Business Finance - Operations Management Two part Assignment
PART 1
Population
Population = entire set of entities
Sample
Sample = subset of the population
Sampling
Population
Sampling is the process by which a researcher selects one or more cases out of some larger grouping for study.
Sample
Sample
4
5
Practice Question:
Which one of this sentence is correct?
Administrators at CSUEB surveyed 100 randomly selected seniors to see how they feel about Pioneer Dining.
The population is all CSUEB seniors; the sample is all of the seniors.
The population is all university seniors in the U.S.; the sample is all CSUEB seniors
The population is all university seniors in the U.S.; the sample is 100 CSUEB seniors
The population is all CSUEB seniors; the sample is 100 CSUEB seniors
Which one of this sentence is correct?
Administrators at CSUEB surveyed 100 randomly selected seniors to see how they feel about Pioneer Dining.
The population is all CSUEB seniors; the sample is all of the seniors.
The population is all university seniors in the U.S.; the sample is all CSUEB seniors
The population is all university seniors in the U.S.; the sample is 100 CSUEB seniors
The population is all CSUEB seniors; the sample is 100 CSUEB seniors
6
Why Sampling?
Population
All possible cases of what we are interested in studying
Feasibility
The whole group is sometimes too large to study everyone
Data quality
Information based on carefully drawn samples can be better than information from an entire group
Why 1000 samples can be more accurate than 10,000 samples some voices is better heard in a smaller sample
Ex) college undergraduate students who are in their 30s
Quality census for example, asking so many questions with relatively less researchers in charge
7
Sampling Frame
A sampling frame is a list of all the items in your population.
Does the sampling frame include all members of the population?
How will you gather sampling frame?
Ex: iPhone users
AppleCare list
iTunes
Access to serial #
Complete list of everyone or everything you want to study
EX) population = people in RST 370, sampling frame =
Population = All the iphone users, sampling frame =
8
PART 2
Sampling Approaches
Probability = every unit in population has the same chance of being chosen for sample
Nonprobability = every unit in population does NOT have the same chance of being chosen for sample
Probability Sampling
No inherent selection bias
Sampling error: an estimate of the extent to which the values of the sample differ from those of the population
Probability sampling = minimizes the sampling error
Good sampling frame is important when collecting probability sampling
Target population – 1,000
Probability of getting in the sample – 1/1,000
Probability Sampling Techniques
Simple random
Systematic random
Stratified random
Area
Simple Random Sampling (SRS)
Each unit of population has equal chance (probability) being selected
How to select …
Each unit pulled “out of the hat”
Computer programs for random selection http://www.randomizer.org/
Table of random numbers
Try to pick 5 States using the simple random sampling
SRS has the lowest sampling error
Systematic Random Sampling
Variation on simple random sampling involves taking every kth unit listed in a sampling frame
First start = randomly chosen
Systematic Sampling Example
Every
5th case
How do we decide K? in Kth people? 1000 / 100 = 10 , K=10
For SRS and systematic random = sampling frame list must exist
Stratified Random Sampling
Stratified sampling involves dividing the population into smaller subgroups, called strata, and then drawing separate random or systematic samples from each of the strata.
Strata ex) gender, school, region
3. Stratified random sampling
15
Stratified Random Sampling
16
Types of Stratified Sampling
Proportionate Sampling:
The size of the sample from each stratum is proportionate to occurrence in the population
Goal is to reduce sampling error
Disproportionate Sampling:
Sufficient proportion is selected from each sample to make statistical comparisons
Goal is to have representative sub-sample for each stratum
Proportionate sampling: the strongest with the reducing sampling error
Why disproportionate? Why we choose this over proportionate?
It could be more accurate when? minority group
17
| Identify sampling technique used | Answer |
| 1. Major concentration divided into four tracks: recreation, sport, tourism, and leisure. Names in all tracks alphabetized and 100 names randomly chosen from the list. | |
| 2. Names of all majors alphabetized. Someone randomly chooses one name on the list to be surveyed. Move down two names from first person chosen, and this person is chosen. Continue this pattern until 111 names chosen. | |
| 3. Name of each major put in paper bag. Person removes one name at a time until 129 names chosen. |
What Kind of Probability Sample?
Stratified random
Systematic random
Simple random
18
Area Sampling
Area sampling is also called “cluster sampling” or “multi-stage sampling.”
Clusters are similar (while strata are different)
Process:
Cluster sampling divides the population area into sections (clusters)
Then randomly selects clusters
Then chooses all the members of those clusters
Cluster Sampling divides the populartion area into sections (clusters) then randomly selects clusters and chooses all the members of those clusters.
19
Activity
Population
?
?
Cluster sample (left side)
Proportionate stratified sampling (right side)
20
Population
Activity
?
?
Disproportionate stratified sample (right)
21
Probability sampling techniques
Summary/review/refresher:
22
How Large a Sample?
How many cases are needed for the research hypotheses?
Precision:
how much error can we accept?
Population homogeneity:
the more variability in the population to be sampled the larger the sample required
Sampling Technique
stratified sampling => smaller sample
area sampling => larger sample
Sampling fraction
23
Sampling fraction = ratio of sample size to population size, stratified case = sample size to strata size
23
PART 3
Nonprobability Samples
Probability of each population element's being included in the sample is unknown
Uses:
No intent to generalize
Qualitative study (small sample size)
Impossible to develop sampling frame
Limitations
Cannot specify representativeness
Degree of sampling error is unknown
25
Non-probability Sampling Types
Convenience sampling (accidental or haphazard sampling)
Volunteer-based sampling => volunteer bias
26
Convenience – sample drawn from the part of the population that is close to hand (e.g., sns, resources around us)
It is often used for pilot study to obtain basic data and trend
Volunteer – participants self select to become part of the study (e.g., call from radio station, or a booth at a rest area)
Limited amount of number
26
Non-probability Sampling Types
Purposive (or judgmental) sampling
Snowball sampling (interactive sampling): rely on interaction of persons to generate sample.
27
Purposive – researcher rely on their own judgement when choosing members of the population to participate in study
Participants with unique or special characteristics, (e.g., age, health status, background, past experience)
Snowball -
27
| Situation | Sampling technique being used |
| 1. Set up tables outside public rest stop and ask people to complete survey. | |
| 2. Form committee of park system’s mid- and upper-level managers to come up with ideas to make park more appealing. | |
| 3. Staff report few young adults (18–21 years) visit their nature centers. You observe a young adult visiting a nature center and ask that person to complete an interview. You also enlist that person to provide you with the name of another young person who he knows visits nature centers in the community. |
Directions: Identify the nonprobability sampling technique being used.
What Kind of Nonprobability Sample?
Volunteer
Purposive
Snowball
28
Non-probability sampling techniques
Summary/review/refresher:
29