Practical Exam

Upload (2.5 points)

Add your name to the Excel filename (as the first part of the filename) and submit the completed file.

Upload (2.5 points)

Add your name to the JMP filename (as the first part of the filename) and submit the completed file, including scripts for all of your actions for this section (B).

Upload (2.5 points)

Add your name to the JMP filename (as the first part of the filename) and submit the completed file, including scripts for all of your actions in this section (C).

Upload (2.5 points)

Add your name to the JMP filename (as the first part of the filename) and submit the completed file, including scripts for all of your actions in this section (D).

Married

Based on a standard least square regression analysis (assuming 5% margin of error) which of the following variables are NOT significantly influencing the variable 'Loan Amount' in the loan application process? Married Education Loan Amount Term Applicant's Income

You reject the null hypothesis and confirm that the means are same

Based on the appropriate statistical test, do you believe that mean SAT scores are different for different categories of tests (with a 5% margin of error)? Which of the following statements is true? You reject the null hypothesis and confirm that the means are same You could not reject the null hypothesis You reject the null hypothesis and confirm at least one of the means is different from the other You could not conclude anything

Mathematics is significantly different from Critical reading

Based on the interpretation of the analysis, identify which categories of mean SAT scores are significantly different. Group of answer choices Mathematics is significantly different from Writing Writing is significantly different from Critical Reading Mathematics is significantly different from Critical reading Mathematics, Critical Reading and Writing are all significantly different from each other.

We fail to reject the null hypothesis

Based on the test, what can we conclude about the district's total SAT mean score? We reject the null hypothesis We fail to reject the null hypothesis We accept the null hypothesis We do not have enough information to make a judgement on the null hypothesis

Married

Based on your analysis, which of the following variables have the least significant influence in predicting 'Loan Amount' in bank loan applications. Married Co-applicant income Education Loan Amount Term

Upload (15 points)

Create a pivot table on a new sheet to calculate how many schools were in each performance category. Show the outcome in both a table and a pie chart. Screenshot of the 2 new columns (1 screenful is enough), pivot table output, and pie chart output (3 x 5 points). Create a word document (that you will upload here) and paste those screenshot in sequence as follows: 1. Two-column output. 2. Pivot Table output 3. Pie chart output

77

How many schools were in the A category? 43 150 77 116

We accept the null hypothesis

If our null hypothesis for the district mean score is that the mean of total SAT score is more than or equal to 1200, what would you conclude form your statistical test (with an alpha level of 5%)? We reject the null hypothesis We fail to reject the null hypothesis We accept the null hypothesis We do not have enough information to make a judgement on the null hypothesis

Yes, because the root mean square error is high

In your final regression model, is there a concern about multicollinearity effects? Yes No Yes, because the root mean square error is high Cannot be concluded based on available data

Section A

Instructions: Use the following data file for this section Section A-Data [Dataset #1]Preview the document Remember the honor code. In addition to responding to multiple-choice questions, you need to submit an updated data file with your name appended to the front of the filename (e.g. firstname_lastname_filename). Create 2 new columns as follows: The first new column shows the outcome when you calculate the total score for a school as a combination of 'critical reading mean' + 'mathematics mean' + 'writing mean'. The second column will use a vlookup() function to segment the performance of a school according to the following Table: Total score Performance 0-1099 D 1100-1199 C 1200-1399 B 1400+ A

Section D

Instructions: Use the following data file for this section Section-D-Data [Dataset #4] Remember the honor code. You must use JMP Pro to complete the analysis and respond to the questions in this section. In addition to responding to multiple-choice questions, you need to submit an updated data file with your name appended to the front of the filename (e.g. firstname_lastname_filename). For each action that you are asked to do, ensure that you save the script for that action. Question: The loan manager would like to construct a statistical model to understand which one or more of the provided variables influence the amount of the loan requested. This information would help the bank to target those types of customers to promote their products such as a line of credit offer.

Section B

Instructions: Use the following data file for this section. Section-B-Data [Dataset #2] Remember the honor code. You must use JMP Pro to complete the analysis and respond to the questions in this section. In addition to responding to multiple-choice questions, you need to submit an updated data file with your name appended to the front of the filename (e.g. firstname_lastname_filename). For this dataset, create a new column 'Total SAT Score' which is a combination of 'critical reading mean' + 'mathematics mean' + 'writing means'.

Section C

Instructions: Use the following data file for this section: Section-C-Data [Dataset #3] Remember the honor code. You must use JMP Pro to complete the analysis and respond to the questions in this section. In addition to responding to multiple-choice questions, you need to submit an updated data file with your name appended to the front of the filename (e.g. firstname_lastname_filename). For each action that you are asked to do, ensure that you save the script for that action. Question: The local school district is wondering if there is a difference among the 3 categories of the SAT test, critical reading, writing & mathematics. In particular, if the mean scores of each category of SAT test are different.

0.0956

It is generally believed that the mean value of the district's total SAT score distribution is less than or equal to 1200 (the null hypothesis). You seem to disagree. Perform the appropriate test with a 5% margin of error. What is the corresponding p-value? 0.0324 0.0956 0.0478 0.9522

0.170

Perform a multivariate correlation analysis using all the continuous variables in the data. What is the correlation coefficient between 'loan amount' and 'Co-applicant income'? 0.170 0.039 0.551 -0.030

398.6 - 409.9

Perform an appropriate analysis to answer the following question. What is the 95% confidence interval for the mean score (rounded up to the first decimal place) in the critical reading category? 398.3 - 410.2 398.6 - 409.9 391.9 - 403.5 403.5 - 409.9

Upload (5 points)

Perform the appropriate test with a 5% margin of error and take a screenshot. Make sure your name is visible in the screenshot. Upload the screenshot here.

Upload (5 points)

Provide a screenshot of the box plots, and results from oneway ANOVA test.

38.1%

The loan manager would like to gain some understanding of customers who are likely to get their loan application approved. This will enable the branch to develop a strategy to market their product to the right customers. Based on the current data sample, what percentage of the married applicants got their loan approved? 28.2% 71.8% 38.1% 61.9%

1109.00 & 1259.25

What is the 95% confidence interval for the population mean of the total SAT score? 1197.37 & 1232. 38 1109.00 & 1259.25 1747.42 & 1968.25 1101.12 & 1239.45

1215

What is the average (with 0 decimal places) across all schools for the total score? 1233 1215 2115 1287

1214.9

What is the average (with 1 decimal place) across all schools for the total SAT score? 1214.9 174.9 8.9 1170.0

1609

What is the average SAT score for performance category A (0 decimal places)? 1609 1690 1634 1693

Upload (5 points)

What is the regression equation for the final model? Get a screenshot and upload it here.

Multiple linear regression

What kind of statistical test would you perform to answer this question? T-test Simple logistic regression ANOVA Multiple linear regression

Regression

What kind of statistical test would you perform to answer this question? T-test Z-test ANOVA Regression

'Applicant Income' and 'Loan Status'

What would be an example of a dependent and an independent variable respectively in this case? 'Loan Status' and 'Credit history' 'Applicant Income' and 'Loan Amount' 'Loan Amount' and 'Applicant Income' 'Applicant Income' and 'Loan Status'

Means for one-way ANOVA

Which of the following tables from a statistical analysis helps you learn if the mean SAT score of one category is significantly different from the other two categories? Summary of fit Means for one-way ANOVA Connecting Letter Reports Analysis of Variance

A

Which performance category has the least number of schools? A B C D

Adjusted R^2 in "Summary of fit" table

Which value (from the one way ANOVA test) would you use to either reject or not reject a null hypothesis? Adjusted R^2 in "Summary of fit" table Root Mean Square error in "Summary of Fit" table Mean square value in the "Analysis of Variance" table p-value in the "Analysis of Variance" table