http://pspp.kiberpipa.org/wiki/ 2012-05-17T04:33:37+02:00 http://pspp.kiberpipa.org/wiki/ http://pspp.kiberpipa.org/wiki/lib/images/favicon.ico text/html 2010-07-05T14:46:15+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=binominal&rev=1278333975&do=diff The binomial test compares the observed distribution of a dichotomous variable with that of a binomial distribution. The variable p specifies the test proportion of the binomial distribution. The default value of 0.5 is assumed if p is omitted. If a single value appears after the variable list, then that value is used as the threshold to partition the observed values. Values less than or equal to the threshold value form the first category. Values greater than the threshold form the second cate… text/html 2010-03-16T12:23:55+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=bivariate_correlation&rev=1268738635&do=diff Correlation is a measure of statistical relationships between two or more random variables or observed data values. In PSPP bivariate correlation (Pearson coefficient of correlatin) can be computed through menu Analyze - Bivariate Correlation. We need to select variables to compute correlations among them and click OK. text/html 2010-07-05T14:46:01+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=chi-square&rev=1278333961&do=diff The Chi-Square test produces a chi-square statistic for the differences between the expected and observed frequencies of the categories of a variable. Optionally, a range of values may appear after the variable list. If a range is given, then non integer values are truncated, and values outside the specified range are excluded from the analysis. text/html 2010-03-17T10:53:09+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=compare_means&rev=1268819589&do=diff PSPP can perform T-tests and ANOVA test for comparing means. T-test is a statistical hypothesis test in which the test statistic follows a Student's t distribution if the null hypothesis is true. The unpaired, or “independent samples” t-test is used when two separate independent and identically distributed samples are obtained, one from each of the two populations being compared. ANOVA test is a statistical test of whether the means of several groups are all equal, and therefore generalizes Stud… text/html 2010-03-18T13:25:00+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=compare_spss_pspp&rev=1268915100&do=diff * PSPP output in PDF format * SPSS output in PDF format text/html 2010-03-16T10:44:44+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=crosstabs&rev=1268732684&do=diff To compute crosstabs, go to Analyze - Descriptive statistics - Crosstabs. First the row and column variables should be selected. By clicking on Statistics button you can select which statistics should be computed. It is also useful to select which cells should be computed (row percentage, column percentage, total percentage, count, residuals,...). text/html 2010-03-16T09:39:44+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=data_files&rev=1268728784&do=diff SPSS data files (SAV) can be directly opened in PSPP, but PSPP also offers option to importing data from several sources. Importing delimited data Import wizard for delimited data files is availabe through File - Import delimited text data and works for textual data only. First, we have to select a file and decide what amount of data we want to import (all cases, only n first cases or only some percentage of datafile). text/html 2010-03-16T10:33:22+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=descriptive&rev=1268732002&do=diff Frequencies To compute frequency distribution of a variable, go to Analyze - Descriptive statistics - Frequencies. Select target variables (in our example Gender) on the left side and move them by clicking to an arrow button to the right side (to “Variable(s)” list). text/html 2010-03-17T21:04:06+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=explore&rev=1268856246&do=diff Explore command is used to compute measures of central tendency (mean and median), dispersion (range, interquartile range, standard deviation, variance, minimum and maximum), kurtosis and skewnessand and Tukey's hinges for box plots. To perform explore computation go to Analyze - Descriptive Statistics - Explore. text/html 2010-07-06T08:50:07+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=factor_analysis&rev=1278399007&do=diff Factor analysis is a procedure which tries to reduce the number of variables and detect structure in the relationships among observed variables. Factor analysis used to describe variability among observed variables in terms of fewer unobserved variables called factors. The observed variables are modeled as linear combinations of the factors, plus “error” terms. text/html 2010-04-06T11:21:11+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=mac&rev=1270545671&do=diff Prerequisites * You need to have X11 installed on your Mac * Building with Macports, Fink or Darwinports installed _will_ fail- remove them from path and ldpath first You can build it the easy or the hard way. Easy way of building: * Download this archive and extract it * enter newly created “pspp” folder, then open the “runme” file in terminal (right click on ”runme” -> open with -> terminal”) * when asked, enter your password (needed to install make 3.81) * it should take aro… text/html 2010-07-05T14:42:26+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=nonparametric&rev=1278333746&do=diff PSPP also performs some nonparametric tests. Non parametric tests make very few assumptions about the distribution of the data. Currenlty there are two tests available: * Chi-square * Binominal text/html 2010-03-18T09:35:07+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=other_wiki&rev=1268901307&do=diff * Free Resources for Methods in Program Evaluation and Social Research, by Gene Shackman. * Comparing free statistical software for data sets with no missing values, by Gene Shackman (review of various packages, including PSPP, which shows that they all give the same results). * Free statistical software, review of free statistical software in Citizendium, by Gene Shackman. * Another PSPP wiki, maintained by Jason Stover from Georgia College and State University and more developer oriente… text/html 2010-07-06T09:40:27+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=overview&rev=1278402027&do=diff PSPP consist of three windows: * dataset window, where user can view and edit dataset and run data analysis from the menu; * syntax window, where user can edit and run SPSS syntax; * output window, where output computation (tables, in future versions also graphics) is presented. text/html 2010-03-16T11:35:44+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=recode_compute&rev=1268735744&do=diff Recode command Recoding is a method to combine (unite) several values of a given variable into less categories. Let's say we want to recode age of respondents into three categories: up to 25 years, 26 to 50 and older than 50. Variables could be recoded into the same variable or new variable. Usually it is better to recode into new variable, because it could happen we will need original variable values for some statistical analysis in the future. text/html 2010-03-17T11:20:39+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=regression&rev=1268821239&do=diff Linear regression refers to any approach to modeling the relationship between dependent variable and one or more independent variables, such that the model depends linearly on the unknown parameters to be estimated from the data. Such a model is called a “linear model”. Linear regression procedure in PSPP fits linear models to data via least-squares estimation. The procedure is appropriate for data which satisfy assumptions typical in linear regression. text/html 2010-03-17T13:58:58+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=reliability&rev=1268830738&do=diff PSPP can also measure the internal consistency or reliability of a data (in psychometry: variables measuring the same “concept”). PSPP supports Cronbach's Alpha and split-half method. To perform reliablity analysis on the data, go to Analysis - Reliability. text/html 2010-03-17T12:49:10+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=roc_curve&rev=1268826550&do=diff Receiver Operating Characteristic (ROC) curve is a graphical plot of the sensitivity, or true positives, vs. (1 − specificity), or false positives, for a binary classifier system as its discrimination threshold is varied. The ROC can also be represented equivalently by plotting the fraction of true positives (TPR = true positive rate) vs. the fraction of false positives (FPR = false positive rate). ROC curves can be used to compare the diagnostic performance of two or more laboratory or diagnost… text/html 2010-03-16T12:04:17+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=sample&rev=1268737457&do=diff PSPP can do several operations to select, filter and sample data. Filtering with boolean-valued variable PSPP uses FILTER command to select cases from the data stream for processing. Cases which have a zero or system- or user-missing value at the filter variable are excluded from analysis. This command is not available through graphical interface, but can be used from syntax. text/html 2010-07-06T09:30:27+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=start&rev=1278401427&do=diff PSPP is an application for statistical analysis of data. PSPP is a completely free replacement for the commercial application SPSS (now PASW) and is very similar to it. It's syntax files and data are also compatible with SPSS. PSPP can perform several data transformation (including count, recode, weighting and handling of missing values), compute descriptive statistics (frequencies, descriptive statistics), compute crosstabs , T-tests (independent samples T-test, paired samples T-test and one-s… text/html 2010-03-17T13:27:37+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=test_data_set&rev=1268828857&do=diff To test PSPP with real data, you can use the following test data sets in SPSS SAV format: * SJM 2002/2 - Slovenian Public Opinion Survey conducded by Public Opinion and Mass Communication Research Centre, Faculty of Social Sciences, University of Ljubljana in October 2002. Published is only a small part of a survey. Published by permission of authors. * test.sav - test data only (data are not real). * Large data set - contains 1,990,052 cases and four variables (Region, Name of region, si… text/html 2010-03-31T09:52:15+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=ubuntu&rev=1270021935&do=diff text/html 2010-03-18T08:22:32+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=video_guides&rev=1268896952&do=diff * Using PSPP for statistical analysis (35,5 Mb MPEG4 video), by Douglas A. Ferguson, College of Charleston, USA. You can check other video guides/textbooks by the same author at his website. text/html 2010-03-16T11:22:18+02:00 http://pspp.kiberpipa.org/wiki/doku.php?id=weight&rev=1268734938&do=diff Weighting is a procedure which can to give some cases more or less influence (weight) on the result than other cases have in the same data set. We use weights in case of over- or underrepresentated units in our sample. For instance, if we know, that there is 51% female in the population, and we have only 49% of female in our sample, we can give female respondents in our sample more influence by computing a weight (which is larger than 1 in our case, actually is 51/49 = 1,040816327). We can compu…