Subject: Statistical Methods and Analysis

Topic: College Registration

Instruction:

Outcomes:

The successful student will be able to:

• Describe the types of data collected in a specific enterprise process
• Identify types of data found in a typical business data set
• Make structured data set for a sample representing a specified enterprise process

1. Make Excel data set for a sample of people or units or Events

A. Your data set will be a sample of people, units or activities related to a specified business function or process. Each group will have a unique topic for which to build there data set.

B. A case is a single row that represents one item in your sample or population.In the example data set, the data set is a sample ofcountries. See the 2^ndcolumn. Eachrowrepresents the data fora country.

C. There must be at least 60 cases or rows of observations.

1. Each row will represent one person, unit, or instance of an activity from your sample or population.
2. Each row will be identified separately by a unique code found in the first column of each row.See column 1 in the sample.

D. There must between 12 to 15 variables, each is a column of data. (If you exceed 15, only the first 15 will be considered. Having less than 12 columns will be penalized.)

1. Each column represents a single variable describing the people, units or activities collected in the sample.
2. A header in the first row of the data set identifies what the variable is.
3. Please continue reading to see what kind of variables/columns are required.

E. The variables (columns) chosen for the data set must include:

i. The first column at the left as anIdentifier.It contains theuniqueidentifying codefor each row. Note in our sample data base, there is a different number for each country inCountry ID which is the first column in the data set.

ii. A column is required for a qualitative, categorical variable where each value provides a description of the cases such as name or product type or type of event.

In our sample data set,Countryis an example of this type of required variable.

iii. At least two columns ofqualitative, categoricalvariables where there is a minimum of three anda maximum of eightdifferent valuesfor the entire set of cases.

These are important variables as they will allow you to create charts using multiple variables required in Part B.

In our sample data set, there are three such variables. In Column 3,Economic Status, Column 5,Gov't Health Spending Levels and in Column 9,Food Safety Risk Levelall have just three different values. You don't have to restrict your variable to three values but the list should be short.

iv. At least three columns of measurable, Quantitative variables. Do not include the units with the numbers in the column of data. Indicate the units in the variable name.For example: Instead of entering a value of 15 kg for a case, your column header will be Weight (kg) and you will enter 15. In our example data set, Column 4,Govt Health Spending (per capita), Column 10,Birth Rate per 1000 Womenand columns 11 through 13 showing life expectancy for males, females and the overall average, are continuous quantitative variables.

v. At least one variable that is a Quantitative with few (8 or less) values.In our example data set, Column 6, theEpidemic Control Index is an example of this type of variable.

vi. Add more variables to complete the 12 to 15 columns of date. Variable types of your own choosing.

2. Once you have your column headers in place, you must populate the data set with at least 60 cases. Please note: You will be graded on thequalityof the cases in your data set:

i. The variables reflect the kind of data that would be collected in the enterprise process you are assigned.

ii. For each case (row), the values are "internally consistent", which means they make sense to be in the same case.

For example, in the sample data set, a "3^rdWorld country" is unlikely to be able to afford High Per Capita spending on health care. Maybe one or two might, but most would not. They would not have high longevity. On the other hand, 1^stworld countries would have values that are different than 3^rdworld countries.

iii. There are very few duplicate cases. Values for continuous variables and combinations of values across a case tend to be different for most cases.

3.In a separate worksheet, beside the worksheet containing your data set, provide documentation for your data set. (See Appendix_B for an example format and content.) Include the following:

a. A paragraph describing the process you were assigned and the item, event or person you are collected the data for

b. A list of your variables and information about them:

i. The name of your variable (column label)

ii. The type of variable it is: Qualitative, Quantitative Discrete or Quantitative Continuous

iii. The range of values for continuous variables or the list of values for discrete variables

iv. An explanation of what the variable represents and how it is represented by its values or range of values.

Sample Provided from Professor

Appendix A: Example Data Set This is the World Health Organization 2012 Longevity Data Set. While it is not a business data set, it is structured in the way yours needs to be. Return to Instructions. The first row displays column headers which are the names of your variables. This data set has 13 variables. You need 15 variables. Each row, a case, is one of the people, units or events in your sample. This data set is studying countries. There is a row for each country. Here there are 15 rows. You need 60 rows. Govt Govt Average Health Country Economic Health Epidemic Epidemic Food Birth Rate Life Average Life Average Spending Spending Control Control Safety Food Safety per 1000 Expectancy Expectancy Life ID Country Status [per capita] Level Index Preparedness Index Risk Level Women (Male] [Female] Expectancy 01 Afghanistan LLDC 10.70 Very low 13 Very Risky 35,30 58 61 02 Algeria LDC 234.40 Very low 10 Very Risky 24.60 70 73 72 03 Andorra DC 2340.60 High 75 73 Very Risky 9.00 79 86 83 04 Antigua & Barbuda LDC 513.60 Low 100 80 Risky 16.60 73 77 75 05 Argentina LDC 688.70 Low 100 60 Safe 16.90 73 75 76 06 Armenia LOC 52.90 Very low 75 100 87 Safe 13.90 67 75 71 07 Australia DC 4108.40 High 100 100 100 Safe 13.30 81 85 Austria DC 4085.10 High 75 100 100 Safe 9.50 78 83 81 09 Bahrain LDC 643.50 LOW 100 70 93 Risky 15.60 76 78 77 10 Bangladesh LLDC 9.00 Very low 75 50 27 Very Risky 20.30 69 71 70K M A B C D E F G H I N O College Registration 2021 Program Student Age Tuition Overall Admission First Admission Genders Group Registration Awarded Campus Bursaries / Cost GPA Identificati Last Name Programs Cost and Categories Name Types Dates Credentials Locations Grants ($) Discounts (Grade on (Years) Books ($) [%) Points) 911589090 Domestic Aaron Frankie Full Time Male 18 10/5/2021 Diploma Accounting 1500.00 3 9832.00 2.22 AW 913458905 Domestic Adiliee Dianella Full Time Other 20 12/16/2021 Diploma Marketing 1100.00 6 9214.00 3.24 914589056 Domestic Andrade Ellenla Part Time Female 23 11/15/2021 Diploma Accounting 1100.00 3 9832.00 3.57 915719207 International Augusta Bill Full Time Other 25 12/10/2021 Diploma Marketing 1500.00 7 34320.00 4 917979509 International Ballmer Hanna Full Time Other 19 8/29/2021 Diploma Marketing 750.00 7 34320.00 4 11/15/2021 Advanced 919109660 Domestic Barbara Anne Full Time Female 20 Diploma Finance 750.00 14748.00 3.84 920239811 International Batto Ed Full Time Male 21 10/20/2021 Diploma Accounting 2300.00 8 34940.00 3.51 11/20/2021 Bachelors 10 922500113 International Belen Carmel Full Time Female 23 Degree Human Resourc 2800,00 10 85808.00 3.85 916849358 Domestic Bogley Kenneth Part Time Male 18 8/30/2021 Diploma Accounting 1000,00 3 9832.00 3.02 11 12 921369962 Domestic Brenden Maryanne Part Time Other 22 8/19/2021 Diploma Marketing 1100.00 6 9214.00 2.06 10/11/2021 Bachelors 13 924760415 International Camee Cheryllee Full Time Female 19 Degree Human Resourc 1500.00 10 85808.00 3.79 927020717 Domestic Cantil Delsis Part Time Other 18 11/25/2021 Diploma Marketing 500,00 6 9214.00 3.38 14 10/28/2021 Bachelors 928150868 International Carag Berg Full Time Male 19 Degree Human Resourc 2000.00 10 85808.00 2.13 15 16 929281019 Domestic Carrieg Lorianne Full Time Female 21 8/8/2021 Diploma Accounting 750.00 3 9832.00 4 Farttler nart TImm Him nal Registration Data Data Set Documentation1 Out of Grade Requirements Comments Each record represents on individual person or unit from the assigned topic population or Lample Each h a unique record reperienting a student in the data wet. Mgets the requirements In terms of the number of records and the number of variables: You have induced sufficient records and variables. 12-15 Variables and a minimum of Co records You are wing Sheridan College as an comple as you are wing the three campuses. The poworch are not representative of the population you are collecting the data from. Even I the data h tailored, the population h has to be memorably repreventative. Sheen that sufficient records exist, each record is a reasonable For commple, 28 of the 60 students are Intern national. Yet nearly 100% of the names are Anglo. Trouble with Anglo names, they description of an individual in the population of sample and the records are gender specific and many names do not match the gender you have indicated. You live tuition and book fees for the year together represent sufficient variability in the population or sample. that are $34,000 . and $89030- that are dignificantly unrealluck. You put buileis programs on the Trafalgar campus where there are none. This is a project and your team has five members. You need to do some work among you in finding out what is monable for a college registration database. WI the required variable types are represented and the number of each hope has been provided: 1" column - unique identifier 2" column . name or type of individual You two name columns are counted as one column as indicated in the topk selection document . At least 2 Qualitativer variables with between $ to S values There are weak as they are randomly avigned. If you look scrow the column, the values aren't always content. Example Is the gender and name indicated earlier. You have problems with your Quant hart Discounts are not offered for tuition which is government regulated. Tuition fees are "discounted" by offering granti, scholarshipi, on campus jobs and student loans. Even if there were discounts, the discount would not apply across all tuition, all books and all spademin fees. So, this variable doesn't work. Take it out of your data . At least > Quantitative variables that measure ddistinctly d Merent set. Tuition fees are the same for all Bush nineis programs but different only for Diploma versus Degree and Domeith versus things about your population International. Even with books induded, they don't swing by $20,000 or more. You need to fix the values for this variable. Your Part Time students would not be paying $15,900 or more for tuition. At best, 75% of students get burwuries or grants and these are matched to GPA which you didn't do. You need to fix this one. You have randomized the swimment of values to your 10 records. You need to think theouch what is seek for each student type you have. 11 Thes are weak and in many orci, they are randomly anticsed. 12 No Tes/No variables. 0.73 Documentation of the data set is complete Generally, wathfactory. OPA explanation is unsathfactory. OFA h a score that has already been earned. You need at least one 13 mother field with this wore to indicate what semesters it greers of from what intitetion. 14 Total The better you do this port of the project, the cooler and faster Port I wil be. 15 16