MKT 343 Exam 3

validation

Determines whether a survey’s interviews or observations were conducted correctly and are free of fraud, bias, or errors

Curbstoning:

Cheating or falsification in the data collection process

validation covers five areas including:

fraud

screening

procedure

completeness

courtesy

editing

Data is checked for mistakes made by the interviewer, respondent, or during data transfer

•By reviewing completed interviews, the researcher can check several areas of concern:

–Asking the proper questions

–Accurate recording of answers

–Correct screening of respondents

–Complete and accurate recording of open-ended questions

Coding

•Grouping and assigning values to various responses from the survey instrument

•Four-step process to coding responses:

–Generate a list of as many potential responses as possible

–Consolidate responses

–Assign a numerical value as a code

–Assign a coded value to each response

•Entering the data into a computer file for analysis:

–That allows the research analyst to manipulate and transform the raw data into useful information

–Scanning technology can be used

–This step is not necessary for online data collection

Data entry involves

–Error detection

–Missing data

–Organizing data

error detection

•Identifies errors from data entry or other sources

Error Detection Approaches include:

–Determine if the software used will allow the user to perform “error edit routines”

–Review a printed representation of the entered data

–Run a tabulation of all survey questions so responses can be examined for completeness and accuracy

Missing Data

–Replace missing value with a value from a similar respondent

–Use answers to the other similar questions as a guide in determining the replacement value

–Use mean of a subsample of the respondents with similar characteristics that answered the question to determine a  replacement value

–Use mean of the entire sample that answered the question as a replacement value

•Not recommended as it reduces overall variance in the question

Data Tabulation

•Counting the number of observations (cases) that are classified into certain categories (frequency count)

–One-way tabulation:

Categorization of single variables existing in a study

–Cross-tabulation:

Simultaneously treating two or more variables in the study

•Categorizing the number of respondents who have answered two or more questions consecutively

One-Way Tabulation Purpose:

–Determine the amount of nonresponse to individual questions

–Locate mistakes in data entry

–Communicate the results of the research project

•Illustrated by constructing a one-way frequency table

One Way Tabulation reviewing the output look for:

–Indications of missing data

–Determining valid percentages

–Summary statistics (not included in one-way table)

•Run “descriptives” for mean, median, mode, standard deviation

Descriptive Statistics

•Used to summarize and describe the data obtained from a sample of respondents

•Measures used to describe data:

–Central tendency

–Dispersion

•These are described in more detail next chapter

Graphical Illustration Data

•Next step following development of frequency tables is to translate them into graphical illustrations

Statistical Analysis

•Every set of data collected needs some summary information developed that describes the numbers it contains

–Central tendency and dispersion

–Relationships of the sample data

–Hypothesis testing

Measures of central tendency include:

mean, median, mode

mean

••The arithmetic average of the sample

••All values of a distribution of responses are summed and divided by the number of valid responses

Median

••The middle value of a rank-ordered distribution

••Exactly half of the responses are above and half are below the median value

Mode

••The most common value in the set of responses to a question

••The response most often given to a question

range

••The distance between the smallest and largest values in a set of responses

standard deviation

••The average distance of the distribution values from the mean

variance

••The average squared deviation about the mean of a distribution of values

•Considerations that influence the choice of a particular technique:

•particular technique:

–Number of variables

–Scale of measurement

–Parametric versus nonparametric statistics

Univariate Statistical Tests

•Used to test hypotheses when the researcher wishes to test a proposition about a sample characteristic against a known or given standard

Bivariate Statistical Tests

•Test hypotheses that compare the characteristics of two groups or two variables

•Three types of bivariate hypothesis tests: Chi-Square(Nominal/categorical) , t-test(2 means), Analysis of variance (3 or more means)

•t-test:

A hypothesis test that utilizes the t distribution

–Especially useful when the sample size is smaller than 30 and the standard deviation is unknown

Analysis of Variance (ANOVA)

•A statistical technique that determines whether three or more means are statistically different from one another

•Null hypothesis for ANOVA always states  that there is no difference between the dependent variable group

•F-test:

The test used to statistically evaluate the differences between the group means in ANOVA

•Follow-up tests:

A test that flags the means that are statistically different from each other

–Performed after an ANOVA determines there are differences between means

Perceptual Mapping

•Used to develop maps showing the perceptions of respondents

–Maps are visual representations of respondents’ perceptions of a company, product, service, brand, or any other object in two dimensions

•Approaches used to develop perceptual maps

–Rankings

–Medians

–Mean ratings

Perceptual Mapping Applications in Marketing Research

•New-product development

•Image measurement

•Advertising

•Distribution

Examining Relationships between Variables

•Relationships between variables can be described through:

–Presence

–Direction

–Strength of association

No, weak, moderate, strong relationship

•Linear relationship:

The strength and nature of the relationship remains the same over the range of both variables

•Curvilinear relationship:

The strength and/or direction of their relationship changes over the range of both variables

•Covariation:

The amount of change in one variable that is consistently related to the change in another variable of interest

–Scatter diagram:

A graphic plot of the relative position of two variables using a horizontal and a vertical axis to represent the values of the respective variables

•A way of visually describing the covariation between two variables

•Pearson correlation coefficient:

Statistical measure of the strength of a linear relationship between two metric variables

–Varies between – 1.00 and 1.00

•0 represents absolutely no association

•– 1.00 or 1.00 represent a perfect link

Assumptions for Calculating
Pearson’s Correlation Coefficient

•The two variables have been measured using interval- or ratio-scaled measures

•Nature of the relationship is linear

–A straight line describes the relationship

Variables to be analyzed need to be from a normally distributed population

What if the Correlation is weak?

•Either:

1.There is no significant relationship present,

  OR

2.The relationship is not linear

–So, if you are pretty sure a relationship exists, you will have to run additional analyses (e.g., curvilinear regression)

•Coefficient of determination (r²):

A number measuring the proportion of variation in one variable accounted for by another

–Can be thought of as a percentage and varies from 0.0 to 1.00

–The larger the size of the coefficient of determination, the stronger the linear relationship between the two variables being examined

What is Regression Analysis?

•A method for arriving at more detailed answers (predictions) than can be provided by the correlation coefficient

•A number of ways to make such predictions:

–Extrapolation from past behavior of the variable

–Simple guesses

–Use of a regression equation that includes information about related variables to assist in the prediction

•Bivariate regression analysis:

A statistical technique that uses information about the relationship between an independent (or predictor) variable and a dependent variable to make predictions

ordinary least squares

••A statistical procedure that estimates regression equation coefficients that produce the lowest sum of squared differences between the actual and predicted values of the dependent variable

Regression Coefficient

••An indicator of the importance of an independent variable in predicting a dependent variable

••Large coefficients are good predictors and small coefficients are weak predictors

Multiple Regression Analysis

•Analyzes the linear relationship between a dependent variable and multiple independent variables by:

–Estimating coefficients for the equation for a straight line

Examining the Statistical Significance
of Each Coefficient

•Each regression coefficient is divided by its standard error to produce a t statistic

–Which is compared against the critical value to determine whether the null hypothesis can be rejected

•Model F statistic:

Compares the amount of variation in the dependent measure “explained” or associated with the independent variables to the “unexplained” or error variance

–A larger F statistic indicates that the regression model has more explained variance than error variance

–Overall Test, then look at individual IVs

Substantive Significance

•The multiple r² describes the strength of the relationship between all the independent variables and the dependent variable

–The larger the r² measure, the more of the behavior of the dependent measure is associated with the independent measures we are using to predict it

–Usually, it is higher when you have multiple IVs, then in bivariate regression

Steps to evaluate MR results

1.Assess overall model significance(using the F Statistic and its associated probability)

2.Evaluate model R-Square

3.Examine individual regression coefficients (betas) and their t-statistics for significance

4.Compare relative influence of IVs on the DV, based on relative size of betas                   

Multiple regression Assumptions

•Linear Relationship(s)

•Normal distribution

–The shape of the distribution of a variable is equal both above and below the mean

•Multicollinearity

•A situation in which several independent variables are highly correlated with each other

•Can result in difficulty in estimating independent regression coefficients for the correlated variables

Marketing Research Reports

•Objectives

–To effectively communicate the findings of the marketing research project

–To provide interpretations of those findings in the form of sound and logical recommendations

–To establish the credibility of the research project

–To serve as a future reference document for strategic or tactical decisions

Marketing Research Reports are….

•The research report or presentation must establish credibility

credibility

–The quality of a report that is related to its accuracy, believability, and professional organization

•Believability:

The quality of a report that is based on:

–Clear and logical thinking

–Precise expression

–Accurate presentation

•Reports are written to reflect three levels of readers:

–Who will read only the executive summary

–Who will read the summary and the findings

–Who will read the entire report and appendix

Format for Marketing Research Reports

•Title page

•Table of contents

•Executive summary

–Research objectives

–Concise statement of method

–Summary of key findings

–Conclusion and recommendations

•Introduction

•Literature Review

•Hypotheses

•Research method and procedures

•Data analysis and findings

•Conclusions and recommendations

•Limitations

•Appendixes

Title Page

•Subject of the report

•Date

•Name, position, and organization of the recipient

•Any numbers/phrases to designate a particular department or division

•Name, position, organization, contact information of the researcher

Executive Summary

•Arguably, the most important section

•Must be complete enough to provide a true representation of the document but in summary form

•Purposes:

–Convey how/why the research was undertaken

–Summarize key findings

–Suggest future actions

•Comes near the front, but should be written last!

Introduction

•Contains background information necessary for a complete understanding of the report

•Communicates:

–Definition of terms

–Relevant background information

–The study’s scope and emphasis

Research Methods and Procedures

•How the research was conducted

•Issues addressed:

–Research design used

–Types of secondary data included

–Procedure used to collect primary data, if any

–Sample and sampling processes

•Remember your audience!

Data Analysis and Findings

•Body of the marketing research report consists of the study’s findings

•Present & Interpret! (again, remember your audience)

•Presentation of findings will be different for each project because data analysis requirements differ for each project

–Report results through tables, bar charts, or pie charts

–Use visuals liberally to complement text

Limitations

•Weaknesses in research methodology that might affect confidence in research conclusions

•All research has limitations!

•Limitations of marketing research include:

–Sampling bias

–Financial constraints

–Time pressures

–Measurement error

Appendix

•A section following the main body of the report

–Used to house complex, detailed, or technical information

–(e.g., scales used)

Common Problems in preparing the marketing research report

1.Lack of data interpretation

2.Unnecessary use of complex statistics

3.Emphasis on packaging instead of quality

4.Lack of relevance

5.Placing too much emphasis on a few statistics

guidelines for preparing oral presentations

1.Visual component should not detract from the information being communicated

2.Be friendly, honest, warm, and open

3.Delivery should be knowledgeable and confident

4.Have a well-organized and inspiring dialogue

5.Be an effective active listener

Professional ≠ Boring!