Integrates with the Menu Bar of SPSS

1. Average d statistic:  Calculates the average d statistic using random and fixed effects models and forms a confidence interval about the average.  Used for meta-analysis.

2. Average raw mean difference:  Calculates the average mean difference and confidence intervals across studies using random and fixed effects model.  Also allows for comparisons of groups of studies.  Used for meta-analysis.

3. Group Contrasts for average d for fixed effects:  Calculates group differences in average d and performs a significance test of those differences. Used for meta-analysis and a fixed effects model.

4. Group Contrasts for average d for random effects:  Calculates group differences in average d and performs a significance test of those differences. Used for meta-analysis and a random effects model.

5. WLS Regression of d. Performs a weighted least squares regression predicting d statistics across studies from study characteristics.  Used in meta-analysis.

6. Average correlation:  Calculates the average correlation across studies or groups using random and fixed effects model and forms a confidence interval about the average.  Used for meta-analysis.

7. Group Contrasts for average correlation for fixed effects:  Calculates differences in average correlations for groups of studies and performs a significance test of those differences. Used for meta-analysis and a ficed effects model.

8. Group Contrasts for average correlation for random effects:  Calculates group differences in average correlations and performs a significance test of those differences. Used for meta-analysis and a random effects model.

9. WLS Regression of correlations: Performs a weighted least squares regression predicting correlations across studies from study characteristics.  Used in meta-analysis.

10. Average percentage difference:  Calculates the average percentage difference across studies or groups using random and fixed effects model and forms a confidence interval about the average.  Used for meta-analysis.

11. Group Contrasts for percentage difference for fixed effects:  Calculates differences in average percent differences for groups of studies and performs a significance test of those differences. Used for meta-analysis and fixed effects model.

12. Group Contrasts for average percentage difference for random effects:  Calculates group differences in average cpercent differences and performs a significance test of those differences. Used for meta-analysis and a random effects model.

13. WLS Regression for percent differences: Performs a weighted least squares regression predicting percent differences across studies from study characteristics.  Used in meta-analysis.

14. Average odds ratio:  Calculates the average odds ratio across studies or groups using random and fixed effects model and forms a confidence interval about the average.  Used for meta-analysis.

15. Group Contrasts for odds ratios for fixed effects:  Calculates differences in average odds ratios for groups of studies and performs a significance test of those differences. Used for meta-analysis with a fixed effects model.

16. Group Contrasts for odds ratios for random effects:  Calculates group differences in average odds ratios and performs a significance test of those differences. Used for meta-analysis and a random effects model.

17. Power for meta-analysis of d statistics:  Calculates the statistical power associated with a meta-analysis of an average d statistic for both fixed effect and random effect models.

18. Power for meta-analytic contrast of average d statistics:  Calculates the statistical power associated with meta-analytic contrasts of average d statistic for both fixed effect and random effect models.

19. Power for Q test of homogeneity for d statistics:  Calculates the statistical power associated with the Q test of effect size homogeneity of d statistics for a fixed effects model.

20. Power for meta-analytic WLS regression for d statistics:  Calculates the statistical power associated with a meta-analytic regression analysis on d statistics.

21. Power for meta-analysis of correlations:  Calculates the statistical power associated with a meta-analysis of an average correlation for both fixed effect and random effect models.

22. Power for meta-analytic contrast of average correlations:  Calculates the statistical power associated with meta-analytic contrasts of average correlations for both fixed effect and random effect models.

23. Power for Q test of homogeneity for correlations:  Calculates the statistical power associated with the Q test of effect size homogeneity of correlations for a fixed effects model.

24. Power for meta-analytic WLS regression for correlations:  Calculates the statistical power associated with a meta-analytic regression analysis on correlations.

25. Power for meta-analysis of odds ratios:  Calculates the statistical power associated with a meta-analysis of an average odds ratio for both fixed effect and random effect models.

26. Power for meta-analytic contrast of average odds ratios:  Calculates the statistical power associated with meta-analytic contrasts of average odds ratios for both fixed effect and random effect models.

27. Power for Q test of homogeneity for odds ratios:  Calculates the statistical power associated with the Q test of effect size homogeneity of odds ratios for a fixed effects model.

28. Power for meta-analysis of percent differences:  Calculates the statistical power associated with a meta-analysis of an average percent differences for both fixed effect and random effect models.

29. Power for meta-analytic contrast of percent differences:  Calculates the statistical power associated with meta-analytic contrasts of average percent differences for both fixed effect and random effect models.

30. Power for Q test of homogeneity for percent differences:  Calculates the statistical power associated with the Q test of effect size homogeneity of percent differences for a fixed effects model.

31. Power for meta-analytic WLS regression for percent differences:  Calculates the statistical power associated with a meta-analytic regression analysis on percent differences.

32. Power analysis for one sample t test:  Performs power analysis for the one sample t test.

33. Power analysis for dependent groups t test:  Performs power analysis for the dependent groups t test.

34. Power analysis for independent groups t test:  Performs power analysis for the independent groups t test.

35. Power analysis for one way ANOVA:  Performs power analysis for a pairwise comparison in one way ANOVA.

36. Power analysis for one way repeated measures ANOVA:  Performs power analysis for a pairwise comparison in a one way repeated measure ANOVA.

37. Power analysis for general contrasts:  Performs power analysis for a complex single degree of freedom contrast in a one way ANOVA.

38. Power analysis for two factor designs:  Performs power analysis for single degree of freedom contrasts for a main effect, a simple main effect and an interaction in a two factor design.

39. Power analysis for three factor designs:  Performs power analysis for single degree of freedom contrasts for a main effect, a simple main effect, a two way interaction and a three way interaction in a three factor design.

40. Power analysis for two factor analysis of covariance:  Performs power analysis for single degree of freedom contrasts for a main effect, a simple main effect and an interaction in a two factor analysis of covariance.

41. Power analysis for three factor analysis of covariance:  Performs power analysis for single degree of freedom contrasts for a main effect, a simple main effect, a two way interaction and a three way interaction in a three factor analysis of covariance.

42. Power analysis for between-within two factor designs:  Performs power analysis for single degree of freedom contrasts for a main effect, a simple main effect and an interaction in a two factor between-within design.

43. Power analysis for a percentage:  Performs power analysis for a test of a percentage against an hypothesized population value.

44. Power analysis for a percentage difference for independent groups:  Performs power analysis for a percentage difference between independent groups.

45. Power analysis for a percentage difference for dependent groups:  Performs power analysis for a percentage difference between dependent groups.

46. Power analysis for a binary predictor in logistic regression:  Performs power analysis for a binary predictor in a multivariate logistic regression.

47. Power analysis for a continuous predictor in logistic regression:  Performs power analysis for a continuous predictor in a multivariate logistic regression.

48. Power analysis for a contingency table:  Performs power analysis for a RXC contingency table.

49. Power analysis for a correlation:  Performs power analysis for a correlation coefficient.

50. Power analysis for a correlation difference:  Performs power analysis for a correlation coefficient difference between two independent groups.

51. Power analysis for hierarchical regression:  Performs power analysis for an hierarchical regression analysis.

52. Power analysis for a multiple correlation:  Performs power analysis for a multiple correlation coefficient.

53. Power analysis for a continuous predictor in a multiple regression:  Performs power analysis for a continuous predictor in a multiple regression equation.

54. Power analysis for growth curves in randomized designs:  Performs power analysis for the comparison of growth curves in two groups in a randomized design.

55. Power analysis for growth curves in cluster randomized designs:  Performs power analysis for the comparison of growth curves in two groups in a cluster randomized design.

56. Power analysis for cluster randomized designs:  Performs power analysis for the comparison of two means in a cluster randomized design.

57. Power analysis for cluster randomized designs with covariates:  Performs power analysis for the comparison of two means in a cluster randomized design with covariates.

58. Power analysis for multi-site cluster randomized designs:  Performs power analysis for the comparison of two means in a multi-site cluster randomized design.

59. Power analysis for multi-site cluster randomized designs with covariates:  Performs power analysis for the comparison of two means in a multi-site cluster randomized design with covariates.

60. Power analysis for multi-site randomized designs:  Performs power analysis for the comparison of two means in a multi-site randomized design.

61. Power analysis for multi-site randomized design moderator analysis:  Performs power analysis for the test of moderators of the difference in two means in a multi-site randomized design.

62. Power analysis for effect variability in a multi-site designs:  Performs power analysis for the variability of effects across sites in a multi-site randomized design.

63. Power analysis for a regression coefficient difference:  Performs power analysis for the difference between regression coefficients in independent groups.

64. Precision analysis for one sample t test:  Performs precision analysis (sample size for desired interval width) for the one sample t test.

65. Precision analysis for dependent groups t test:  Performs precision analysis (sample size for desired interval width) for the dependent groups t test.

66. Precision analysis for independent groups t test:  Performs precision analysis (sample size for desired interval width) for the independent groups t test.

67. Precision analysis for one way ANOVA:  Performs precision analysis (sample size for desired interval width) for a pairwise comparison in one way ANOVA.

68. Precision analysis for one way repeated measures ANOVA:  Performs precision analysis (sample size for desired interval width) for a pairwise comparison in a one way repeated measure ANOVA.

69. Precision analysis for general contrasts:  Performs precision analysis (sample size for desired interval width) for a complex single degree of freedom contrast in a one way ANOVA.

70. Precision analysis for two factor designs:  Performs precision analysis (sample size for desired interval width) for single degree of freedom contrasts for a main effect, a simple main effect and an interaction in a two factor design.

71. Precision analysis for three factor designs:  Performs precision analysis (sample size for desired interval width) for single degree of freedom contrasts for a main effect, a simple main effect, a two way interaction and a three way interaction in a three factor design.

72. Precision analysis for two factor analysis of covariance:  Performs precision analysis (sample size for desired interval width) for single degree of freedom contrasts for a main effect, a simple main effect and an interaction in a two factor analysis of covariance.

73. Precision analysis for three factor analysis of covariance:  Performs precision analysis (sample size for desired interval width) for single degree of freedom contrasts for a main effect, a simple main effect, a two way interaction and a three way interaction in a three factor analysis of covariance.

74. Precision analysis for between-within two factor designs:  Performs precision analysis (sample size for desired interval width) for single degree of freedom contrasts for a main effect, a simple main effect and an interaction in a two factor between-within design.

75. Precision analysis for a percentage:  Performs precision analysis (sample size for desired interval width) for a test of a percentage against an hypothesized population value.

76. Precision analysis for a percentage difference for independent groups:  Performs precision analysis (sample size for desired interval width) for a percentage difference between independent groups.

77. Precision analysis for a percentage difference for dependent groups:  Performs precision analysis (sample size for desired interval width) for a percentage difference between dependent groups.

78. Precision analysis for a correlation:  Performs precision analysis (sample size for desired interval width) for a correlation coefficient.

79. Precision analysis for a correlation difference:  Performs precision analysis (sample size for desired interval width) for a correlation coefficient difference between two independent groups.

80. Precision analysis for a multiple correlation:  Performs precision analysis (sample size for desired interval width) for a multiple correlation coefficient.

81. Precision analysis for a continuous predictor in a multiple regression:  Performs precision analysis (sample size for desired interval width) for a continuous predictor in a multiple regression equation.

82. Precision analysis for a regression coefficient difference:  Performs precision analysis (sample size for desired interval width) for the difference between regression coefficients in independent groups.

83. Equivalence test for means:  Uses confidence interval approach to allow for "accepting the null" when comparing means in different groups. 

84. Equivalence test for odds for independent groups:  Uses confidence interval approach to allow for "accepting the null" when comparing odds for independent groups.

85. Equivalence test for percentages for independent groups:  Uses confidence interval approach to allow for "accepting the null" when comparing percentages for independent groups.

86. Equivalence test for percentages for dependent groups:  Uses confidence interval approach to allow for "accepting the null" when comparing percentages for dependent groups.

87. Equivalence test for correlations in independent groups:  Uses confidence interval approach to allow for "accepting the null" when comparing correlations in independent groups.

88. Equivalence test for correlations in dependent groups:  Uses confidence interval approach to allow for "accepting the null" when comparing correlations in dependent groups. 

89. Equivalence test for multiple correlations in independent groups:  Uses confidence interval approach to allow for "accepting the null" when comparing multiple correlations in independent groups.

90. Equivalence test for partial correlations in independent groups:  Uses confidence interval approach to allow for "accepting the null" when comparing partial correlations in independent groups.

91. Trivial correlations:  Uses confidence interval approach to allow for "accepting the null" when evaluating a correlation coefficient.

92. Trivial multiple correlations:  Uses confidence interval approach to allow for "accepting the null" when evaluating a correlation coefficient.

93. Trivial partial correlations:  Uses confidence interval approach to allow for "accepting the null" when evaluating a correlation coefficient.

94. Excel bar graph of frequencies for variable in SPSS data set:  Automatically opens Excel and passes summary data to it for a variable in your active SPSS data file.  Automatically draws a nice Excel bar graph of frequencies. Can be "cut and pasted" into Word.

95. Excel bar graph of two way frequency table for variables in SPSS data set:  Automatically opens Excel from SPSS and passes to it summary data for a two way contingency table based on variables in your active SPSS data file.  Automatically draws a nice Excel two-way bar graph of the frequencies. Can be "cut and pasted" into Word.

96. Excel bar graph of means in a one way anova for variables in SPSS data set:  Automatically opens Excel  from SPSS and passes to it summary data of mean values of a variable in your SPSS data set as a function of a break variable or factor (as in one way anova).  Automatically draws a nice Excel bar graph of the means. Can be "cut and pasted" into Word.

97. Excel line plot of means in a one way anova for variables in SPSS data set:  Automatically opens Excel  from SPSS and passes to it summary data of mean values of a variable in your SPSS data set as a function of a break variable or factor (as in one way anova).  Automatically draws a nice Excel line plot of the means.  Can be "cut and pasted" into Word.

98. Excel bar graph of two factor anova means for variables in SPSS data set:  Automatically opens Excel from SPSS and passes to it summary data for a two way table of means based on variables in your active SPSS data file.  Automatically draws a nice Excel two-way bar graph of the means.  Can be "cut and pasted" into Word.

99. Excel line plot of two factor anova means for variables in SPSS data set:  Automatically opens Excel from SPSS and passes to it summary data for a two way table of means based on variables in your active SPSS data file.  Automatically draws a nice Excel two-way line plot of the means.  Can be "cut and pasted" into Word.

100. Excel scatterplot for variables in SPSS data set:  Automatically opens Excel from SPSS and passes to it data for two variables from your SPSS active data file.  Automatically draws a nice Excel scatterplot with the regression line.  Can be "cut and pasted" into Word.

101. Excel smoothed scatterplot for variables in SPSS data set:  Automatically opens Excel from SPSS and passes to it data for two variables from your SPSS active data file.  Automatically draws a nice Excel smoothed scatterplot with the regression line.  See the "Sample Programs" section of this website for more details and an illustration. Can be "cut and pasted" into Word.

102. Excel growth curve plots for variables in SPSS data set:  Automatically opens Excel from SPSS and passes to it data to illustrate growth curves across time points for individual respondents.  Automatically draws a nice Excel line plot that contains all of the respondents growth curves. Can be "cut and pasted" into Word.

103. Excel bar graph for frequency distribution of a variable:  Automatically opens Excel, after obtaining input about the range of the frequencies and the name of the variable.  Automatically draws a nice Excel bar graph of randomly generated frequencies.  The frequencies can be edited and the graph is automatically updated.  Can be "cut and pasted" into Word.

104. Excel bar graph for two way contingency table:  Automatically opens Excel, after obtaining input about the range of the frequencies and the names of the variables.  Automatically draws a nice Excel bar graph of randomly generated frequencies for a two way contingency table.  The frequencies can be edited and the graph is automatically updated.  Can be "cut and pasted" into Word.

105. Excel bar graph for means in a one way anova:  Automatically opens Excel, after obtaining input about the range of the means and the names of the dependent variable and factor.  Automatically draws a nice Excel bar graph of randomly generated means.  The means can be edited and the graph is automatically updated.  Error bars are included. Can be "cut and pasted" into Word.

106. Excel bar graph for means in a two factor anova:  Automatically opens Excel, after obtaining input about the range of the means and the names of the variables.  Automatically draws a nice Excel bar graph of randomly generated means for a two way table.  The means can be edited and the graph is automatically updated.   Error bars are included. Can be "cut and pasted" into Word.

107. Excel line plot for means in a one way anova:  Automatically opens Excel, after obtaining input about the range of the means and the names of the dependent variable and factor.  Automatically draws a nice Excel line plot of randomly generated means.  The means can be edited and the graph is automatically updated.  Error bars are included. Can be "cut and pasted" into Word.

108. Excel line plot for means in a two factor anova:  Automatically opens Excel, after obtaining input about the range of the means and the names of the variables.  Automatically draws a nice Excel line plot of randomly generated means for a two way table.  The means can be edited and the graph is automatically updated.   Error bars are included. Can be "cut and pasted" into Word.

109. Excel bar graph for means in a one way anova:  Automatically opens Excel, after obtaining input about the range of the means and the names of the dependent variable and factor.  Automatically draws a nice Excel bar graph of randomly generated means.  The means can be edited and the graph is automatically updated.  Error bars are included. Can be "cut and pasted" into Word.

110. Excel scatterplot:  Automatically opens Excel, after obtaining input about the range of values and the names of X and Y.  Automatically draws a nice Excel scatterplot with a regression line shown for randomly generated data of a specified N.  The data can be edited and the graph is automatically updated. Can be "cut and pasted" into Word.

111. Excel plot of up to five regression lines:  Automatically opens Excel and on a scatterplot, draws up to five regression lines specified by the user.  Useful for illustrating interaction effects in multiple regression. Can be "cut and pasted" into Word.

112. Excel plot of up to five regression curves based on quadratic regression:  Automatically opens Excel and on a scatterplot, draws up to five regression curves specified by the user using quadratic regression.  Useful for illustrating curvilinear trends and non-linear interaction effects. Can be "cut and pasted" into Word.

113. Excel plot of up to five regression curves based on cubic regression:  Automatically opens Excel and on a scatterplot, draws up to five regression curves specified by the user using cubic regression.  Useful for illustrating curvilinear trends and non-linear interaction effects. Can be "cut and pasted" into Word.

114. Excel plot of up to five logistic regression lines/curves:  Automatically opens Excel and on a scatterplot, draws up to five logistic regression lines/curves specified by the user.  Useful for illustrating interaction effects in logistic regression. Plots either probabilities, odds or log odds.  Can be "cut and pasted" into Word.

115. Excel plot of up to five logistic regression curves based on quadratic logistic  regression:  Automatically opens Excel and on a scatterplot, draws up to five logistic regression curves specified by the user using quadratic logistic regression.  Useful for illustrating curvilinear trends and non-linear interaction effects in logistic regression. Plots either probabilities, odds or log odds. Can be "cut and pasted" into Word.

116. Excel plot for individual growth curves:  Automatically opens Excel and passes data from SPSS to Excel for a variable measured at multiple time points and then makes a line plot for each case in the data file across time. The utility is useful for seeing trends in growth curves for individuals considered separately.

117. SPSS utility to mean center variables: Automatically creates new variables in an SPSS data set that equal the specified variables minus their means.  This utility also will center at one standard deviation of the mean and one standard deviation below the mean.

118. SPSS utility to mean center a variable with a break variable: Automatically creates new variables in an SPSS data set that equal the specified variables minus their means for different subgroups defined by a break variable. 

119. SPSS utility to reorder variables in a data file: Use simple point and click to quickly reorder variables in a data file, keeping and dropping as many as you want.

120. SPSS utility to create dummy variables with dummy coding: Specify a variable and ZumaStat automatically and quickly creates dummy variables with dummy coding to represent the specified variable.

121. SPSS utility to create dummy variables with effect coding: Specify a variable and ZumaStat automatically and quickly creates dummy variables with effect coding to represent the specified variable.

122. SPSS utility to create product terms: Specify a set of variables and ZumaStat automatically creates all possible product terms between them.  Useful for interaction terms in regression analysis.

123. SPSS utility to create dummy variables for missing data: Quickly and easily copy the value labels for one variable to one or more other variables.

124. SPSS utility to copy value labels: Quickly and easily copy the value labels for one variable to one or more other variables.

125. SPSS utility to reformat correlation matrix output: Reformats a correlation matrix output so that you can easily see the correlations on a single page without printing them.

126. SPSS utility to eliminate missing data: Deletes from the data set all cases that have missing data on specified variables.  Simple point and click.

127. SPSS utility to create missing data dummy variables:  When you have missing data, you often want to determine if there is bias in the missing data pattern.  This utility creates a dummy variable, where a score of 1 is assigned to cases with missing data and a score of 0 is assigned to cases with non-missing data.  This dummy variable can then be correlated with other variables to determine if it is associated  with them.

128. SPSS utility to save filtered cases:  A utility to save cases to a new SPSS file but apply a filter so that only a subset of the cases are saved.  Simple point and click.

129. SPSS utility to remove scientific notation and change decimals in a pivot table. With the click of a button, you can change the number of decimals displayed in a Pivot Table and remove scientific notation.

130. SPSS utility to remove page breaks from output. Removes all page breaks from an output document.

131. SPSS utility to change column widths. Allows simple point and click for changing the column widths of a large number of variables in the SPSS active data file.

132. SPSS utility to form weighted combinations of variables:  This routine creates a new variable that is a weighted sum of other variables in your data file. 

133. SPSS utility to round variables: This routine rounds variables using efficient point and click.

134. SPSS utility for creating difference scores:  Specify a set of variables and ZumaStat automatically calculates all possible difference scores between them.  This can be useful for analyzing repeated measure designs. 

135. SPSS utility to add or subtract constants to many variables:  For up to 10 variables, quickly subtract or add the same constant to them using simple point and click.

136. SPSS utility to exchange values on a variable:  If you rely on the parameter estimates of SPSS's GLM program to isolate single degree of freedom contrasts, then you often have to change the reference group.  ZumaStat quickly exchanges values on a variable to simplify this process.

137. SPSS utility to export data with keep and drop: Uses simple point and click to export data files while keeping or dropping variables.  .

138. SPSS utility to group scores on a variable:  Suppose you want to recode scores on a variable so that individuals with values between 1 and 5 are in one group, those with scores of 6 to 10 are in another group, and so on.  ZumaStat does so easily.

139. SPSS utility to create a break variable from several variables:  If you have two factors in a factorial design and want to turn this into a one way design, ZumaStat will do so with simple point and click. This is useful for applying contrast formulas to factorial designs.

140. SPSS utility to reverse score variables:  Quickly reverse scores variables in your data set with simple point and click. 

141. SPSS utility to rename variables:  Renaming a variable is straightforward but cumbersome in SPSS.  ZumaStat makes it easy to rename many variables.

142. SPSS utility to convert user missing to system missing for all variables:  Converts all user missing values on all variables to system missing values with the click of one button.

143. SPSS utility to calculate date intervals:  Specify two date variables and this utility creates a new variable that is the number of days, months or years between the two dates.

144.  SPSS utility for matrix operations: Uses the SPSS matrix language to perform operations on a single matrix. The operations include absolute value, Cholesky decomposition, determinant, eigenvalues, exponentiation, generalized inverse, inverse, rank, scalar multiply, square root, trace and transpose. This is all done with point and click and involves no syntax.

145. SPSS utility for matrix algebra: Uses the SPSS matrix language to perform matrix algebra on two matrices. The algebra includes addition, subtraction, multiplication, division, Kronecker products, element-wise multiplication and element-wise division. This is all done with point and click and involves no syntax.

146. SPSS utility for cross validation: Randomly divides an active data file in half and saves the two halves to separate files. The is useful for cross-validation analyses.

147. SPSS utility to create simulation data:  ZumaStat allows you to create a set of random variables for a user selected number of cases such that the variables come from either a normal distribution, a chi square distribution, a lognormal distribution, a uniform distribution or a mixed normal distribution. The variables will be uncorrelated. This is useful for conducting simulations.

148. SPSS utility to create correlated simulation data:  ZumaStat allows you to create a set of random variables for a user selected number of cases such that the variables come from either a normal distribution, a chi square distribution, a lognormal distribution, a uniform distribution or a mixed normal distribution. The variables will be correlated in accord with a pre-specified correlation matrix. This is useful for conducting simulations.

149. SPSS utility to create categorical simulation data:  ZumaStat allows you to create a data for a categorical variable sampled from a population with specified category probabilities. This routine will also handle the fixed case where a fixed number of cases are assigned to experimental conditions. This is useful for conducting simulations.

150. SPSS utility to create simulation data for latent variables and indicators:  ZumaStat allows you to create a set of random latent variables for a user selected number of cases such that the variables come from either a normal distribution, a chi square distribution, a lognormal distribution, a uniform distribution or a mixed normal distribution. The variables will be correlated in accord with a pre-specified correlation matrix. The user then specifies a measurement model for those latent variables. This is useful for conducting simulations.

151. SPSS utility to create simulation data using sampling with replacement:  ZumaStat allows you to create a set of simulated data from an active data file using sampling with replacement. This is useful for conducting simulations from a data file in the spirit of bootstrapping.

152.  SPSS utility to implement a simulation of multiple regression: ZumaStat has a utility that will execute and summarize a simulation for multiple regression problems. It permits simple evaluation of Type I and Type II errors, confidence interval coverage and a bias.

153. Determine valid range of correlations:  Given three variables X, Y and Z, the correlation between any two pairs of variables dictates the range that the third pair must fall within. ZumaStat calculates this. 

154. SPSS utility to create input files for LISREL:  Although LISREL imports SPSS data files, there are times when it will be more convenient to output a correlation matrix with means and standard deviations in ascii files for input into LISREL.  ZumaStat does so with a few mouse clicks. 

155. SPSS utility to create input files of raw data for LISREL:  Writes data to an ascii file in a way that can be easily read into LISREL. 

156. SPSS utility to prepare data for HLM analyses:  Quickly formats data for input into the HLM computer program.  Works well for growth curve analyses.

157. SPSS utility to generate syntax for the GLM program:  Writing syntax for the /LMatrix line of the SPSS GLM program is cumbersome.  This utility automatically generates syntax for main effect comparisons, simple main effect comparisons and interaction contrasts, so you can paste the syntax into the program.

158. SPSS utility to generate multiple imputation data sets through Amelia:  Interfaces with the computer program Amelia to generate multiple imputed data sets to deal with missing data.

159. SPSS utility to conduct multiple imputation regression analyses:  Interfaces with the computer program Amelia to conduct multiple regression analyses on multiple imputed data sets and then combines estimates to yield final solution.

160. SPSS utility to conduct multiple imputation logistic regression analyses:  Interfaces with the computer program Amelia to conduct multiple logistic regression analyses on multiple imputed data sets and then combines estimates to yield final solution.

161. Combine estimates from multiple imputed data sets:  Utility to combine results from the analysis of multiple imputed data sets.

162. Confidence interval for d statistic (independent groups): Calculates confidence intervals for a standardized effect size d based on two independent groups.

163. Confidence interval for d statistic (dependent groups): Calculates confidence intervals for a standardized effect size d based on two dependent groups.

164. Confidence interval for epsilon squared: Calculates confidence intervals for an index of percent of variance accounted for in analysis of variance designs.

165. Confidence interval for a standard deviation: Calculates confidence intervals for a standard deviation.

166. Confidence interval for a variance ratio: Calculates confidence intervals for a variance ratio.  Useful for evaluating decisions about heterogeneous variance analytic methods.

167. Common language effect size for independent groups: Specifies the probability that a randomly selected individual from group 1 will have a higher score on the dependent variable than a randomly selected individual from group 2.

168. Common language effect size for dependent groups: Specifies the probability that a randomly selected observation from condition 1 will be higher on the  dependent variable than a randomly selected observation from condition 2.

169. Probability of superiority (PS) effect size measure for independent groups: Non-parametric counterpart to the Common Language Effect Size index for independent groups.  Based on the Mann-Whitney U statistic.

170. Mean contrasts: Performs a complex contrast of means based on traditional multiple comparison formulas based on means, sample sizes, and contrast coefficients as input (in addition to the MSerror).

171. Mean contrasts in the case of heterogeneous variances: Performs a complex contrast of means based on multiple comparison formulas for non-homogeneous variances based on means, standard deviations, sample sizes, and contrast coefficients as input.

172. Trimmed means from SPSS: Calculates a trimmed mean and a Winsorized standard deviation for any variable in an SPSS active data set. 

173. Trimmed means from SPSS with a break variable: Calculates a trimmed mean and a Winsorized standard deviation for any variable in an SPSS active data set for each value of a break variable (or a factor). 

174. Trimmed mean confidence interval: Calculates the confidence interval of a trimmed mean.

175. Trimmed mean dependent groups t test: Performs a dependent groups t test of trimmed means.

176. Trimmed mean one sample t test: Performs a one sample t test of trimmed means.

177. Trimmed mean independent groups t test: Performs an independent groups t test of trimmed means.

178. Mean contrasts for trimmed means: Performs a complex contrast of trimmed means based on traditional multiple comparison formulas based on trimmed means, Winsorized standard deviations, sample sizes, and contrast coefficients as input.

179. Johnson-Neyman analysis of mean differences as a function of a continuous variable:  Analyzes an interaction between a continuous variable and a dichotomous variable.  Identifies regions on the continuous variable where the mean difference on the dependent variable as a function of the dichotomous variable is statistically significant.  Uses means, standard deviations and correlations as input.

180. Regression to the mean for an intervention: ZumaStat calculates the effect of regression toward the mean for analyses that adjust for pre-existing differences between experimental and control groups by statistically holding constant the pre-test scores and examining group differences in the covariate adjusted post-test scores.

181. Independent groups t test from summary statistics: Performs an independent groups t test based on means, standard deviations and sample sizes as input.

182. Dependent groups t test from summary statistics: Performs a dependent groups t test based on means, standard deviations and a correlation as input.

183. One sample t test from summary statistics: Performs a one sample t test based on means, standard deviations and sample size as input.

184. One way analysis of variance from summary statistics: Performs a one way anova based on means, standard deviations and sample sizes as input.

185. Summary table from an F ratio and means: User inputs an F ratio, degrees of freedom, means and sample sizes (information usually contained in a journal article).  ZumaStat generates a complete summary table from the anova, including the mean square between, the mean square error, the sum of squares between and the sum of squares error.

186. Tukey HSD pairwise differences from summary statistics: Performs all possible pairwise comparisons using the Tukey HSD test.  Input is the means, sample sizes and the MSerror as input.  Generates confidence intervals.

187. Tukey LSD pairwise differences from summary statistics: Performs all possible pairwise comparisons using the Tukey LSD test.  Input is the means, sample sizes and the MSerror as input. Generates confidence intervals.

188. Tukey-Kramer pairwise differences from summary statistics: Performs all possible pairwise comparisons using the Tukey-Kramer test.  Input is the means, sample sizes and the MSerror as input. Generates confidence intervals.

189. Fisher-Hayter pairwise differences from summary statistics: Performs all possible pairwise comparisons using the Fisher-Hayter test.  Input is the means, sample sizes and the MSerror as input. Generates confidence intervals.

190. Bonferroni pairwise differences from summary statistics: Performs all possible pairwise comparisons using a Bonferroni test.  Input is the means, sample sizes and the MSerror as input. Generates confidence intervals.

191. REGW Q pairwise differences from summary statistics: Performs all possible pairwise comparisons using the REGW Q procedure.  Input is the means, sample sizes and the MSerror as input. Generates confidence intervals.

192. Games and Howell pairwise differences from summary statistics: Performs all possible pairwise comparisons using the Games and Howell test.  Input is the means, sample sizes and standard deviations as input. Generates confidence intervals.

193. Trimmed mean pairwise differences from summary statistics: Performs all possible pairwise comparisons of trimmed means.  Input is the trimmed means, sample sizes and Winsorized standard deviations as input. Generates confidence intervals.

194. Hochberg modified Bonferroni approach:  Generates critical p values for the Hochberg step up method to control for family wise error rates. 

195. Holm modified Bonferroni approach:  Generates critical p values for the Holm step down method to control for family wise error rates.

196. False discovery rate:  Generates critical p values for the False Discovery Rate method of FWE control. 

197. Scheffe tests:  User provides the number of tests and the traditional critical F and ZumaStat produces the Scheffe based critical F.   

198. Single degree of freedom contrasts in a two factor anova: User inputs means, sample sizes and MSerror from a two factor anova.  ZumaStat calculates all relevant main effect comparisons, simple main effect comparisons, and interaction contrasts. 

199. Single degree of freedom contrasts in a three factor anova: User inputs means, sample sizes and MSerror from a three factor anova.  ZumaStat calculates all relevant main effect comparisons, simple main effect comparisons, and simple and full interaction contrasts. 

200. Single degree of freedom contrasts in a two factor design with heterogeneous variances: User inputs means, sample sizes and standard deviations from a two factor design.  ZumaStat calculates all relevant main effect comparisons, simple main effect comparisons, and interaction contrasts adjusting for heterogeneous variances. 

201. Single degree of freedom contrasts in a three factor design: User inputs means, sample sizes and standard deviations from a three factor design.  ZumaStat calculates all relevant main effect comparisons, simple main effect comparisons, and simple and full interaction contrasts adjusting for heterogeneous variances.   

202. Pooled mean: User provides the means and sample sizes from several groups and ZumaStat calculates the pooled mean.

203. Confidence interval for a correlation: Calculates confidence interval and significance test for a correlation coefficient.  Input is the correlation and sample size.

204. Confidence interval for a squared correlation: Calculates confidence interval and significance test for a squared correlation coefficient.  Input is the correlation and sample size.

205. Confidence interval for a squared multiple correlation: Calculates confidence interval and significance test for a squared multiple correlation coefficient.  Input is the correlation, the number of predictors and the sample size.

206. Confidence interval for the difference between independent correlations: Calculates confidence interval and significance test for the difference between two correlations derived from independent groups.  Input is the correlation and sample size for each group.

207. Confidence interval for the difference between dependent correlations: Calculates confidence interval and significance test for the difference between two correlations derived from dependent groups.  Input includes releavnt correlations and sample size.

208. Test of difference for non-overlapping correlations: Tests the difference between the correlation of Y and X with the correlation of Z and Q, both derived from the same sample

209. Confidence interval for a partial correlation: Calculates confidence interval and significance test for a partial correlation.  Input is the correlation, the number of covariates, and the sample size.

210. Confidence interval for a squared partial correlation: Calculates confidence interval and significance test for a squared partial correlation.  Input is the correlation, the number of covariates, and the sample size.

211. Confidence interval for the difference between independent partial correlations: Calculates confidence interval and significance test for the difference between two partial correlations derived from independent groups.  Input is the correlation, sample size, and number of covariates for each group.

212. Confidence interval for the difference between two squared multiple correlations derived in independent groups: Calculates confidence interval and significance test for the difference between two squared multiple correlations derived from independent groups.  Input is the correlation, sample size and number of predictors for each group.

213. Test of within equation standardized regression coefficients: Tests the null hypothesis that two predictors in the same multiple regression equation have equal standardized regression coefficients.  Does all possible pairwise comaprsions.  Uses summary statistics.

214. Test of within equation unstandardized regression coefficients: Tests the null hypothesis that two predictors in the same multiple regression equation have equal unstandardized regression coefficients.  Does all possible pairwise comaprsions.  Uses summary statistics.

215. Confidence interval for a regression coefficient: Calculates confidence interval and significance test for a regression coefficient.  Input is the coefficient, its standard error and the degrees of freedom.

216. Confidence interval for a path coefficient: Calculates confidence interval and significance test for a path coefficient.  Input is the coefficient and its standard error.

217. All possible regressions: Uses SPSS to calculate all possible regressions as an alternative to stepwise regression.  Maximum of 10 predictors.

218. Hierarchical multiple regression from summary statistics: Calculates a significance test for a hierarchical regression from the sample size, the two squared Rs and the number of predictors.

219. Common language effect size for a correlation: Specifies the probability that a randomly selected individual who has a score higher than another individual on X will also have a score higher than the individual on Y.  Input is the correlation and sample size.

220.  r to Z transform: Transforms r to Fisher's z or Fisher's z to r.

221. Mediation: Applies asymmetric confidence interval approach to the product of two regression coefficients and tests of joint path significance.  Has more statistical power than the traditional Baron-Kenny approach. Uses summary statistics.

222. Bivariate regression from summary statistics: Calculates a complete bivariate regression analysis from simple summary statistics.

223. Multiple regression from summary statistics: Calculates a complete multiple regression analysis from summary statistics of means, standard deviations, and correlations.  Up to 10 predictors.

224. Partial correlation from summary statistics: Calculates a partial correlation analysis from zero order correlations.  Up to 10 covariates.

225. Interaction analysis in multiple regression: Calculates the slope of Y on X at any given value of Z in an interaction model.

226. Interaction analysis with significance tests in multiple regression: Calculates the slope of Y on X at any given value of Z in an interaction model and also provides significance tests of the simple slopes.

227. Exploratory interaction analysis in multiple regression: Based on bandwidth regression, helps one isolate interactions in an exploratory mode.  Requires use of SPSS.

228. Intersection point of two regression lines: For disordinal interactions, identification of the exact point where the two regression lines intersect. 

229. Quadratic regression: Algebraic heuristics for interpreting quadratic regression models.

230. Cubic regression: Algebraic heuristics for interpreting cubic regression models.

231. Predicted score in a multiple regression equation. You provide the equation, ZumaStat calculates the predicted scores of different predictor profiles.

232. Reliability of a change score: Calculates the reliability of a change score from the reliabilities of the scores comprising the change scores.

233. Correlation corrected for attenuation: Calculates the value of a correlation after adjusting for the unreliability of the measures.

234. Regression to the mean: Given an experimental versus control group study where there are pre-existing differences on the outcome variable at the pretest, this utility reports the amount of difference that will persist after an intervention that could reflect regression to the mean, assuming no intervention effect.  The assumed analysis is an analysis of covariance on the posttest holding constant the pretest.

235. Confidence interval for a percentage: Calculates confidence interval and significance test for a percentage.  Input is the percentage and sample size.    

236. Confidence interval for a percentage difference between independent groups: Calculates confidence interval and significance test for a percentage difference between independent groups.  Input is the percentages and sample sizes.    

237. Confidence interval for a percentage difference for the same group of individuals: Calculates confidence interval and significance test for a percentage difference where two percentages come from the same sample.  Input is the percentages, the correlation between percentages, and the sample size.

238. Confidence interval for a difference between percentage differences: Calculates confidence interval and significance test for a difference between two percentage differences.  Input is the percentages and sample sizes.    

239. Percentage contrasts: General algorithm for conducting linear contrasts among a set of percentages from independent groups.     

240. Confidence interval for an odds: Calculates confidence interval for an odds.

241. Confidence interval for an odds ratio: Calculates confidence interval for an odds ratio comparing the odds of two groups.

242. Confidence interval for a ratio of odds ratios: Calculates confidence interval for a the ratio of two odds ratios.   

243. Confidence interval for a two way interaction of odds ratios: Calculates confidence interval for a the ratio of the ratio of two odds ratios.

244. Confidence interval for a relative risk: Calculates confidence interval for a relative risk.

245. Confidence interval for a logistic regression coefficient: Calculates confidence interval and significance test for a logistic regression coefficient.  Input is the coefficient and its standard error.

246. Odds calculator: Converts log odds to odds and odds to probability.  Or any combination of the three.

247. Logistic regression model fit: Performs an informal evaluation of the fit of a logistic model using a variant of the Hosmer-Lemeshow test.

248. Pseudo R squared: Calculates values of pseudo R squared in logistic regression using versions not available in SPSS and which have desirable properties.

249. Predicted score in a logistic regression equation: You provide the equation, ZumaStat calculates the predicted scores of different predictor profiles.  Calculates the predicted log odds, the predicted odds and the predicted probability.

250. RXC contingency table: Does a chi square test of independence based on cell frequencies that you provide.  Includes follow-up tests and calculation of Cramer's V.

251. Confidence interval for Cramer's V.  Calculates the confidence interval for Cramer's V.  Input is the size of the contingency table, the overall sample size and the chi square from the test of independence.

252. Alternatives to the Wald Coefficient.  Uses the SPSS logistic regression program. The default output for SPSS for a test of a logistic coefficient is a Wald test. This test has been found to behave badly under some circumstances. This utility uses a programming trick to have SPSS print out a likelhood ratio test and an exact conditional scores test for each coefficient in addition to the Wald test.

253. Combinations: Calculates the number of unique combinations of a given size that can be formed from a larger set of objects.  Ordering of objects within a set does not matter.

254. Permutations: Calculates the number of unique combinations of a given size that can be formed from a larger set of objects.  Ordering of objects within a set does  matter.

255. Factorials: Calculates the factorial of a number.

256. Critical value for a chi square distribution: You provide the alpha level and the degrees of freedom and ZumaStat gives you the critical value of chi square associated with them.

257. Critical value for an F distribution: You provide the alpha level and the degrees of freedom and ZumaStat gives you the critical value of F associated with them.

258. Critical value for a t distribution: You provide the alpha level and the degrees of freedom and ZumaStat gives you the critical value of t associated with them.

259. Critical value for a normal distribution: You provide the alpha level and ZumaStat gives you the critical value of F associated with them.

260. Critical value for a Studentized range distribution: You provide the alpha level, teh span, and the degrees of freedom and ZumaStat gives you the critical value of q associated with them.

261. p value for a chi square distribution: You provide the chi square value and the  degrees of freedom, and ZumaStat gives you the p value.

262. p value for an F distribution: You provide the F value and the degrees of freedom, and ZumaStat gives you the p value.

263. p value for a t distribution: You provide the t value and the degrees of freedom, and ZumaStat gives you the p value.

264. p value for a normal distribution: You provide the z value and ZumaStat gives you the p value.

265. p value for a Studentized range distribution: You provide the q value, the span, and the degrees of freedom, and ZumaStat gives you the p value.

266. p value for  a binomial distribution: You provide the number of trials, the number of successes and the probability of a success and ZumaStat reports the probability of obtaining that number of successes.

267. p value for  a cumulative binomial distribution: You provide the number of trials, the number of successes and the probability of a success and ZumaStat reports the probability of obtaining that number of successes or more.

268. Region between two standard scores in a normal distribution: You provide two z scores and ZumaStat gives you the proportion of scores that occur between them.

269. Cumulative normal distribution: ZumaStat provides probability values for the cumulative normal distribution.

270. Confidence interval for coefficient alpha: Uses bootstrapping to estimate confidence intervals for coefficient alpha.

271. Number of items to achieve specified alpha coefficient: You specify the typical correlation you expect to observe between items and the coefficient alpha that you want to achieve. The routine tells you the number of items your scale will have to consist of in order to achieve that alpha.

272. Analysis of change: Six types of change scores: You identify the pretest and the posttest variables and ZumaStat quickly calculates a raw change score, a reliable change index, an ordinal reliable change index, a residualized change score, a backward residualized change score and the Lord-McNemar true change score.

273. Analysis of change: Reliability of change scores: Zumastat calculates the reliability of a change score from the reliability of its component parts.

274. Analysis of change: Correlation of pretest with change score: Zumastat calculates what the correlation between a pretest and a change score must be, given that the pretest is part of the change score.

275. Analysis of change: Regression to the mean: Zumastat calculates how much regression to the mean will occur after an analysis of covariance to adjust for pretest differences in two groups by using the pretest as a covariate when predicting the posttest.

276. Analysis of change: Galton squeeze diagram: Zumastat starts Excel and draws a Galton squeeze plot to document the extent of regression to the mean over time.

277. Analysis of change: Pair-link diagram: Zumastat starts Excel and draws a Pair-link plot to illustrate change for individuals between a pretest and a posttest.