2015:Access SPSS VIDEO TUTOR at: and Set up your free account

Note: (procedure) means you must indicate step by step how to accomplish the task at hand. Use the “help” command in SPSS and your textbook to answer any questions not addressed in the video tutorials.

Introduction to SPSS (Video 1a)
  1. SPSS lets you analyze data in three basic ways – what are they and which statistical techniques do you

use to explore each?

  1. What are the two main windows in SPSS? Describe what you use each window for.
  1. What is the difference between the “data view” and the “variable view” in the data editor?
  1. What do the rows and columns in an SPSS data set (data view) represent?
  1. What is a case? A variable?

6, If a person wanted to do some simple summaries of frequencies with SPSS, whatmenu itens would that person use? (describe procedure)

  1. Open the Hobbit.sav data set (on the S:/drive under 381/Wilhelm/SPSS): run frequencies on gender –

what % of respondents are female?

  1. In the frequencies output, what is the difference between the “valid percent” column and the “percent”

column? Which do you always want to use?

Inputting Data (Video 2a)
  1. What are the four steps for inputting data into an SPSS data editor? Define each.
  1. What is a “code book?” Why is it important?
  1. What do the numerical codes entered into the SPSS data editor represent?
  1. Define the following: (1) variable name, (2) variable label, (3) value, (4) value label. What is the

difference between a variable label and a value label?

  1. Below are the paired ratings for Red Lobster and Jake's Seafood Restaurant for 10 respondents for each of three different restaurant features. The 7-point ratings were obtained on a questionnaire that instructed respondents to rate each restaurant from low (1) to high (7) prices, slow (1) to fast (7) service, and wide (1) to limited (7) menu. Input these responses into an SPSS for Windows dataset (File-New-Data) and save the file for future use; make sure and define an ID number for each respondent (1 -10). In the variable view window, provide – for each of the six variables (prices, service, menu for each restaurant) - a variable name, variable label, values (e.g., 1) and value labels (e.g., slow). NOTE: values and value labels will be the same for each restaurant. Include a hard copy of the data view and variable view windows in the data editor.

ID # / RLprices / Jakeprices / RLservice / Jakesservice / RLmenu / Jakesmenu
1 / 2 / 4 / 5 / 4 / 2 / 7
2 / 3 / 5 / 6 / 4 / 2 / 5
3 / 2 / 7 / 7 / 2 / 1 / 5
4 / 1 / 6 / 5 / 3 / 3 / 4
5 / 3 / 4 / 4 / 1 / 1 / 6
6 / 4 / 7 / 7 / 3 / 4 / 5
7 / 3 / 6 / 7 / 2 / 2 / 7
8 / 2 / 4 / 5 / 1 / 2 / 4
9 / 1 / 5 / 6 / 3 / 4 / 5
10 / 2 / 6 / 7 / 3 / 2 / 6

Recoding and Computing Variables (Video 3a and text)

  1. What is a reverse-scored variable, and what purpose does it serve?(see textbook for answer)
  1. When you recode a variable using the "into the same variable" option, what happens to the original data values? What purpose do you think the "into different variable recode" option serves?
  1. How does a computed variable differ from a recoded variable?
  1. A researcher has coded all instances where respondents have indicated "do not know" or "refuse to answer" with the code, "99." How can you use the recode operation to cause SPSS for Windows to recognize that 99 stands for missing data?

5. Open your red lobster/jakes data set.

a. Recode the service ratings so they are fast-to-slow – use the “into same variable” command. This will ensure that all of the variables are scaled as 1 = positive and 7 = negative. Students should use the recode into the same variable operation.

b. Compute average overall ratings for Red Lobster and Jake's Seafood Restaurant using the three restaurant attributes of: prices, service, and menu

c. Compute the difference between the averages for each restaurant for each respondent.

d. Inspect your computed differences across all ten respondents, and indicate which restaurant has a better overall perceived image.

e. Print a hard copy of the data editor window with your computed/recoded data

Descriptive Statistics (Video 4a and Text, Ch. 12)

  1. If you have nominal/categorical/string variables, which descriptive statistics routine (“descriptives” or “frequencies”)would you use? What are the proper descriptive statistics for these variables?

What is the “Valid Percent” in an SPSS frequencies table, and how are these values computed? How is it different from the “Percent” column?

  1. What are the appropriate descriptive statistics with numeric and scaled data?
  1. With the Descriptives command, the mean, standard deviation, minimum, and maximum check boxes are checked when the options window opens. Why do you think this is the default?
  1. Indicate whether you should use Frequencies or Descriptives to calculate the appropriate descriptive statistics for each of the following variables.

a.Gender

b.Type of dwelling (apt., house, etc.)

c.Take home pay (exact amount)

d.Favorite brand of diet cola

e.First, second, and third choice of pain reliever

f.Satisfaction with customer service on a 7-point scale

  1. Open your Red Lobster data set w/the recoded service variables. Run Descriptive-Descriptive statistics for all of the variables (run as one table) and obtain the mean and standard deviation for each. Create a table to hand inthat summarizes this information for each variable, and interpret your findings – how is each restaurant perceived re menu, price and service? Make sure and include scale endpoints in your write-up (e.g. 1= X, 7= Y). Report findings up to two decimals.

Creating Bar Chars (Video 5d)

  1. What is the procedure (command sequence in SPSS) for creating bar charts?
  1. What are the three bar chart options and under what circumstances would you use each option?
  1. Open your Red Lobster data set. Create a bar chart that compares the mean for Red Lobster’s overall

evaluation with Jake’s overall average. Make it look professional, similar to the video! Print a hard copy of your bar chart to turn in. Interpret your results.

One Sample t-test (Video 6a and text, Ch. 13)

  1. What is a one-sample t-test all about?
  1. What are the scaling requirements for a one sample t-test?
  1. When the test value in a one-sample t-test is set to zero, confidence intervals around the mean will be

computed. Open the Hobbit.sav data set (S:/drive/CBE/MKTG381/Wilhelm/SPSS/Hobbit). Calculate the confidence intervals around the means for the variables totspent (How many total dollars do you spend per month in restaurants?) and likely (How likely would it be for you to patronize this new upscale restaurant?). Make sure and include means, and scale endpoints for the variable likely ( and interpret the mean).

  1. When performing a hypothesis test for a mean, what does the test value represent?
  1. Which part of the output do you look at to see if there is support for your hypothesized mean? What

does it mean if the sig. level is <.05? >.05?

  1. Using your Hobbit data set, test the hypothesis that respondents expect an average evening meal entrée item at this new restaurant to cost $25 (variable=avprice, i.e., What would you expect an average evening meal entree item alone to be priced?). Is the hypothesis supported (what are t and sig values?) If not, what do respondents expect an entrée to cost? Next, re-run the 1-sample t-test with test value = 0 to obtain the confidence intervals around the sample mean. Report both the sample mean and confidence intervals for this variable.No need to include SPSS output.

Independent Samples t-test (Video 6b and text, Ch. 13)

  1. What is the purpose of this statistical test? What are the scaling assumptions for the “grouping” variable and the dependent variable?
  1. With an Independent Samples t-test, how many groups are involved, and why are the groups considered "independent?"
  1. Indicate how to determine if the variances of two compared means are equal or unequal.
  1. If the Sig. (2-tailed) statistic is <.05, what does this mean? I s there a significant difference between the 2 means?
  1. Open the Hobbit.sav data set on the S:/drive and conduct the appropriate analysis to determine whether men or women are more likely to patronize this restaurant (variable = likely). What are the means for men and women? Is there a significant difference (report the t and sig values here)? Interpret your findings.No need to include SPSS output.

Paired Samples t-test (Video6c and text, Ch. 13)

  1. A paired samples t-test can be used to examine which kinds of differences?
  1. How many groups are involved in a Paired Samples T-test? What are the scaling requirements for each

variable?

  1. Describe how you would determine if the means of two variables in the same dataset are significantly different. Specifically, what output table would you inspect, and how would you determine the significance level?

4. Suppose you had a 7-point rating scale where respondents indicate how important a store’s attributes

are in deciding to be loyal to that store, and a 1-5 rating scale where respondents indicated how well

that store performed on each of these attributes. What is the proper use of a Paired Samples Test in this

instance?

5.Using the Hobbit.sav data set, determine whether consumers prefer a waterfront view over a drive of

less than 30 minutes. Report means, t and sig values and interpret your findings. Make sure andinclude scale endpoints and interpret the means (e.g., what does a 4 mean???) No need to include SPSS output.

One-way Analysis of Variance (ANOVA) (Video 6d and text, ch. 13)

  1. What is the purpose of an ANOVA test? When is it appropriate to use ANOVA rather than a t-test, i.e.,

what is the primary difference between the two?

  1. With ANOVA, differentiate a dependent variable from a factor. Indicate the scaling assumptions of each.
  1. How does one interpret the significance level reported in an ANOVA table?
  1. What is a Post Hoc Test? When is it appropriate to examine this output?
  1. Using the Hobbit.sav data set, determine whether higher or lower income groups are more likely to patronize this new restaurant (DV=likely). If sig value < .05, run a Duncan post hoc test to see which means are significantly different?Which income group(s) would you target? Report ANOVA F and sig. values and post hoc results, and include scale endpoints when you report means. No need to include SPSS output. NOTE: you do NOT need to check any options as done in the video.

Chi-square Test for Independence (Video 8b and text, Ch. 14)

  1. What is a crosstabulation, and why is it used? Is it appropriate to talk about independent and

dependent variables – why or why not?

  1. What are the appropriate scaling assumptions of crosstabulated variables?
  1. How can you determine if a crosstabulation result is statistically significant - What statistic do you

examine?[NOTE: we will NOT use the Continuity Correction]. Explain what is meant by a statistically

significant crosstabulation finding.

  1. What are the "observed" counts in a crosstabulation table?
  1. Using your Hobbit.sav data set, perform a crosstab and chi-square test to determine if there is any relationship between gender and city magazine subscriptions (i.e., are men or women more likely to subscribe?). Include row and column percentages in the output table but NOT observed, expected or totals. Report the chi-square statistic and sig level. What % of men subscribe to City magazine? What % of women subscribe to City magazine? Is there a significant difference? No need to include SPSS output.

Bivariate Correlation (Video 7a and text, ch. 14)

  1. What is the purpose of Bivariate (Pearson) correlation analysis? .
  1. What are the appropriate scaling assumptions of variables analyzed using Pearson Product Moment correlations? What do you do if you believe your data is not normally distributed?

3 .What is the null hypothesis in correlation analysis, and how do you determine the degree of support for the null hypothesis?

4,If you were inspecting an SPSS correlation matrix, and you found a correlation coefficient without any asterisk(s) beside it, what would this signify?

5. Why does SPSS for Windows report the sample size for every pair of variables for which it computes a correlation? That is, why not just report the total sample size?

6.Suppose you found a positive correlation of .646 between sales and sales force size with a significance level of .01. How would you interpret this finding?

7.Is it correct to claim that its higher prices in some territories caused Novartis’ sales to be lower in those territories? Why or why not?

8.Using your Hobbit.sav data set, perform a correlation analysis among the décor (simple, elegant) and music (jazz, string quartet) variables. Include a table here that reports the correlations and statistical significance between each pair of variables. Interpret your findings: Do respondents who prefer a simple restaurant décor also prefer jazz and string quartets? Do respondents who prefer an elegant restaurant décor also prefer jazz and string quartets? No need to include original SPSS output.

Multiple Regression (Video 7c and text, Ch. 15)

  1. Under what circumstances would you want to use MR? Explain the value of the use of multiple regression in a marketing situation (see textbook).
  1. What are the appropriate distribution and scaling assumptions of variables analyzed using multiple regression?
  1. What is the meaning of the ANOVA table? If the sig. value < .05, what does this mean?

4.What are standardized beta coefficients, and how should they be interpreted? What does the adjusted R-squared statistic mean?

5.What is multicollinearity and how do you assess multicollinearity among the independent variables?

6.What is a trimmed regression model (see text)?

7.Using your Hobbit data set, perform a MR analysis to determine how well total dollars spent in restaurants (totspent) and expectations regarding an average entrée price (avprice) predict the likelihood of individuals to patronize this new restaurant (likely). Check the significance of the F test. Remove any predictor variables that are not statistically significant (i.e., look at p value of each standardized beta), and then re-run the regression.Create a table that displays the standardized betas, their significance levels, and the adjusted r-squared statistic. Make sure and check for multicolinearity! Interpret your results (e.g. which independent variable is most important in predicting the dependent variable?). No need to include original SPSS output.

1