Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
43 Cards in this Set
- Front
- Back
What is a nonprobability sample?
|
A sample that relies of personal judgement
|
|
What are the steps in drawing a sample?
|
Define the Problem
Identify the Sampling Frame Select a Sampling procedure Determine sample size Select sampling elements collect data |
|
convenience sample
|
Accidental Sample
Usually not representative of population |
|
Judgment Sample
|
purposive
representative of pop or offer contributions sought |
|
Quota sample
|
proportional to a certain characteristic
|
|
Types of nonprobability sample
|
Convenience
Judgment Quota |
|
What is a probability sample?
|
each population has a known chance to be included
|
|
Types of probability samples
|
simple random sample
stratified sample cluster sample |
|
simple random sample
|
each chosen randomly and each has = chance of being selected
|
|
Probability Sample
|
does not involve personal judgment
allows computation of sample size |
|
stratified sample
|
groups members into subgroups before selecting independently
|
|
cluster sample
|
divided into groups then selected randomly
|
|
parameter
|
characteristic of a parent or target population
|
|
Statistic
|
Characteristic of measure of a sample
Deals with sample mean and variances |
|
Precision
|
Degree of error in a study
|
|
how does precision relate to determining a sample size
|
the more important the decision, the more precise the information needs to be
|
|
How does precision relate to setting a confidence interval?
|
There is a trade off between them
can specify one but not both |
|
sampling error
|
The difference between the observed values of a variable and the long run average of the observed values
|
|
Non sampling error
|
Error that arises in research and that is not due to sampling
|
|
Examples of non sampling error
(read) |
poorly written research report
poor problem formulation improper design poor methods inadequate sample design improper use of stats poor logic |
|
What is the advantage of taking a sample rather than doing a census?
|
Takes less time
Less money |
|
How would you estimate sigma (population standard deviation) when it is unknown
|
Estimate sigma by:
looking at range (plus/minus 3sigma) Past experience or similar studies Small pretest Conservatively guess |
|
What is systematic random sampling? How is it classified?
|
sampling every kth (from random number table) of the population.
Classified as cluster sampling |
|
What is Probability-Proportional-to-Size (PPS) sampling? Why does each sample member have an equal chance of being selected?
|
PPS is selecting first stage units based on population, and using a fixed number for selecting second stage units.
Each sample has an equal chance of being selected because the two probabilities cancel each other out. |
|
statistical efficiency
|
Measure used to compare sampling plans; the smaller the standard error of estimate the better
|
|
economic efficiency
|
cost per observation
|
|
Overall efficiency
|
Cluster
|
|
Cluster sampling
|
More economically efficient than stratified
|
|
Stratified Sampling
|
More statistically efficient than cluster
|
|
What is area sampling?
|
Form of cluster sampling
areas serve as primary sampling units population is divided one or two stage area sampling |
|
What are the advantage in using (cluster) area sampling?
|
Faster
Cheaper More efficient do not need listing of population to draw sample |
|
When having multiple objectives how do you determine which sample size to use?
|
Most conservative
Most critical variable as large as you can afford |
|
For means what do you do when the population variance is unknown?
|
Use sample variance
|
|
What are the three variances that are relevant in computing confidence intervals?
|
population, sample, sampling distribution
|
|
significance level
|
must be under .05, which equals 95% confidence
Answers if the results happened by chance. |
|
Cramer's V, PHI, Contingency
|
Indicates how strong the relationship is
Under.25 is low .25-.35 is medium over.35 is a strong relationship |
|
What are three ways to determine samples size?
|
Statistically
Type analysis Budget |
|
Calculating %s on contingency tables
|
Calculate %s across the dependent variable
|
|
What are ethical issues in marketing research? What are the main categories to classify these issues?
|
Researcher/Participant
Researcher/Client |
|
Summary
|
Most important part of the report
|
|
What is in a research report?
|
Title Page
Table of Contents Summary Intro Body Conclusions and recommendations Appendix Synopsis |
|
What are some good guidelines when making an oral presentation? How much technical detail should be included?
|
try to appeal to the audience
Too little technical stuff is better than too much |
|
When and how often should graphics be used?
|
Graphics should be used alot
|