Descriptive and Stats interpretation.
lken82
hm_assignment.docxDescriptive Statistics and Interpretation
Create a Microsoft® Excel® spreadsheet with the two variables from your learning team's dataset.
Analyze the data with MegaStat®, StatCrunch®, Microsoft® Excel®or other statistical tool(s), including:
(a) Descriptive stats for each numeric variable
(b) Histogram for each numeric variable
(c) Bar chart for each attribute (non numeric) variable
(d) Scatter plot if the data contains two numeric variables
Determine the appropriate descriptive statistics.
(a) For normally distributed data use the mean and standard deviation.
(b) For significantly skewed data use the median and interquartile range.
Use the Individual Methodology Findings Template to complete the descriptive statistics. Use the Descriptive Statistics and Interpretation Example to develop an interpretation of the descriptive statistics.
Format your paper consistent with APA guidelines.
Submit both the spreadsheet and the completed Individual Methodology Findings Template.
Here are the 3 papers from my team you need to use to populate the spreadsheet and the Individual Methodology Findings
Week 3: Random Sampling Plan
LEARNING TEAM REFLECTION 4
Random Sampling Plan
Pierre Lane
Applied Business Research & Statistics/561
February 21, 2015
Louis Daily
Abstract
This paper will focus on the electrical resident of the state of Alabama, and more specifically the customer of Alabama Power. We will pay close attention to the square footage of the target population’s home square footage and the amount of electricity consumed on an annual basis to determine it the average home size in the stated determines the amount of electricity consumed by the average resident. The paper will also focus on the collecting and analyzing sampling methods used to arrive at a decision on square footage and its effect on energy consumption.
Variables
Independent – square footage of a home
Dependent – electricity usage of a home
Target Population and Population Size
For the purpose of this paper to outline the random sampling population size and target population we will included all 2.08 MM Alabama Power residential customers. We will only use residential customers that have at least one consecutive year of usage data available in the company historical databases. This is to ensure that the residential data used is the most accurate and a true representation of energy consumption used in homes relative to their square footage. This data will be mined using both Microsoft Excel an Access. All residential customer data from Alabama power will be analyzed and exclusion parameters will be set after the data is pulled but before analysis has commenced. We will then take this information and overlap it with the residential home size for residential customers that we pulled from the state’s records of county tax assessors property value files. There will be twelve samples taken using this information. Essential we will conduct the samples on a monthly basis. These two critical pieces of information along with the twelve samples sizes will provide everything that is needed to analyze both the residential customer’s annual power consumption and the residential home sizes of those same customers.
Data Validity, Reliability, and Integrity
Since the sample data will originate from the actual energy consumption records that actual residential customers used, and we will take into account all of the data points that are available. The data reliability will be incredibly strong, and valid due to it being previous year’s data and not data from, let’s say 10 years ago. Being that the data is relatively current, the use of current customer’s names and addresses will not be included in the actual data pull of energy customers or their tax records. We will analyze the consumption amounts of all residential power customers with that have one continuous year of consumption history on a monthly basis in every Alabama County. The integrity of this data will remain intact due to its use only for this sampling plan. There will be no outside parties permitted to analyze this information other than the team members and the company employees used to access the information.
Data Collection and Storage
Data will be collected from both Alabama Power and the State’s division of The Tax Assessors office by both written and verbal request. The information will be emailed via a compressed zip drive from both entities and stored on a secure hard drive. Being that there will be no account number, personal information, and information traceable to that actual residents, this is minimal chance that personal information of the sample population will be compromised.
Reference
Alabama Power Fact Card. (n.d.). Retrieved February 23, 2015, from http://www.alabamapower.com/about-us/pdf/factcard.pdf
|
|
|
|
|
|
|
|
|
Population and size
week 3 qnt 561.docx
Sampling and Data Collection Plan
Ariel Smith
|
Running head: Sampling and Data Collection Plan |
1
|
|
Sampling and Data Collection Plan |
6
|
Louis Daily
Population and size
Company C is located in Alabama. Company C provides the valuable combination of competitive prices, reliable electricity supply and unparalleled service to 1.4 million homes, businesses and industries in the southern two-thirds of Alabama. My research will focus on the Montgomery County area (population of 201,332). My research sample size will be 384.
The target population and brief reasoning
My research will focus on Montgomery County, which is the capital of the city. Because Montgomery is the capital of the state this data will provide general information about the state as a whole. This will give a general aspect of how much electricity is used in the state of Alabama. A survey will be conducted at consumers home[footnoteRef:1]. The survey will consist of 8 questions, which will be based on electricity usage. The data collected on the survey will be used to decrease the amount of electricity usage in residential homes. [1: Survey is located in appendix.]
Method
The type of random sampling that would be best to use for this research is stratified sampling. This sampling method puts the population into groups based on a factor that may influence the variable that is being measured. For my case the factor that my group will be based on is being consumers of Company C. Stratification generally produces more precise estimates of the population percent’s than estimates that would be found from a simple random sample as well as reduces sampling error.
Validity
Validity is concerned with the accuracy of our measurement, and it often affects survey data. There is three types of validity that I will ensure are incorporated into my survey: content, internal and external validity. Content validity related to our ability to create questions that reflect the issue we are researching and make sure that key related subjects are not excluded. Internal validity asks whether the questions we pose can really explain the outcome we want to research. External validity refers to the extend in which the results can be generalized to the target population the survey sample is representing. To ensure my survey is valid it must meet the following requirements:
1. Be detailed
2. Be clear
3. Responses to survey must be consistent
4. All question must be related to research topic
Privacy
All participants will be asked to complete survey without producing a name. Respondents will be assigned a number. The number will correlate with data taken from each survey. The data will than be put into SPSS system (statistical software used for analysis) where it will be stored until further use. I will be the only one with access to the data.
Data Collection
The data will be collected over a 3-month period; in case there is a need to revisit home because participants was not there. In that time I will go door to door administering the survey. After every day, the data collected will be put into the SPSS system until the data of the 2000 participants are collected. At that time all data collected will be analyzed and report will be completed.
Calculation
The formula general used to calculate sample size is:
A 95% degree confidence corresponds to = 0.05. Each of the shaded tails in the following figure has an area of
= 0.025. The region to the left of
and to the right of
= 0 is 0.5 – 0.025, or 0.475 (Six Sigma, 2014). In the table of the standard normal (
) distribution, an area of 0.475 corresponds to a
value of 1.96. The critical value is therefore
= 1.96. (Six Sigma, 2014)
Because the populations is 201,332, the margin or error is 5% at a 95% confidence level the minimum recommended size for my survey would be 384. If I were to create a sample of this many people and get responses from everyone, I am more likely to get a correct answer than I would from a large sample where only a small percentage of the sample responds to my survey.
Appendix
Electricity Usage
Number______
Address_________________________
_________________________
1. How many people live in household? _________________
2. What is the annual income of household? ________________
3. How much is your monthly bill? ______________
4. What is the total square ft. of your home?______________
5. Do you believe that the amount of electricity usage is affected by the size of your home? ______________
6. Do you keep your lights on even when you are not in the room?___________
7. Do you consistently leave air condition on during the summer time?____________
8. Do you consistently leave heater on during the winter time?________
Reference
Six Sigma. (2014). Retrieved from http://www.isixsigma.com/tools-templates/sampling-data/how-determine-sample-size-determining-sample-size/
Week 3: Random Sampling Plan
LEARNING TEAM REFLECTION 4
Random Sampling Plan
Pierre Lane
Applied Business Research & Statistics/561
February 21, 2015
Louis Daily
Abstract
This paper will focus on the electrical resident of the state of Alabama, and more specifically the customer of Alabama Power. We will pay close attention to the square footage of the target population’s home square footage and the amount of electricity consumed on an annual basis to determine it the average home size in the stated determines the amount of electricity consumed by the average resident. The paper will also focus on the collecting and analyzing sampling methods used to arrive at a decision on square footage and its effect on energy consumption.
Variables
Independent – square footage of a home
Dependent – electricity usage of a home
Target Population and Population Size
For the purpose of this paper to outline the random sampling population size and target population we will included all 2.08 MM Alabama Power residential customers. We will only use residential customers that have at least one consecutive year of usage data available in the company historical databases. This is to ensure that the residential data used is the most accurate and a true representation of energy consumption used in homes relative to their square footage. This data will be mined using both Microsoft Excel an Access. All residential customer data from Alabama power will be analyzed and exclusion parameters will be set after the data is pulled but before analysis has commenced. We will then take this information and overlap it with the residential home size for residential customers that we pulled from the state’s records of county tax assessors property value files. There will be twelve samples taken using this information. Essential we will conduct the samples on a monthly basis. These two critical pieces of information along with the twelve samples sizes will provide everything that is needed to analyze both the residential customer’s annual power consumption and the residential home sizes of those same customers.
Data Validity, Reliability, and Integrity
Since the sample data will originate from the actual energy consumption records that actual residential customers used, and we will take into account all of the data points that are available. The data reliability will be incredibly strong, and valid due to it being previous year’s data and not data from, let’s say 10 years ago. Being that the data is relatively current, the use of current customer’s names and addresses will not be included in the actual data pull of energy customers or their tax records. We will analyze the consumption amounts of all residential power customers with that have one continuous year of consumption history on a monthly basis in every Alabama County. The integrity of this data will remain intact due to its use only for this sampling plan. There will be no outside parties permitted to analyze this information other than the team members and the company employees used to access the information.
Data Collection and Storage
Data will be collected from both Alabama Power and the State’s division of The Tax Assessors office by both written and verbal request. The information will be emailed via a compressed zip drive from both entities and stored on a secure hard drive. Being that there will be no account number, personal information, and information traceable to that actual residents, this is minimal chance that personal information of the sample population will be compromised.
Reference
Alabama Power Fact Card. (n.d.). Retrieved February 23, 2015, from http://www.alabamapower.com/about-us/pdf/factcard.pdf
|
|
|
|
|
|
|
|
|
individual_method
ology_findings_template_week4.doc
|
SHORT TITLE OF PAPER |
1 |
|
Running head: DESCRIPTIVE STATISTICS |
1 |
Descriptive Statistics
Name
QNT/561
Date
Instructor’s Name
Descriptive Statistics
Determine the appropriate descriptive statistics.
Note: If the data was normally distributed, use the mean and standard deviation. If the data was skewed significantly, use the median and interquartile range.
Numeric Variable Name1
Distribution: State if not normally distributed
|
Central Tendency: |
|
Dispersion: |
|
Number: |
|
Min/Max: |
|
Confidence Interval: (if distribution is normal) |
Numeric Variable Name2 (if applicable)
Distribution: State if not normally distributed
|
Central Tendency: |
|
Dispersion: |
|
Number: |
|
Min/Max: |
|
Confidence Interval: (if distribution is normal) |
Attribute Variable Name (if applicable)
Create a bar chart. Describe the proportions.
Descriptive Statistics Interpretation
Numeric Variable Name1
Describe the variable in laymen terms.
Numeric Variable Name2 (if applicable)
Describe the variable in laymen terms.
Appendix A
Raw data used in the analysis
Fit data to one page.
Appendix B
Charts and Tables
This part of the paper will include items that are then cited in the body of the paper. Usually, large items are placed here not to distract from reading the paper.
Appendix C
Descriptive Statistics
This part of the paper will include descriptive statistics.
descriptive_statistic
s_and_interpretation_example_week4.doc
|
Descriptive Statistics and Interpretation Example QNT/561 Version 7 |
1 |
University of Phoenix Material
Descriptive Statistics and Interpretation Example
Interpretation Phrases
Central Tendency:
Mean = average of a set of data
Median = half or equal number of data is above and half or equal number of data is below. It is a midpoint in an ordered (sorted) set of data, a physical location
Mode = most frequent value in a set of data
Dispersion:
Standard deviation = variation
Interquartile range (IQR) = the middle 50% of the data
Range = the difference between the largest and smallest value of the data
Confidence Interval: (data must be normal)
There is 95% confidence that the population average is between _____ and ____ units.
Normal or significantly skewed data:
MegaStat: Descriptive statistics Normal curve goodness of fit p-value
· Normal, p-value > .05
· Significantly Skewed, p-value < .05
Histogram: Eyeball the histogram.
· Normal data will have a symmetrical or slightly skewed shape.
· Significantly Skewed shape will have extreme skewness
Use phrase combinations: Normally distributed: Mean and Standard Deviation, Not normally distributed: Median and IQR
Descriptive Statistics
Body Weight (Lbs.)
|
Central Tendency: |
Mean = 149 Lbs. |
|
Dispersion: |
Standard deviation = 30 Lbs. |
|
Count: |
100 |
|
Min/Max: |
99 pounds and 234 Lbs. |
|
Confidence Interval: |
144 to 155 Lbs. |
See the histogram in Appendix A, and descriptive statistics in Appendix B.
Age
Distribution is not normally distributed
|
Central Tendency: |
Median = 36 years |
|
Dispersion: |
Interquartile Range = 20.5 years / 2 = ± 10 years |
|
Count: |
100 |
|
Min/Max: |
18 years and 74 years |
|
Confidence Interval: |
Not applicable (data is not normally distributed) |
See the histogram in Appendix A, and descriptive statistics in Appendix B. A scatter plot is in Appendix C.
Education Level
Thirteen percent of the subjects have no high school degree while 44% have high school degree. Forty three percent have a college or college graduate degree. See the bar chart in Appendix D.
Descriptive Statistics Interpretation
Interpretation
Body Weight
One hundred subjects were randomly selected. Their body weight was observed between 99 and 234 pounds. Their average weight was 149 pounds, with a variation of plus or minus 30 pounds. One half or more were above 149 pounds. There is 95% confidence that the population body weight average is between 144 and 155 pounds.
Age
The data was significantly skewed. One hundred subjects were randomly selected. Their ages were between 18 and 74 years, with a variation of plus or minus 10 years. One half or more subjects were 36 years of age or older. The middle half of the subjects’ ages fell between 27 and 47 years. The most frequent age was 36 years.
APPENDIX A
Body Weight and Age Histograms
APPENDIX B
Descriptive Statistics Body Weight and Age
APPENDIX C
Scatterplot Body Age versus Weight
APPENDIX D
Bar Chart Education Level
Copyright © 2014 by University of Phoenix. All rights reserved.
Week 3_Week
4Sampling Plan Team Paper_022615.docx
