STAT 1430 Study Guide - Fall 2018, Comprehensive Midterm Notes - Simple Random Sample, Sampling Bias, Response Bias

116 views14 pages
12 Oct 2018
Department
Course
Professor
STAT 1430
MIDTERM EXAM
STUDY GUIDE
Fall 2018
Unlock document

This preview shows pages 1-3 of the document.
Unlock all 14 pages and 3 million more documents.

Already have an account? Log in
Unlock document

This preview shows pages 1-3 of the document.
Unlock all 14 pages and 3 million more documents.

Already have an account? Log in
Lecture 1.1 Survey
1. Method of collecting data
a. Observational studies (part1)
i. Most common observational study: surveys
b. Experiments (part 2)
c. The difference between the two:
i. An observational study just observes and collects data
ii. An experiment intervenes= more involved
2. Main Objective: minimize or avoid bias
a. Bias is the systematic favoritism on behalf of sample or data collected
b. Impact is losing credibility, can’t measure bias
3. Getting Good survey Results
a. Two challenges
i. Select a good sample
ii. Collect good data
b. Selecting a good sample
i. All good samples are random
ii. Random sample
1. Each group of the same size has the same chance of being selected
as the sample
2. Allow no favoritism by the sampler of the sampled (bias)
4. Types of random sampled
a. Simple random sample
b. Stratified random sample
c. Many others
5. Simple random sample
a. Purpose: Examine the entire population as it exists
i. Ex: What percent of all Americans have a certain occupation?
b. Process
i. Gallup poll, random digit dialing
6. Stratified random sample
a. Purpose: Compare subgroups of the population equally
i. Ex: How do people with different occupations feel about the economy?
b. Process
i. Divide the population into subgroups (strata) of interest
ii. Choose a simple random sample from each subgroup
7. Spot/ avoid biased samples
a. A sampling procedure must be used
find more resources at oneclass.com
find more resources at oneclass.com
Unlock document

This preview shows pages 1-3 of the document.
Unlock all 14 pages and 3 million more documents.

Already have an account? Log in
b. The sample must represent the entire population
8. Biased sample: Convenience
a. Choose individuals in the easiest way
i. Ex: going to the oval and asking OSU students for their opinion on tuition
ii. Issue: Sampling procedure is used
1. Sample won’t represent any population
9. Biased sample: Volunteer (self-selected)
a. A call goes out and people enter the study on their own (not sampled)
i. Ex: Call in polls, web surveys
ii. Issue: No sampling procedure used
iii. Sample won’t represent any population
10. Biased sample: Undercoverage
a. A subgroup of the population is excluded from the very beginning
i. Ex: want OSU student opinion on tuition; took a random sample from
dorms
ii. Issue: sampling procedure is used
iii. Can only represent the remaining population without the subgroup
11. Doing a good survey
a. Select a good sample
b. Design a survey that avoids bias
c. Implement your survey to avoid bias
d. Analyze your data properly
12. Design: Question wording
a. The wording of a survey question can affect the results
i. Ex: “Don’t you think sophomores should be able to live off campus?”
1. Can lead to bias
13. Design: Type of survey
a. The type of survey you conduct can affect results
i. Phone survey, door to door, mail
ii. Ex: Landline surveys to get students opinions
14. Implementation: Nonresponses
a. An individual is selected to be in the sample but doesn’t respond to the survey
b. Don’t be fooled by a high number of respondents. Look for a high percentage of
respondents. This is called the response rate
c. Always look for the response rate. If it’s too low, you have to question the results
d. What you can do?
i. Better to select a smaller sample and follow through
ii. Appropriate incentives
15. Implementation: Response bias
find more resources at oneclass.com
find more resources at oneclass.com
Unlock document

This preview shows pages 1-3 of the document.
Unlock all 14 pages and 3 million more documents.

Already have an account? Log in

Get OneClass Grade+

Unlimited access to all notes and study guides.

Grade+All Inclusive
$10 USD/m
You will be charged $120 USD upfront and auto renewed at the end of each cycle. You may cancel anytime under Payment Settings. For more information, see our Terms and Privacy.
Payments are encrypted using 256-bit SSL. Powered by Stripe.