Você está na página 1de 17

III UNIT Primary vs.

Secondary Data Primary data are originated by a researcher for the specific purpose of addressing the problem at hand. The collection of primary data involves all six steps of the marketing research process Secondary data are data which have already been collected for purposes other than the problem at hand. These data can be located quickly and inexpensively. A Comparison of Primary & Secondary Data Uses of Secondary Data Identify the problem Better define the problem Develop an approach to the problem Formulate an appropriate research design (for example, by identifying the key variables) Answer certain research questions and test some hypotheses Interpret primary data more insightfully Criteria for Evaluating Secondary Data Specifications: Methodology Used to Collect the Data Error: Accuracy of the Data Currency: When the Data Were Collected Objective(s): The Purpose for Which the Data Were Collected Nature: The Content of the Data Dependability: Overall, How Dependable Are the Data Criteria for Evaluating Secondary Data A Classification of Secondary Data Internal Secondary Data Department Store Project Sales were analyzed to obtain: Sales by product line Sales by major department (e.g., men's wear, house wares) Sales by specific stores Sales by geographical region

Sales Sales Sales Sales

by cash versus credit purchases in specific time periods by size of purchase trends in many of these classifications were also examined.

Type of Individual/Household Level Data Available from Syndicated Firms Type of Individual/Household Level Data Available from Syndicated Firms A Classification of Published Secondary Sources A Classification of Computerized Databases Published External Secondary Sources Guides An excellent source of standard or recurring information Helpful in identifying other important sources of directories, trade associations, and trade publications One of the first sources a researcher should consult Directories Helpful for identifying individuals or organizations that collect specific data Examples: Consultants and Consulting Organizations Directory, Encyclopedia of Associations, FINDEX: The Directory of Market Research Reports, Studies and Surveys, and Research Services Directory Indices Helpful in locating information on a particular topic in several different publications Classification of Computerized Databases Bibliographic databases are composed of citations to articles. Numeric databases contain numerical and statistical information. Full-text databases contain the complete text of the source documents comprising the database. Directory databases provide information on individuals, organizations, and services. Special-purpose databases provide specialized information. Syndicated Services Companies that collect and sell common pools of data of known commercial value designed to serve a number of clients. Syndicated sources can be classified based on the unit of measurement (households/consumers or institutions).

Household/consumer data may be obtained from surveys, diary panels, or electronic scanner services. Institutional data may be obtained from retailers, wholesalers, or industrial firms. A Classification of Syndicated Services Syndicated Services: Consumers Syndicated Services: Institutions Overview of Syndicated Services Overview of Syndicated Services Overview of Syndicated Services Single-Source Data Single-source data provide integrated information on household variables, including media consumption and purchases, and marketing variables, such as product sales, price, advertising, promotion, and in-store marketing effort. Recruit a test panel of households and meter each home's TV sets. Survey households periodically on what they read. Grocery purchases are tracked by UPC scanners. Track retail data, such as sales, advertising, and promotion. The NYT on the Web: A New Way To Target Customers The NYT on the Web: A New Way To Target Customers A Classification of International Sources Sampling Techniques Population - total group of respondents that the researcher wants to study. Populations are too costly and time consuming to study in entirety. Sampling Techniques A probability sample is one that gives every member of the population a known chance of being selected. simple random sample - anyone stratified sample - different groups (ages) cluster sample - different areas (cities) All are selected randomly. Sampling Techniques

A non-probability sample is an arbitrary grouping that limits the use of some statistical tests. It is not selected randomly. convenience sample - readily available quota sample - maintain representation Primary Research Methods Focus Groups bring together respondents with common characteristics Observation - actually view respondents Experiment - controlled variables and respondent groups. Non-personal survey on site, telephone, mail, fax, computer, panel Personal interview - one-on-one survey with respondents Company records internal document survey research Constructing the Questionnaire Select the correct types of questions: open ended harder to score but get gricherh information closed ended, dichotomous offer two either/or responses (true/false; yes/no; for/against multiple choice select one or more than one scaled response gather range of gvaluesh (strongly disagree, somewhat disagree, neutral, somewhat agree, strongly agree 1. Have you had any of the following medical preventive tests/exams? _____ mammogram (if a women) _____ prostate exam (if a man) _____ lung x-ray _____ electrocardiogram _____ stress test 2. Do you currently smoke? _____ YES _____ NO Important characteristics of good questionnaires Plan a user-friendly format Gather demographic data age, gender, etc., when necessary. Guarantee anonymity Ensure ease of tabulation Scantron forms Ask well-phrased and unambiguous questions that can be answered Develop for completeness get all the data Pilot test the instrument Assignment

Prepare a questionnaire (word processed on paper) that you utilized to gather the primary data for the formal report case. The questionnaire will be inserted as an appendix at the end of your formal report. Remember, you should include on the survey: an introductory statement about the purpose of the survey, a motivational reason why customers should take it, and a reminder to participants that they are taking the survey anonymously. You should NOT include on the survey: answer percentages Complementary Research Methods Overview Outline relative merits of Triangulation - the integration of both qualitative and quantitative research methodologies Review a variety of research methods:

Experimental design, ethnography, case study, survey methods.

Discuss Nowaczyk and Underwoods (1995) paper. Fundamental Goals... Of Science:

To Understand, To Predict, To Control

Of Scientists: To communicate discoveries and findings to a community of peers

Designing Research Dimensions of Analysis Research Purposes - theoretical or applied? Research Problems - what questions are asked? Research Settings - simulated or natural? Research Investigators - background and training Research Methods - a continuum

Experimental, Ethnography, Case study, Survey

Evaluating Research



A concern for most social scientists is the complex nature of the phenomena under study: human behavior. Multiple perspectives are required in order to adequately reflect the richness of these complexities. Consistency, Replicability Contribution to knowledge Advance THEORY and PRACTICE in discipline

Usefulness or Value of Investigation

Research Methodologies A continuum rather than either/or Qualitative

Goal: To Understand, Predict

Descriptive accounts Similarities and Contrasts Applied and Theoretical Research Questions Field study

Natural conditions Quantitative Goal: To Predict and Control

Measure and Evaluate Generalize to population, reproduction Basic and Theoretical Hypothesis testing Lab study

Controlled, contrived Validity and Reliability Both Quantitative and Qualitative research designs seek reliable and valid results. For example:

Quantitative Reliability: Data that are consistent or stable as indicated by the researcher's ability to replicate the findings. Qualitative: Validity of findings are paramount so that data are

representative of a true and full picture of constructs under investigation. Part Versus Whole Whole is often greater than Parts It is a non-trivial matter to infer the behavior of the whole from the behavior of its parts

Quantitative research designs strive to identify and isolate specific variables within the context (seeking correlation, relationships, causality) of the study. Qualitative design focuses on a holistic view of what is being studied

(via documents, case histories, observations and interviews). Data Collection Quantitative Emphasis on numerical data, measurable variables Data is collected under controlled conditions in order to rule out the

possibility that variables other than the one under study can account for the relationships identified Qualitative Emphasis on observation and interpretation. Data are collected within the context of their natural occurrence.

Static and Dynamic Quantitative The accumulation of facts and causes of behavior through careful isolation, measurement and evaluation of variables.

Predictability and Control over time.

Qualitative Concerned with the changing and dynamic nature of reality. Understanding a Point in time

Triangulation Combines independent yet complementary research methods.

Simultaneous triangulation:

Use of both qualitative and quantitative methods at the same time e.g., Survey methods and Case study

Sequential triangulation:

Results of one method are essential for planning the next method e.g., Exploratory Pilot study precedes Experimental design

Also known as mixed methods Benefits of Triangulation Advantages of each complement the other

resulting in a stronger research design, and more valid and reliable findings.

Inadequacies of individual methods are minimized

threats to Internal Validity are realized and addressed

Example Quantitative design strives to control for bias so that facts, instances, phenomena can be understood in an objective way.

Qualitative approach strives to understand the perspective of participants or a situation by looking at firsthand experience to provide meaningful data.

Additional Benefits Triangulation offers a balance between logic and stories. Qualititative research, which emphasizes exploration, understanding, contextualizing, introspection, and theory construction, provides a strong base for wider quantitative measures, scaling, and generalization. Quantitative research, which emphasizes large samples, can provide an overview of an area that can reveal patterns, inconsistencies, and so forth, that can be further investigated with qualitative methods.

Effectiveness of Triangulation In order for Triangulation to be used effectively, four principles must be adhered to:

1. research question(s) must be clearly focused; 2. strengths and weaknesses of each chosen method must complement each other; 3. data collection methods should be selected according to their relevance to the nature of the phenomenon being studied; 4. a continual evaluation of the approach should be under-taken during the study.

Validity and Reliability There are many different stories to be told

Different researchers have different questions to answer, different conceptualizations of the situation, and set different boundaries for the case

Generalizability: What is true of one case is often true about other cases

Consistencies can be found - predictability How many cases are needed before patterns emerge? It depends...

Survey Research Methods Purpose and Goal

Describe specific characteristics of a large group of persons, objects, or institutions Understand present conditions, rather than the effects of particular intervention (as in experimental research)

Sample of Population

Groups of interest are well defined and chosen using well defined rules Representativeness

Survey Methods Mail

postage and printing costs, participation rate

Telephone sampling, wage and time costs, participation rates


wage and time costs, participation rates, like structured interview

Web-based anytime, anywhere, cost effective

Issues in Survey Construction Item (question) and scale construction Pilot Testing and revision Sampling procedures Analysis and reporting of results Generalizability

Drawing conclusions about the conditions, attitudes, opinions, or status of a population of persons, objects, institutions, or other entities.

Nowaczyk and Underwood (1995) http://epaa.asu.edu/epaa/v3n20.html "Possible Indicators of Research Quality for Colleges and Universities"

Used qualitative method, focus group, to investigate research quality in higher education

Results Academics promoted the use of both quantitative and qualitative measures to report on quality


Journal publications, conference presentations, books and book chapters, awards, grants, budget, and so on


Reputation of publication, reputation of granting agency, quality of conference, peer reviews of research programs, Quality of institutions that hire graduate students Societal benefit of research

Questionnaire Construction Introduction Questionnaires play a major role in virtually every research study you read, but are often not given the same attention in development that the test, instruments, interventions, interviews, or observations that the questionnaire will be used to explain. Survey:Test::Questionnaire:Form Questionnaires, like tests, should Have a clear purpose or construct(s) Avoid construct irrelevant variance Cover only necessary material but is comprehensive Be valid and reliable Be simple in terms of interface/presentation Be appropriate for the population Content can the respondent answer Language will the respondent understand Be efficient in gathering information Writing Individual Questions Will the population being surveyed be Able to understand the question Readability Vocabulary Able to answer the question Direct knowledge Privacy Willing to answer honestly

Bothered by the content

The question stem should be Clear, so the answer could be given without the answer options present (for multiple choice) Unambiguous, only one interpretation Direct, use as few words as needed Simple, keep directions for answering the question The answer options should be Direct, use as few words as needed Comprehensive, so the respondent can find a reasonable answer Avoid compound answers where a person could reasonably have one piece but not the other Logically ordered Best clear hierarchy to answer options Next best - alphabetical Different ways to get at the same information I attend class everyday : Yes/No Literal interpretation if not 100% attendance the accurate answer is No I try to attend class everyday : Yes/No Intent is not the same as actions How often do you miss class : Never, Rarely, Sometimes, Often, Always Different interpretations of categories, also not linear Writing Individual Questions Different ways to get at the same information

How many times have you missed class :


0, 1-2, 3-5, 6-10, 11 or

By having categories, locked into those breakouts

How many times have you missed class : _____ By making open-ended, can group after data is collected; but data
entry is more difficult

Obtain actual attendance records from college Most accurate, but requires matching of data and additional

Negatively or reverse worded questions

May make understanding the question more difficult I disagree with not allowing a calculator on the test Strongly Agree with a positive statement is not the same as Strongly
Disagree with a negative statement

I am healthy / I am unhealthy

Demographic and background questions

What to ask Only ask background questions that have a clear use in the analysis Only ask for personally identifying information if needed for
matching of data or for follow-ups

Where to place them If placed first, may impact some responses

Sampling Theory and Methods


Census Sampling Error

Developing a Sampling Plan Define the Population of Interest Identify a Sampling Frame (if possible) Select a Sampling Method Determine Sample Size Execute the Sampling Plan Defining Population of Interest Population of interest is entirely dependent on Management Problem, Research Problems, and Research Design. Some Bases for Defining Population:

Geographic Area Demographics Usage/Lifestyle Awareness

Sampling Frame A list of population elements (people, companies, houses, cities, etc.) from which units to be sampled can be selected. Difficult to get an accurate list. Sample frame error occurs when certain elements of the population are accidentally omitted or not included on the list. Sampling Methods

Types of Sampling Methods


Simple random sampling Systematic random sampling Stratified random sampling

Cluster sampling Nonprobability

Convenience sampling Judgment sampling Quota sampling Snowball sampling

Simple Random Sampling Systematic Random Sampling Steps in Drawing a Systematic Random Sample

1: Obtain a list of units that contains an acceptable frame of the target population 2: Determine the number of units in the list and the desired sample size 3: Compute the skip interval 4: Determine a random start point 5: Beginning at the start point, select the units by choosing each unit that corresponds to the skip interval

Stratified Random Sampling Steps in Drawing a Stratified Random Sample

1: Divide the target population into homogeneous subgroups or strata 2: Draw random samples fro each stratum 3: Combine the samples from each stratum into a single sample of the target population

Nonprobability Sampling Methods Factors to Consider in Sample Design

Determining Sample Size How many completed questionnaires do we need to have a representative sample? Generally the larger the better, but that takes more time and money. Answer depends on:

How different or dispersed the population is. Desired level of confidence. Desired degree of accuracy.

Common Methods for Determining Sample Size

Common Methods:

Budget/time available Executive decision Statistical methods Historical data/guidelines

Factors Affecting Sample Size for Probability Designs

Variability of the population characteristic under investigation Level of confidence desired in the estimate Degree of precision desired in estimating the population characteristic