Reference no: EM132399195 , Length: word count : 500
SPSS Project : Confidence Interval and Hypotheses Testing
Part 1
If the level of employee satisfaction drops below 0.60 overall, then there is a belief that there may be a serious problem with morale in that department. There have been rumors that the Marketing department (marketing in the data file – there are 10 departments and you are only looking at marketing) may be having just such issues. This project is only calling for the satisfaction level of the Marketing department
(marketing). So, we need to split this whole data set into different files based on the department. To do this:
Click on Data>Split File (near bottom of the list)
Click on “Organize output by groups”.
Then move “Department” on the space below “Groups Based on:”
Click OK.
1. Is satisfaction_level a qualitative/categorical variable OR quantitative variable?
2. What graphical displays are appropriate for this type of variable? Using SPSS, graph 2 different appropriate graphical displays for the employee satisfaction level for the Marketing department (marketing in the data set). Refer to SPSS 1 Project. Copy and paste the two graphs. Make sure you copy and paste the ones for marketing. Remember to resize.
3. Using SPSS, find the appropriate statistics as you have done in SPSS Project 1, needed to describe the employee satisfaction level of the Marketing department. Then copy and paste the table of appropriate statistics here.
4. Using SPSS, test to determine if the mean employee satisfaction level in the Marketing department is less than 0.60. Conduct the appropriate hypothesis test by following steps. Write your answers after every part a - g.
a. Determine the null and alternative hypotheses. Use proper notation as done in the textbook. Is this a one-tailed or two-tailed test?
b. Use a significance level of α = 0.05. (No answer to write here.)
c. List and validate the assumptions of the hypothesis test. Go to the LEARN part of the chapter for hypothesis test appropriate for this problem.
d. Using SPSS: Analyze>Compare Means> One-Sample T-test. Move Satisfaction_Level to the Test Variable window. Then put the value of the parameter you are testing that can be found in letter a, when you defined your null and alternative hypotheses. Then click OK. Copy and paste the 2 output tables here. The table titles are: One-sample Statistics and One- Sample Test. Make sure to copy and paste the marketing tables. The test statistic value is found on the second table (One-Sample Test) under the t column. Write the test statistic value here. ________
e. The P-value can be found in the table “One-Sample Test” under column “Sig. (2-tailed)”. This value is for a two-tailed test. So, if you are doing a one-tailed test, the p-value is half the tabled value. What is the p-value for this test? __________
f. Based on your answer in letter e, decide to reject or fail to reject the null hypothesis. State the conclusion in terms of the original problem (in context). Go to the Announcement page in Canvas on how to write a conclusion.
5. Based on our conclusion from the previous step, what type of error could we have just made (Type I or Type II)? State the practical implications of this error in the context of the problem (from the company’s perspective).
6. What is the 95% confidence interval for the mean satisfaction level of the Marketing department? Look at the second table again, under “95% Confidence Interval of the Difference” you will find two values – Lower and Upper. The 95% confidence interval for the satisfaction level of the Marketing department is found by: Write on the spaces below based on the output table “One-Sample Test”.
(Test Value + Lower, Test value + Upper) → ( ______ + ______ , ______ +______ ) → ( ______ , ______ )
7. Interpret the confidence interval you just found in the context of the problem. Check the Announcement page in Canvas for the template. Write both parts/sentences.
8. Would we arrive at the same conclusion for the hypothesis test in number 4 and the confidence interval for the mean in number 6 no matter what the value of the significance level? Why or why not? Explain.
Part 2
Part 2 would use the whole data set, so let us undo the Split File command we did for Part 1. Go to Data > Split File. Click on the variable in the space below“Group Based on:”(which should be Department) and click the arrow to move it back on the list. Then click on “Analyze all cases, do not create groups” then click OK.
According to the US Bureau of Labor Statistics, there was a 12.4% incidence of workplace injury in 2016 in the private sector. If the workplace accident rate is above 12.4%, the company will increase inspections and implement additional safety training. For this data, is there statistical support to increase inspections and implement additional safety training? Use the entire dataset and the work_accident variable where 0 = no accident and 1 = an accident occurred.
Insert your answers after each question and change the color of the font of your answers to any color except black. READ the problems carefully.
1. Is work_accident a qualitative/categorical variable OR quantitative variable?
2. Based on your answer in number 1 and using SPSS, graphically display the work_accident variable. Copy and paste 2 different types of graphical displays for this type of variable. Refer to SPSS 1 Project.
Remember to resize.
Using SPSS, find the appropriate statistics needed to describe this type of variable. Analyze> Descriptive Statistics>Frequencies. Move the variable work_accident to the Variable(s) window. Click OK. Copy and paste the table of appropriate statistics (frequency and proportion/probabilities) for the work_accident variable here.
3. Conduct the appropriate hypothesis test using the following steps. Write your answers after every part a - g.
a. Determine the null and alternative hypotheses. Is this a one-tailed or two-tailed test?
b. Use a significance level of α = 0.05. (No answer needed here.)
c. List and validate the assumptions of the hypothesis test. Is this a one-tailed or two-tailed test?
d. Identify the appropriate test statistic and calculate the test statistic by hand (using formulas) using the proportion (for 1 = an accident occurred) found in number 2. Remember to change the percent in the tables to decimal form before using them in the formula. Go to the LEARN part of Chapter 10.3 for hypothesis test appropriate for this problem. SHOW WORK. Fill in the spaces below.
FORMULA PLUG-IN VALUES ANSWER
e. Determine the P-value using the z-table.
f. Based on your answer in letter e, decide to reject or fail to reject the null hypothesis. State the conclusion in terms of the original problem (in context). Go to the Announcement page in Canvas on how to write a conclusion.
4. Based on our conclusion from the previous step, what type of error could we have just made (Type I or Type II)? State the practical implications of this error in the context of the problem (from the company’s perspective).
5. Using the formula found in the LEARN part in the book, find the 95% confidence interval for the proportion of incidence of workplace injury in 2016 for this company. Write the formula first, and then fill in the appropriate values.
FORMULA PLUG-IN VALUES ANSWER
6. Interpret the confidence interval in the context of the problem. Check the Announcement page in Canvas for the template on how to interpret a confidence interval. Write both parts/sentences.
Attachment:- Employee Satisfaction Data.rar