Chapters 12, 13, 14, & 15

Planning Issues

planning is important because it will help the validity of the research

In the planning process, the researcher should also prepare for any potential problems

Analytical Software vs Online Research Supplier

availability and familiarity

Analytical Software

custom software for a specific purpose

improvements are expected

voice recognition

"point and shoot"

SPSS

most widely used

offers a full line of data analysis products

SAS

widely used for data anlysis and report writing

Excel

most popular for it's statistical and analytical tools

Microsoft

Online Research Suppliers

expected to grow because of new technologies

outsourcing the research function

benefits > costs?

The Preanalytical Process

Step 1: Data editing

clarity, readability, consistency, and completeness to a set of data

Step 2: Variable development

specifying the variables from the data

Step 3: Data coding

transfering data into numeric codes

Step 4: Error check

the coded data is verified before it's transfered to storage

Step 5: Data structure generation

data structure is finalized for storage

Step 6: Preanalytical computer check

data is prep'd for computer analysis

Step 7: Tabulation

the results are seperated by how they responded

can be used for crosstabulation and statistical purposes

Basic Analytical Framework for Business Research

Nonscientific business research (NSBR)

exploratory

description/ prediction

discovery

Scientific business research (SBR)

description/ prediction

causal

hypothesis testing

Feel Good Store (project)

planning is extremely important

with improper planning we could be

wasting time and resources

developing the wrong conclusion

choosing analytical software or online research will come down to which is the cheapest and easiest to use

SBR would be appropriate because we would want a generalization for the population

Classification by Purpose

SBR can generalize results where NSBR can not

can a discovery be made?

findings could be analyzed with inferential stats and a statistical test of hypothesis

Exploratory Data Analysis

graphical displays

visual displays

frequency tables

bar charts

histograms

box plots

scatterplots

Basic Methods of Assessing Association

Crosstabulation

cross-break

uses categorical data

need the ability to calc percentages

shows whether there is a relationship

Contingency correlation

calcs the strength of the relationship

phi coefficient

range -1 to 1

C range 0 to 1

stronger as it approaches 1

Spearman rank correlation

Kendall tau

the measurement must be ranked for each variable

Pearson's r

summary stat of the strength of the relationship

Basic Methods of Assessing Differences

Chi-square (x^2) test

test of hypothesis for group differences

Z-test for differences in proportions

illustrated by the normal dist curve

divided by the standard error of the mean

t-test for differences in means

mean differences used on interval-scale measures

Feel Good Store (project)

these statistical analysis of the data will be important in order for us to interpret the results

Introduction

complex design structures emerged with the innovation of technology

1. means of analyzing phenomena

2. fitting algebraic models to situations

allow the researcher to examine interactions, dependencies, and commonalities

Selection of a Multivariate Technique

depends on the study and design

Analysis of Dependency

Multivariate anlaysis of variance

MANOVA

examines the effect of a treatment on 2 or more dep var

1. provides more total info

2. takes into consideration that the dep var are correlation somehow

uses general linear model & follows similar assumptions of ANOVA

a more multivariate nrmal dist is used

Multiple discriminant analysis

stat technique

examines the relationship between:

a nominally scaled dep var

& a set of exploratory or ind var

Conjoint analysis

stat technique

concerned with the joint effect of a combin or rank-ordered ind var on a dep var

similar to variance

Covariance structure analysis

causal modeling

researcher specifies the relationships between theoretical constructs and observables

Analysis of Interdependency

Factor analysis

uses a linear approach

follows a series of steps

generate a correlation matrix

1. estimates of communality

2. the # of factors to keep

3. the indeterminacy problem

4. theoretical considerations

only performed for very large samples

Cluster analysis

dimension-free classification procedure

attempts to subdivid or partition a set of different objects, variables, or both into similar groups

Multidimensional scaling

involves the spatial rep of relations among the perceptions and preferences of individuals

Comment on the Techniques

rules for choosing a technique:

1. acknowledge the assumptions

2. know the data characteristics and requirements

3. determine the final use of the outcome info.

Feel Good Store (project)

choosing a technique to fit our study will be important

it should follow the 3 rules in order for the study to be successful

The Nature of Variance Decomposition

variance - the spread of the results

breaking down the variance into explained and error will help the study

the researcher tries to control the error variance

finding relationships is crucial

Linear Models

One-way analysis (ANOVA)

fixed effects model vs. random effects model

mixed effects model

mathematical formulas distinguish: variance/ relationship

ANOVA = analysis of variance

dependant variable is maintained

Two-way analysis of variance (ANOVA)

2 classification variables and 1 dependant variable

interaction effect

more complex than the one-way analysis

Linear regression

Simple linear regression

used to estimate to predict

analyze the change of the dep var by using info on 1 or more ind var

multiple linear regression

>1 independant variable

essentially the same as simple linear regression

used to estimate and to look at the intercorrelation

Covariance

1. remove extraneous variance - increase precision

2. fully understand the differences

ANCOVA

long and complicated

Nonparametric ANOVA

analyze of the difference between:

a dep var that doesn't contain interval properities

an ind var of a categorical nature

Kruskal-Wallis ANOVA

Wilcoxon rank-sum test

Feel Good Store (project)

the formulas outlined in this chapter are going to important when analyzing data