# General Social Survey (2014): Statistics (PSPP version)

## Exercises:

• STAT1S_pspp -  Exercise Using PSPP to Explore Levels of Measurement
• STAT2S_pspp  - Exercise Using PSPP to Explore Measures of Central Tendency and Dispersion
• STAT3S_pspp  - Exercise Using PSPP to Explore Measures of Skewness and Kurtosis
• STAT4S_pspp  -  Exercise Omitted
• STAT5S_pspp  - Exercise Using PSPP to Explore Hypothesis Testing - One-Sample t Test
• STAT6S_pspp  - Exercise Using PSPP to Explore Hypothesis Testing - Independent-Samples t Test
• STAT7S_pspp  - Exercise Using PSPP to Explore Hypothesis Testing – Paired-Samples t Test
• STAT8S_pspp  - Exercise Using PSPP to Explore Hypothesis Testing – One-Way Analysis of Variance
• STAT9S_pspp -  Exercise Using PSPP to Explore Crosstabulation
• STAT10S_pspp  - Exercise Using PSPP to Explore Chi Square
• STAT11S_pspp  - Exercise Using PSPP to Explore Measures of Association
• STAT12S_pspp  - Exercise Using PSPP to Explore Spuriousness
• STAT13S_pspp  - Exercise Using PSPP to Explore Correlation
• STAT14S_pspp  - Exercise Using PSPP to Explore Bivariate Linear Regression
• STAT15S_pspp  - Exercise Using PSPP to Explore Multiple Linear Regression
• STAT16S_pspp  - Exercise Using PSPP to Explore Dummy Variable Regression

Author:   Ed Nelson
Department of Sociology M/S SS97
California State University, Fresno
Fresno, CA 93740
Email:
ednelson@csufresno.edu

This is the second in a series of exercises for instructors teaching an introductory class in statistics. This set uses PSPP. There is another set of exercises using SPSS and a third set using SDA. The exercises were written so each exercise is independent of the others and any one exercise can be used even if the other exercises are not used. There is one exception. Exercises STAT14_pspp, STAT15S_pspp, and STAT16S_pspp all focus on regression and are best used as a unit. Because the first 13 exercises are written to stand alone there is often duplication across the exercises. If you use several of the exercises together you may want to edit them to remove this duplication or to add material of your own.

PSPP will run your SPSS data (.sav) files.  You can also run SPSS syntax (.sps) files in PSPP.  Sometimes PSPP will not run a particular SPSS command.  I have rewritten some of the exercises to make sure that all the syntax files included with the exercises will run.  That means I had to eliminate some parts of certain exercises.  I also eliminated one exercise (STAT4S) which was heavily dependent on charts and graphs, since PSPP does not have much capability in this area.  I kept the original numbering of the exercises to make it easier to make comparisons to the SPSS version.

The data set used in this exercise is gss14_subset_for_classes_STATISTICS_pspp.sav which is a subset of the 2014 General Social Survey.  Some of the variables in the GSS have been recoded to make them easier to use and some new variables have been created. The data have been weighted according to the instructions from the National Opinion Research Center.

Each exercise consists of four files all of which can be downloaded:

• the data file in PSPP format,
• extended notes to instructor as a Word (docx) file,
• the PSPP syntax necessary to carry out the exercise as a PSPP syntax file, and
• the exercise itself as a Word (docx) file.

These exercises are not a comprehensive treatment of these statistical tools.  They do not discuss how to compute any of the statistics nor do not discuss all the assumptions of these statistics.  You may want to add some of this information to the exercises.

You have permission to use these exercises and to revise them to fit your needs. I would appreciate receiving a copy of your revision so I can see how the exercises are being used.  If you find any errors in the exercise, please email me and I will correct them.  I would also like to hear from you about your experiences using the exercises.  Please contact me for more information at ednelson@csufresno.edu.

Each exercise has a set of keywords which are listed below.  After each keyword you’ll find the words PSPP or statistics indicating whether it is a PSPP or a statistical term.  There are also two spreadsheets – one for statistical terms and another for PSPP terms – which will help you find appropriate exercises.

## Keywords for the Exercises

• STAT1S_pspp: Frequencies (PSPP), levels of measurement (statistics), nominal measure (statistics), ordinal measure (statistics), interval measure (statistics), ratio measure (statistics)
• STAT2S_pspp: Frequencies (PSPP), mode (statistics), median (statistics), mean (statistics), skewness (statistics), normal distribution (statistics), histogram (statistics), bar chart (histogram), range (statistics), interquartile range (statistics), variance (statistics), standard deviation (statistics), third quartile (statistics), first quartile (statistics),
• STAT3S_pspp: Frequencies (PSPP), normal distribution (statistics), mean (statistics), median (statistics), mode (statistics), skewness (statistics), kurtosis (statistics), histogram (statistics)
• STAT4S_pspp: omitted
• STAT5S_pspp: Compare means (PSPP), select cases (PSPP), one-sample t test (PSPP and statistics),  population (statistics), sample (statistics), statistic (statistics), parameter (statistics), inference (statistics), probability sampling (statistics), non-probability sampling (statistics), probability of selection (statistics), simple random sample (statistics), sampling error (statistics), research hypothesis (statistics), null hypothesis(statistics)
• STAT6S_pspp: Compare means (PSPP), independent-samples t test (PSPP and statistics),  population (statistics), sample (statistics), statistic (statistics), parameter (statistics), inference (statistics), probability sampling (statistics), non-probability sampling (statistics), sampling error (statistics), research hypothesis (statistics), null hypothesis(statistics)
• STAT7S_pspp: Compare means (PSPP), paired-samples t test (PSPP and statistics),  population (statistics), sample (statistics), statistic (statistics), parameter (statistics), inference (statistics), probability sampling (statistics), non-probability sampling (statistics), sampling error (statistics), research hypothesis (statistics), null hypothesis(statistics)
• STAT8S_pspp: Compare means (PSPP), one-way analysis of variance (PSPP and statistics),  population (statistics), sample (statistics), statistic (statistics), parameter (statistics), inference (statistics), probability sampling (statistics), non-probability sampling (statistics), sampling error (statistics), research hypothesis (statistics), null hypothesis(statistics)
• STAT9S_pspp: Crosstabs (PSPP), crosstabulation (statistics), row percents (statistics),  column percents (statistics), independent variable (statistics), dependent variable (statistics), two-variable tables (statistics), three-variable tables (statistics)​
• STAT10S_pspp: Crosstabs (PSPP), Chi Square (statistics), observed frequencies (statistics), expected frequencies (statistics), degrees of freedom (statistics), significance (statistics), crosstabulation (statistics)
• STAT11S_pspp: Crosstabs (PSPP), Chi Square (statistics), column percents (statistics), independent variable (statistics), dependent variable (statistics), measures of association (statistics), symmetric measures (statistics), asymmetric measures (statistics), Contingency Coefficient (statistics), Phi (statistics), Cramer's V (statistics), Lambda (statistics), Gamma (statistics), Somer's d(statistics), Kendall's Tau-b (statistics), Kendall's Tau-c (statistics)
• STAT12S_pspp: Crosstabs (PSPP), recode (PSPP), column percents (statistics), Chi Square(statistics),  measures of association (statistics), hypothesis (methods), dummy table (methods), two-variable tables (statistics), three-variable tables (statistics), spuriousness (statistics)
• STAT13S_pspp: Bivariate Correlations (PSPP), compare means (PSPP), linear relationship (statistics), positive relationship (statistics),, negative relationship (statistics), curvilinear relationship (statistics), Pearson Correlation Coefficient (r) (statistics), Coefficient of Determination (r2) (statistics), correlation matrix (statistics)
• ​STAT14S_pspp: Linear regression (PSPP), frequencies (PSPP), select cases (PSPP), Pearson correlation coefficient (statistics), Pearson correlation coefficient squared (statistics), analysis of variance (statistics), linear relationship, linear regression equation (statistics), slope (statistics), constant (statistics), t test (statistics)
• STAT15S_pspp: Linear regression (PSPP), frequencies (PSPP), select cases (PSPP), outliers (statistics), multiple linear regression (statistics), unstandardized regression coefficient (statistics), standardized regression coefficient (statistics), Pearson Correlation Coefficient (statistics), Coefficient of Determination (statistics), adjusted R squared (statistics), tests of significance (statistics), multicollinearity (statistics)
• STAT16S_pspp: Linear regression (PSPP), select cases (PSPP), frequencies (PSPP), compute (PSPP), dummy variables (statistics), multiple linear regression (statistics), unstandardized regression coefficient (statistics), standardized regression coefficient (statistics), Pearson Multiple Correlation Coefficient (statistics), Coefficient of Determination (statistics), tests of significance (statistics)