Lab 2 Worksheet
Uploaded by
PohuyistLab 2 Worksheet
Uploaded by
PohuyistPsych 248 — Lab 2 Descriptive Statistics
Name:____________________________________________________
This assignment will give you practice working with an existing data file, entering a new data file, and creating
descriptive statistics. You may work in pairs during lab but both should turn in this worksheet at the end for lab credit.
Part A. OPEN AN EXISTING SPSS DATA FILE.
Open the SPSS data file called Sales.sav (located on K drive under Psych248 folder).
Look at the data file—both in data view and variable view windows.
[Control-End will take you to the bottom of the file & Control-Home will take you back to the top]
1. How many variables are there? _________ How many cases are there? ________
2. What are the value labels for Industry variable? 1 = ________________ 2 = ____________3 = ___________
3. Which variable is scale/ratio measure? ____________________
4. Why is Support classified “ordinal” whereas Region and Industry are nominal measures?
Create frequency distribution tables and bar graphs for customer, support, region, & industry variables.
Go to Analyze Descriptive Stats Frequencies then select the 4 variables.
Make sure the Display frequency table box is checked. Under Statistics – leave all boxes unchecked.
Under Charts; Select Bar chart as Chart Type AND Select Frequencies under Chart Values.
5. Why would it make no sense to compute a mean or standard deviation for these variables?
6. What percentage of customers was left on hold less than one minute? _________
7. What percentage of customers was kept on hold for more than 4 minutes? ________
Create a table of descriptive statistics and a histogram with a normal curve for revenue variable (the only meaningful
ratio-level variable).
Go to Analyze, Descriptive Statistics, Frequencies. Remove previous variables and select revenue.
Uncheck box that says Display frequency table.
Click Statistics – Check standard deviation, minimum, maximum, mean, median, mode, and skewness.
Under Charts select histogram and check the box to Show normal curve on histogram.
8. Does revenue appear to be fairly normally distributed? How can you tell from the stats & histogram?
9. What does skewness mean?
Another useful way to summarize data is to break down a continuous variable (e.g. revenue) by a categorical or nominal
variable of interest (e.g., region, customer type).
Go to Analyze Descriptive Statistics Explore. Select revenue as the DV AND region as the Factor.
Under Statistics select Descriptives. Under Plots select Histogram and Boxplots (factor levels together).
10. Which is the only region that does not have outliers (extreme values) at the high end of the scale? ______________
11. Do you think the medians and amount of variability in revenue are similar across regions? Justify your answer.
Create a means table for revenue to answer Q#12.
Use Analyze Compare Means Means.
Select revenue as DVs and customer as IV.
12. One might predict that preferred customers are bigger spenders than regular customers. Is this hypothesis supported in
the data? Explain your answer.
Create a cross-tabulation for support (time on hold) by customer status to answer Q#13.
Go to Analyze Descriptives Crosstabs. Put customer status in rows and Support in columns.
Click on Cells and click on row percentages.
13. One might predict that preferred customers receive better treatment when they need help (technical support) from the
company. Is this hypothesis supported in the data? Explain your answer.
Part B: CREATING A NEW DATA FILE AND EXAMINING RELATIONSHIPS.
The following data represent the results of descriptive research on the ability to solve mazes in preschool children. The
researchers tested 60 children with the same maze, and recorded the number of errors each child made while solving it.
Each child’s age and gender were also recorded.
4-year-old girls: 12, 9, 13, 7, 10, 8, 11, 9, 10, 12 4-year-old boys: 9, 13, 14, 11, 9, 9, 10, 8, 7, 10
5-year-old girls: 9, 7, 8, 11, 6, 7, 9, 7, 5, 8 5-year-old boys: 10, 6, 7, 8, 9, 8, 11, 5, 8, 7
6-year-old girls: 3, 2, 5, 3, 4, 3, 6, 1, 3, 4 6-year-old boys: 1, 5, 4, 2, 2, 4, 3, 2, 3, 3
Input these data into SPSS data window.
Think about IVs and DVs and create proper variables for each aspect of the given data. Generate a frequency
table for the DV (error score). Obtain the mean, median, mode, SD, skewness, kurtosis.
Obtain a histogram with a normal curve superimposed on it.
1. What kind of distribution does the dependent variable have? ___________________
Obtain descriptive statistics and a histogram for error variable separately for girls and boys using gender as a factor.
2. How do girls compare to boys in terms of the number of errors?
Generate a scatterplot and side by side boxplots using age as an explanatory variable (X axis) and number of errors
as an outcome variable (Y axis). [Hint: Set age as an ordinal measure. Create the boxplots and scatterplot by going
to Graphs Chart Builder]
3. Do age groups seem to be different from one another in terms of the number of errors? (Explain)
