available to be used during the sampling process. o Exhibit 6.1 clarifies several sampling theory terms. B. Sampling Frame After defining the target population, the researcher develops a list of all eligible sampling units, referred to as a sampling frame. Some common sources of sampling frames are lists of registered voters and customer lists from magazine publishers or credit card companies. © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 5 Chapter 06 – Sampling: Theory and Methods There also are specialized commercial companies (for instance, Survey Sampling, Inc.; American Business Lists, Inc.; and Scientific Telephone Samples) that sell databases containing names, addresses, and telephone numbers of potential population elements. Regardless of the source, it is often difficult and expensive to obtain accurate, representative, and current sampling frames. It is doubtful a list of people who ate a Taco Bell taco in a particular city in the past six months is readily available. Researchers have to use alternative methods such as random-digit dialing or mall-intercept interviews to generate a sample. C. Factors Underlying Sampling Theory To understand sampling theory, researchers must know sampling-related concepts. Sampling concepts and approaches are often discussed as if the researcher already knows the key population parameters prior to conducting the research project. However, because most business environments are complex and rapidly changing, researchers often do not know these parameters prior to conducting research. o For example, experts estimate the world’s population exceeds 3 billion people, but the actual number of online shoppers is more difficult to estimate. If business decision makers had complete knowledge about their target populations, they would have perfect information, eliminating the need for primary research. 95% of marketing problems exist because decision makers lack information about problem situations o Who their customer are o Customers’ attitudes and preferences o Marketplace behaviors Central Limit Theorem The central limit theorem (CLT) describes the theoretical characteristics of a sample population. The CLT is the theoretical backbone of survey research and is important in understanding the concepts of sampling error, statistical significance, and sample sizes. o In brief, the theorem states that for almost all defined target populations, © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 6 Chapter 06 – Sampling: Theory and Methods The sampling distribution of the mean ( x ) or the percentage value ( p ) derived from a simple random sample will be approximately normally distributed, Given the sample size is sufficiently large (when n is ≥30). o Moreover, the mean ( x ) of the random sample with an estimated sampling error ( S x ) fluctuates around the true population mean (µ) with a standard error of σ / n and an approximately normal sampling distribution regardless of the shape of the probability frequency distribution of the overall target population In other words, there is a high probability the mean of any sample ( x ) taken from the target population will be a close approximation of the true target population mean (µ), as one increases the size of the sample (n). With an understanding of the basics of the central limit theorem (CLT), the researcher can do the following: Draw representative samples from any target population Obtain sample statistics from a random sample that serve as accurate estimates of the target population’s parameters Draw one random sample, instead of many, reducing the costs of data collection More accurately assess the reliability and validity of constructs and scale measurements Statistically analyze data and transform it into meaningful information about the target population D. Tools Used to Assess the Quality of Samples There are numerous opportunities to make mistakes that result in some type of bias in any research study. This bias can be classified as either: o Sampling error o Nonsampling error Random sampling errors could be detected by o Observing the difference between the sample results and the results of a census conducted using identical procedures. Two difficulties associated with detecting sampling error are: o A census is very seldom conducted in survey research. o Sampling error can be determined only after the sample is drawn and data collection is completed. © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 7 Chapter 06 – Sampling: Theory and Methods Sampling error is any bias resulting from mistakes in either the selection process for prospective sampling units or in determining the sample size. Moreover, random sampling error tends to occur because of chance variations in the selection of sampling units. o Even if the sampling units are properly selected, those units still might not be a perfect representation of the defined target population, but they generally are reliable estimates. When there is a discrepancy between the statistic estimated from the sample and the actual value from the population, a sampling error has occurred. o Sampling error can be reduced by increasing the size of the sample. o In fact, doubling the size of the sample can reduce the sampling error, but increasing the sample size primarily to reduce the standard error may not be worth the cost. Nonsampling error occurs regardless of whether a sample or a census is used. These errors can occur at any stage of the research process. o For example, the target population may be inaccurately defined causing population frame error o Inappropriate question/scale measurements can result in measurement error o A questionnaire may be poorly designed causing response error o There may be other errors in gathering and recording data or when raw data are coded and entered for analysis. In general, the more extensive a study, the greater the potential for nonsampling errors. o Unlike sampling error, there are no statistical procedures to assess the impact of nonsampling errors on the quality of the data collected. o Yet, most researchers realize that all forms of nonsampling errors reduce the overall quality of the data regardless of the data collection method. Nonsampling errors usually are related to the accuracy of the data, whereas sampling errors relate to the representativeness of the sample to the defined target population. III. Probability and Nonprobability Sampling There are two basic sampling designs: probability and nonprobability. Exhibit 6.2 lists the different types of both sampling methods, and included here. o Probability sampling methods include: simple random sampling, systematic random sampling, stratified random sampling, and cluster sampling. o Nonprobability sampling methods include: convenience sampling, judgment sampling, quota sampling, and snowball sampling. © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 8 Chapter 06 – Sampling: Theory and Methods In probability sampling, each sampling unit in the defined target population has a known probability of being selected for the sample. The actual probability of selection for each sampling unit may or may not be equal depending on the type of probability sampling design used. Specific rules for selecting members from the population for inclusion in the sample are determined at the beginning of a study to ensure o unbiased selection of the sampling units o proper sample representation of the defined target population Probability sampling enables the researcher to judge the reliability and validity of data collected by calculating the probability that the sample findings are different from the defined target population. o The observed difference can be partially attributed to the existence of sampling error. o The results obtained by using probability sampling designs can be generalized to the target population within a specified margin of error. In nonprobability sampling, the probability of selecting each sampling unit is not known. Therefore, sampling error is not known. o The selection of sampling units is based on the judgment of the researcher and may or may not be representative of the target population. o The degree to which the sample is representative of the defined target population depends on the sampling approach and how well the researcher executes the selection activities. A. Probability Sampling Designs Simple Random Sampling: Simple random sampling is a probability sampling in which every sampling unit has a known and equal chance of being selected. Drawing names out a hat in order to choose 10 of 30 students. Many software programs including SPSS have an option to select a random sample. Advantages and Disadvantages Simple random sampling has several advantages. The technique is easily understood and the survey’s results can be generalized to the defined target population with a prespecified margin of error. Simple random samples produce unbiased estimates of the population’s characteristics. o This method guarantees that every sampling unit has a known and equal chance of being selected, no matter the actual size of the sample, © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 9 Chapter 06 – Sampling: Theory and Methods resulting in a valid representation of the defined target population. The primary disadvantage of simple random sampling is the difficulty of obtaining a complete and accurate listing of the target population elements. Simple random sampling requires that all sampling units be identified. o For this reason, simple random sampling works best for small populations where accurate lists are available. Systematic Random Sampling: Systematic random sampling is similar to simple random sampling but requires that the defined target population be ordered in some way, usually in the form of a customer list, taxpayer roll, or membership roster. Compared to simple random sampling, systematic random sampling is less costly because it can be done relatively quickly. When executed properly, systematic random sampling creates a sample of objects or prospective respondents that is very similar in quality to a sample drawn using simple random sampling. To use systematic random sampling, the researcher must be able to secure a complete listing of the potential sampling units that make up the defined target population. But unlike simple random sampling, there is no need to give the sampling units any special code prior to drawing the sample. Instead, sampling units are selected according to their position using a skip interval. o The skip interval is determined by dividing the number of potential sampling units in the defined target population by the number of units desired in the sample. o The required skip interval is calculated using the following formula: Skip interval = Defined target population list size/Desired sample size For example, if a researcher wants a sample of 100 drawn from a population of 1,000, the skip interval would be 10 (1,000/100). Then the researcher randomly selects a starting point and takes every 10th unit until they proceed through the entire list. Exhibit 6.3 displays the steps that a researcher would take in drawing a systematic random sample. Advantages and Disadvantages Systematic sampling is frequently used because it is a relatively easy way to draw a sample while ensuring randomness. The availability of lists and the shorter time required to draw a sample versus simple random sampling makes systematic sampling an attractive, economical method for researchers. The greatest weakness of systematic random sampling is the possibility of © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 10 Chapter 06 – Sampling: Theory and Methods hidden patterns in the list of names that create bias. o Hidden patterns represent populations that researchers may be interested in studying, but often are hard to reach or “hidden.” o Such populations may be hidden because they exhibit Some type of social stigma (certain medical conditions) Illicit or illegal behavior (drug usage) Atypical or socially marginalized individuals (homeless) Another difficulty is the number of sampling units in the target population must be known. o When the size of the target population is large or unknown, identifying the number of units is difficult, and estimates may not be accurate. Stratified Random Sampling: Stratified random sampling involves the separation of the target population into different groups, called strata, and the selection of samples from each stratum. It is similar to segmentation of the defined target population into smaller, more homogeneous sets of elements. To ensure that the sample maintains the required precision, representative samples must be drawn from each of the smaller population groups (stratum). Drawing a stratified random sample involves three basic steps. o Dividing the target population into homogeneous subgroups or strata o Drawing random samples from each stratum o Combining the samples from each stratum into a single sample of the target population As an example, if researchers are interested in the market potential for home security systems in a specific geographic area, o They may wish to divide the homeowners into several different strata. o Subdivisions could be based on such factors as Assessed value of the homes Household income Population density Or location (sections designated as high- or low-crime areas) Two common methods are used to derive samples from the strata: proportionate and disproportionate. In proportionately stratified sampling, o The sample size from each stratum is dependent on that stratum’s size relative to the defined target population. Larger strata are sampled more heavily as they make up a larger percentage of the target population. In disproportionately stratified sampling, © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 11 Chapter 06 – Sampling: Theory and Methods o The sample size selected from each stratum is independent of that stratum’s proportion of the total defined target population. This is used when stratification of the target population produces sample sizes for subgroups that differ from their relative importance to the study. For example, stratification of manufacturers based on number of employees will usually result in large segments with fewer than ten employees And a very small proportion with, say, 500 or more employees. The economic importance of those firms with 500 or more employees would dictate taking a larger sample from this stratum and a smaller sample from the other subgroup with fewer than 10 employees. An alternative type of disproportionate stratified method is optimal allocation sampling. In this method, consideration is given to the relative size of the stratum as well as the variability within the stratum to determine the necessary sample size of each stratum. o The basic logic here is that the greater the homogeneity of the prospective sampling units within a particular stratum All else being equal o The fewer the units that would have to be selected to accurately estimate the true population parameter (u or P) for that subgroup. In contrast, more units would be selected for any stratum that has considerable variance among its sampling units or that is heterogeneous. In some situations, multisource sampling is used when no single source can generate a large or low incidence sample. While researchers have shied away from using multiple sources o Mainly because sampling theory dictates the use of a defined single population Changing respondent behaviors are supporting multisource sampling. o Behaviors such as less use of email and more frequent use of social media For example, if the manufacturer of golfing equipment used a stratified random sample of country club members as the sample frame, o The likelihood of visitors or invited guests would be hidden from the researcher. © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 12 Chapter 06 – Sampling: Theory and Methods o Excluding these two groups could omit valuable data that would be available in a multisource approach. Exhibit 6.4 displays the steps that a researcher would take in drawing a stratified random sample. Advantages and Disadvantages Dividing the target population into homogeneous strata has several advantages, including: o The assurance of representativeness in the sample o The opportunity to study each stratum and make comparisons between strata o The ability to make estimates for the target population with the expectation of greater precision and less error The primary difficulty encountered with stratified sampling is determining the basis for stratifying. o Stratification is based on the target population’s characteristics of interest. o Secondary information relevant to the required stratification factors might not be readily available, forcing researchers to use less desirable criteria to stratify the target population. Usually, the larger the number of relevant strata, the more precise the results. o Inclusion of irrelevant strata will waste time and money without providing meaningful results. Cluster Sampling Cluster sampling is similar to stratified random sampling, but is different in that the sampling units are divided into mutually exclusive and collectively exhaustive subpopulations called clusters. Each cluster is assumed to be representative of the heterogeneity of the target population. o Examples of possible divisions for cluster sampling include: Customers who patronize a store on a given day The audience for a movie shown at a particular time—the matinee Or the invoices processed during a specific week Once the cluster has been identified, the prospective sampling units are selected for the sample by either using a simple random sampling method or canvassing all the elements (a census) within the defined cluster. A popular form of cluster sampling is area sampling. In area sampling, the clusters are formed by geographic designations. o Examples include metropolitan statistical areas (MSAs), cities, © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 13 Chapter 06 – Sampling: Theory and Methods subdivisions, and blocks. o Any geographic area with identifiable boundaries can be used. When using area sampling, the researcher has two additional options: the onestep approach or the two-step approach. o When deciding on a one-step approach, the researcher must have enough prior information about the various geographic clusters to believe that all the geographic clusters are basically identical with regard to the specific factors that were used to initially identify the clusters. By assuming all clusters are identical, the researcher can focus attention on surveying the sampling units within one designated cluster and generalizing the results to the population. The probability aspect of this sampling method is executed by randomly selecting one geographic cluster and sampling all units in that cluster. Advantages and Disadvantages Cluster sampling is widely used because of its cost-effectiveness and ease of implementation. In many cases, the only representative sampling frame available to researchers is one based on clusters. o Such as states, counties, MSAs, census tracts o These lists can be easily compiled, avoiding the need of lists of all the individual sampling units of the target population. A primary disadvantage of cluster sampling is that the clusters often are homogeneous. The more homogeneous the cluster, the less precise the sample estimates. o Ideally, the people in a cluster should be as heterogeneous as those in the population. Another concern with cluster sampling is the appropriateness of the designated cluster factor used to identify the sampling units within clusters. While the defined target population remains constant, o The subdivision of sampling units can be modified depending on the selection of the factor used to identify the clusters. Caution must be used in selecting the factor to determine clusters in area sampling situations. B. Nonprobability Sampling Designs Convenience Sampling: Convenience sampling is a method in which samples are drawn based on convenience. For example, interviewing people at shopping malls or other high-traffic areas is a common method of generating a convenience sample. © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 14 Chapter 06 – Sampling: Theory and Methods o The assumption is that the individuals interviewed at the shopping mall are similar to the overall defined target population with regard to the characteristic being studied. o In reality, it is difficult to accurately assess the representativeness of the sample. o Given self-selection and the voluntary nature of participating, researchers should consider the impact of nonresponse error when using sampling based on convenience only. Advantages and Disadvantages Convenience sampling enables a large number of respondents to be interviewed in a relatively short time. For this reason, it is commonly used in the early stages of research, including construct and scale measurement development as well as pretesting of questionnaires. o But using convenience samples to develop constructs and scales can be risky. Assume a researcher is developing a measure of service quality and in the preliminary stages uses a convenience sample of 300 undergraduate business students. Serious questions should be raised about whether they are truly representative of the general population. o By developing constructs and scales using a convenience sample, the constructs might be unreliable if used to study a broader population. Another major disadvantage of convenience samples is that the data are not generalizable to the defined target population. o The representativeness of the sample cannot be measured because sampling error estimates cannot be calculated. Judgment Sampling In judgment sampling, or purposive sampling, respondents are selected because the researcher believes they meet the requirements of the study. For example, sales representatives may be interviewed rather than customers to determine whether customers’ wants and needs are changing or to assess the firm’s product or service performance. Similarly, Procter & Gamble may select a sample of key accounts to obtain information about consumption patterns and changes in demand. o The assumption is that the opinions of a group of experts are representative of the target population. Advantages and Disadvantages If the judgment of the researcher is correct, the sample generated by judgment sampling © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 15 Chapter 06 – Sampling: Theory and Methods will be better than one generated by convenience sampling. As with all nonprobability sampling procedures, however, the representativeness of the sample cannot be measured. Thus data collected from judgment sampling should be interpreted cautiously Quota Sampling Quota sampling involves the selection of prospective participants according to prespecified quotas for either Demographic characteristics: o Age, race, gender, income Specific attitudes: o Satisfied/dissatisfied, liking/disliking, great/marginal/no quality Or specific behaviors: o Regular/occasional/rare customer, product user/nonuser The purpose of quota sampling is to assure that prespecified subgroups of the population are represented. Research panel samples are most often considered quota sampling. They are quota samples drawn on demographic quota, behavioral patterns, and similar information. They are nonprobability samples but are considered representative of the target population. o As an example, if a researcher would like a sample that is representative of middle managers in a single industry or a cross-section of industries, Then Qualtrics can contract to collect data from such a sample. o Similarly, if the target population is physicians, attorneys, teachers, or any type of consumer group, Then panels are available to represent them. Qualtrics provides assistance in developing and distributing questionnaires to current customers For a fee, companies can upload data to the Qualtrics platform, develop their questionnaire using the software, and distribute and collect the data. There are two types of research panels: in-house and one set up by and managed by another company. Companies justify in-house research panels only if they plan on conducting numerous studies in future years. Most companies work with an outside vendor, such as Qualtrics. A frequently sought panel today is social media users. This can be easily obtained, depending on the specific demographic or © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 16 Chapter 06 – Sampling: Theory and Methods classification variables. o Younger age groups (18–40 years old) are easier to obtain as they are more frequent social media users. o But usage among older groups (40–65) is increasing. A popular panel group for social media users is students. They are often easily accessible and inexpensive to obtain responses from, particularly for university professors. If student samples are used, the researcher needs to screen them to ensure they are knowledgeable about the products they are commenting on in the survey. Advantages and Disadvantages The major advantage of quota sampling is that the sample generated contains specific subgroups in the proportions desired by researchers. Also, quota sampling reduces selection bias by field workers. An inherent limitation of quota sampling is that the success of the study is dependent on subjective decisions made by researchers. Since it is a nonprobability sampling method, the representativeness of the sample cannot be measured. o Therefore, generalizing the results beyond the sampled respondents is questionable. Snowball Sampling Snowball sampling involves identifying a set of respondents who can help the researcher identify additional people to include in the study. This method of sampling is also called referral sampling. Snowball sampling is typically used in the following situations. o The defined target population is small and unique o Compiling a complete list of sampling units is very difficult Consider, for example, researching the attitudes and behaviors of volunteers working for charitable organizations like the Children’s Wish Foundation. o Traditional sampling methods would require an extensive search o The snowball method yields better results in less time and at a lower cost o When the researcher finds a qualified respondent, they solicit their help in identifying others with similar characteristics. o While members may not be publicly known, intra-circle knowledge is very accurate. The underlying logic is that rare groups tend to form their own unique social circles. Advantages and Disadvantages Snowball sampling is a reasonable method of identifying respondents who are members © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 17 Chapter 06 – Sampling: Theory and Methods of small, hard-to-reach, uniquely defined target populations. As a nonprobability sampling method, it is most useful in qualitative research. But snowball sampling allows bias to enter the study. o If there are significant differences between people who are known in certain social circles and those who are not, there may be problems with this sampling technique. o Like all other nonprobability sampling approaches, the ability to generalize the results to members of the target population is limited. C. Determining the Appropriate Sampling Design Determining the best sampling design involves consideration of several factors. Exhibit 6.5 provides an overview of the major factors that should be considered. Take a close look at Exhibit 6.5 and review your understanding of these factors. IV. Determining Sample Sizes Determining the sample size is not an easy task. The researcher must consider how precise the estimates must be and how much time and money are available to collect the required data, o Since data collection is generally one of the most expensive components of a study. Sample size determination differs between probability and nonprobability designs. A. Probability Sample Sizes Three factors play an important role in determining sample sizes with probability designs. The population variance, which is a measure of the dispersion of the population, and its square root, referred to as the population standard deviation. o The greater the variability in the data being estimated, the larger the sample size needed. The level of confidence desired in the estimate. o Confidence is the certainty that the true value of what we are estimating falls within the precision range selected. Marketing researchers typically select 90–95% confidence level for their projects. o The higher the level of confidence desired, the larger the sample size needed. The degree of precision desired in estimating the population characteristic. o Precision is the acceptable amount of error in the sample estimate. For example, if we want to estimate the likelihood of returning in the future to the Sante Fe Grill (based on a 7-point scale) © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 18 Chapter 06 – Sampling: Theory and Methods Is it acceptable to be within a single scale point, either plus or minus? o The more precise the required sample results, that is, the smaller the desired error, the larger the sample size. For a particular sample size, there is a trade-off between degree of confidence and degree of precision, And the desire for confidence and precision must be balanced. These two considerations must be agreed upon by the client and the marketing researcher based on the research situation. Formulas based on statistical theory can be used to compute the sample size. For pragmatic reasons, such as budget and time constraints, alternative “ad hoc” methods often are used. o Examples of these are sample sizes based on rules of thumb, previous similar studies, one’s own experience, or simply what is affordable. Irrespective of how the sample size is determined, it is essential that it should be of a sufficient size and quality to yield results that are seen to be credible in terms of their accuracy and consistency. When formulas are used to determine sample size, there are separate approaches based on a predicted population mean and a population proportion. The formulas are used to estimate the sample size for a simple random sample. When the situation involves estimating a population mean, the formula for calculating the sample size is: σ2 2 n Z B,CL e2 Where o Z B,CL = the standardized z value associated with the level of confidence o = Estimate of the population standard deviation (σ) based on some type of prior information o e = Acceptable tolerance level of error (stated in percentage points) In situations where estimates of a population proportion are of concern, the standardized formula for calculating the needed sample size would be: P X Q 2 n Z B,CL 2 e Where © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 19 Chapter 06 – Sampling: Theory and Methods o Z B,CL = the standardized z value associated with the level of confidence o P = Estimate of expected population proportion having a desired characteristic based on intuition or prior information o Q 1 P , or the estimate of expected population proportion not holding the characteristic of interest o e = Acceptable tolerance level of error (stated in percentage points) When the defined target population size in a consumer study is 500 elements or less, the researcher should consider taking a census of the population rather than a sample. The logic behind this is based on the theoretical notion that at least 384 sampling units need to be included in most studies to have a ±5% confidence level and a sampling error of ±5 percentage points. Sample sizes in business-to-business studies present a different problem than in consumer studies where the population almost always is very large. With business-to-business studies the population frequently is only 200 to 300 individuals. o What is an acceptable sample size? o Should all of them be contacted and surveyed? An acceptable sample size may be as small as 30% but the final decision would be made after examining the profile of the respondents. For example, look at position titles to see if you have a good cross-section of respondents from all relevant categories. You may wish to avoid having only smaller firms that do not provide a representative picture of the firm’s customers. Whatever approach you use, in the final analysis you must have a good understanding of who has responded so you can accurately interpret the findings. B. Sampling from a Small Population In the previously described formulas, the size of the population has no impact on the determination of the sample size—this is always true for “large” populations. When working with small populations, use of the above formulas may lead to an unnecessarily large sample size. If, for example, the sample size is larger than 5% of the population, then the calculated sample size should be multiplied by the following correction factor: N N n 1 © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 20 Chapter 06 – Sampling: Theory and Methods Where o N = Population size o n = Calculated sample size determined by the original formula Thus, the adjusted sample size is: o Sample size Specified degree of confidence Variability / Desired precision N N n 1 C. Nonprobability Sample Sizes Sample size formulas cannot be used for nonprobability samples. Determining the sample size for nonprobability samples is usually a subjective, intuitive judgment made by the researcher based on either past studies, industry standards, or the amount of resources available. Regardless of the method, the sampling results should not be used to make statistical inferences about the true population parameters. o Researchers can compare specific characteristics of the sample, such as age, income, and education, and note that the sample is similar to the population. o But the best that can be offered is a description of the sample findings. D. Other Sample Size Determination Approaches Sample sizes are often determined using less formal approaches. For example, the budget is almost always a consideration, and the sample size then will be determined by what the client can afford. o A related approach is basing sample size on similar previous studies that are considered comparable and judged as having produced reliable and valid findings. Consideration also is often given to the number of subgroups that will be examined and the minimum sample size per subgroup needed to draw conclusions about each subgroup. o If the minimum subgroup sample size is 30 and there are five subgroups, then the total sample size would be 150. Sometimes the sample size is determined by the number of questions on a questionnaire. o Typical rules of thumb are five respondents for each question asked. o If there are 25 questions, the recommended sample is 125. The sample size may be determined by the method of statistical analysis. o Partial least squares analysis (Chapter 12) is appropriate for smaller samples. © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 2 21 Chapter 06 – Sampling: Theory and Methods V. Decisions on which of these approaches, or combinations of approaches, to use require the judgment of both research experts and managers to select the best alternative. Steps in Developing a Sampling Plan A sampling plan is the blueprint to ensure the data collected are representative of the population. A good sampling plan includes the following seven steps: Step 1: Define the Target Population With the problem and research objectives as guidelines, the characteristics of the target population should be identified. Understanding the target population helps successfully draw a representative sample. Step 2: Select the Data Collection Method Choices include some type of interviewing approach, a self-administered survey, or perhaps observation. The method of data collection guides the researcher in selecting the sampling frame(s). Step 3: Identify the Sampling Frame(s) Needed A list of eligible sampling units must be obtained. An incomplete sampling frame decreases the likelihood of drawing a representative sample. Examples of sampling list sources: o Customer lists from company’s internal databases o Random-digit dialing o An organization’s membership roster o Or purchased from a sampling vendor Step 4: Select the Appropriate Sampling Method The researcher chooses between probability and nonprobability methods. o If the findings will be generalized. A probability sampling method will provide more accurate information than will nonprobability sampling methods. The researcher must considers seven factors: o Research objectives o Desired accuracy o Availability of resources o Time frame © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 22 Chapter 06 – Sampling: Theory and Methods o Knowledge of the target population o Scope of the research o Statistical analysis needs Step 5: Determine Necessary Sample Sizes and Overall Contact Rates The researcher must decide how precise the sample estimates must be and how much time and money are available to collect the data. To determine the appropriate sample size, decisions have to be made concerning: o The variability of the population characteristic under investigation o The level of confidence desired in the estimates o The precision required The researcher also must decide how many completed surveys are needed for data analysis. o And the impact of having fewer surveys than initially desired would have on the accuracy of the sample statistics. Step 6: Create an Operating Plan for Selecting Sampling Units The researcher must decide how to contact the prospective respondents in the sample. Instructions should be written so that interviewers know what to do and how to handle problems contacting prospective respondents. o For example, if the study data will be collected using mall-intercept interviews, o Then interviewers must be given instructions on how to select respondents and conduct the interviews. Step 7: Execute the Operational Plan This step is similar to collecting the data from respondents. The important consideration in this step is to maintain consistency and control. VI. Sampling and Secondary Data The process of designing a representative sample of the population is frequently discussed when collecting primary data. However, researchers using secondary data commonly analyze the entire set of data without even considering implementation of a sampling procedure. o The reason is that most secondary databases were not that large, and it was easy to quickly analyze all available data. o The exception was large government data, such as populations. In the last decade, the era of big data emerged along with additional huge data files. Most of the currently available secondary data require sampling procedures to © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC. 23 Chapter 06 – Sampling: Theory and Methods ensure the accuracy of research results. Knowledge of the sampling process with secondary data is essential as they differ from that with primary data. Typical steps in designing a sampling plan when secondary data are used: o Examine how the original primary data were collected to ensure it is considered to determine whether it is consistent with the purpose of the current project. o Were the researchers who completed the previously collected data considered competent and reputable? o Is the documentation for the original study sufficient to assess its reliability and validity? o When were the original primary data collected and were there any unique circumstances at that time that may have influenced the results? o Were the original primary data collected in a manner consistent with recommended social sciences standards—sampling, response rates, data cleaning, and so on? o Are there more than one source for similar data and are the results of the multiple sources consistent in their findings? Completion of all these steps is important. o But the sampling design and execution of the original study is particularly important o More than the other elements, it determines the accuracy of the secondary research findings. © McGraw Hill LLC. All rights reserved. No reproduction or distribution without the prior written consent of McGraw Hill LLC.