SPRING STAT MODULES

TURBO Spring-Stat© consists of 22 separate MODULES which are accessed from a MAIN control program which is MENU/prompt driven as are all the individual modules.

DOS vs. WINDOWS: This system is available in both DOS and WINDOWS versions. The two systems are functionally identical EXCEPT that the WINDOWS version does not include a text editor (it uses NOTEPAD), and includes a WINDOWS based SPREADSHEET/GRAPHING RESOURCE (number of cells limited only by FREE memory), and DATABASE MANAGER (unlimited cases; 256 variables). The DOS based versions of these two data entry/editing modules are ALSO included in the WINDOWS version.

The basic number crunching modules are the same in both DOS and WINDOWS. In the case of WINDOWS, a WINDOWS based SHELL is used to control all activities, and access all resources.

DATA ENTRY/EDITING

1. DATA BASE MODULE

Requires: NO ADDITIONAL MODULES
Capacity: 5 million Data Points

A full-featured DATA BASE MODULE is available as a key part of the package. This module allows up to 10,000 records with up to 500 variables (fields) per record. With it you can design custom data bases interactively and add records, delete records, change fields within records, search and sort records, and design custom report formats. You can also merge files, and create sub-files which include only those variables that you specify and only those records which meet the conditions you supply interactively. In fact, you can use this data base module for non-statistical applications (mailing lists, record catalogs etc.) because all the data is stored in ASCII format.

2. TRANSFORMATION MODULE

Requires: DATA BASE MODULE
Capacity: 5 million Data Points

A separate TRANSFORMATION MODULE is also available as an adjunct to the data base. This module allows you to create one or more new variables using a BASIC-like interpreter that supports

arithmetic (^,+,-,*,/)
logical (IF,THEN,ELSE,AND,OR,>,<,>=,<=, =,<>)
function (SQR,SIN,COS,TAN,ATN,INT,LOG,EXP,ABS,NEG)
commands. You can include up to 26 existing variables as well as numeric constants when creating the formula for computing a new variable. The transformation module also allows you to recode variables (alphanumeric codes can be changed to numeric codes; continuous values can be changed to categorical values representing intervals), and to transform variables to normal or standardized scores.

3. SCREEN EDITOR (Spreadsheet) MODULE

Requires: NO ADDITIONAL MODULES
Capacity: 10K Data Points

A spreadsheet-like SCREEN EDITOR MODULE is available for handling small to medium jobs. This editor can read and write files that are compatible with the data base module, read/write files in its own unique format, read ASCII files and read/write DIF files. If a job is medium to small (observations x variables < 10,000), this module can be used to create and edit the data in a more convenient fashion than when using the data base module. It also has the same data transformation capabilities as the TRANSFORMATION module, as well as the ability to: save a subset of a matrix, transpose a matrix, sort a matrix, and calulate: lags, column sums, row sums, cum columns, and ranks. This module is also the only data entry/edit method acceptable for Multidimensional Scaling and Hierarchical clustering, 2-D/3-D labeled ASCII graphs, HI-RES graphics, the Logit model, and Non-Linear curve fitting.

STATISTICS/GRAPHICS

TURBO Spring-Stat© provides 16 statistical procedures as separate modules. Unless stated otherwise, the number of cases/respondents that can be handled by each module is 10,000. For each module the variable capacity is also indicated, along with requirements for support modules:

4. ELEMENTARY STATISTICS MODULE

Requires: DATA BASE MODULE
Capacity: Up to 500 variables.

Sum of X, Sum of X^2, Sum of X^3
Maximum, Minimum
Range, Mid-range
Mean, Variance, Standard Deviation, Standard error of mean
Coefficient of skewness, Coefficient of variation

5. CONTINGENCY TABLES (CROSS TABS) MODULE

Requires: DATA BASE MODULE; ELEMENTARY STATS
Capacity: Up to 500 Variables (2 at a time).

CROSS-TABS of either categorical variables or continuous variables with computed intervals
Row, column, and cell percents and totals
Chi Square and Contingency Coefficient
Pearson's R, Bi-variate regression coefficients (where applicable)
Row and column means, T-test on means (where applicable)

6. CORRELATION MATRIX MODULE

Requires: DATA BASE MODULE
Capacity: Up to 120 Variables .

Means and Standard Deviations
Sums of squares and cross products
Corrected sums of squares and cross products (Dispersion Matrix)
Correlation Matrix
Bartlett's Sphericity Test
Multiple R^2 of each variable with others

7. STEPWISE MULTIPLE REGRESSION MODULE

Requires: DATA BASE MODULE; CORRELATION MATRIX MODULE
Capacity: Up to 120 Variables .

Multiple R^2, Standard Error of Estimate at each step
AnOVA for REGRESSION vs. RESIDUAL at each step
F to remove, F to enter, Beta Coefficient, Error of Beta, Partial R, Tolerance value for each variable at each step
Provision to either enter or remove a variable at each step using the Sweep algorithm

8. FACTOR ANALYSIS MODULE

Requires: DATA BASE MODULE; CORRELATION MATRIX MODULE
Capacity: Up to 120 Variables .

Principal Components using HOW algorithm for eigenstructure computations
Eigenvalue, %Trace, Wilk's Lambda, Bartlett's test for each successively extracted Eigenvalue/root
Unrotated Factor structure, Communalities, Factor Score Coefficients
Varimax (orthogonal) rotation
Promax (oblique) rotation with Factor Structure, Factor Pattern, and Inter-factor correlations

9. CANONICAL CORRELATION MODULE

Requires: DATA BASE MODULE; CORRELATION MATRIX MODULE
Capacity: Up to 120 Variables .

Eigenvalues, Canonical R's, and Bartlett's test for each Canonical root
Canonical Coefficients for Dependent and Independent variables
Structure Correlations for Dependent and Independent variables
Stewart & Love Redundancy measures

10. MULTIVARIATE ANOVA MODULE

Requires: DATA BASE MODULE; CORRELATION MATRIX MODULE
Capacity: Up to 120 Variables .

Group means and Standard Deviations for each variable
Univariate F-ratios and Correlation ratios (Etas) for each variable
Group sample sizes and Determinants of each group's correlation matrix
Test for equivalence of dispersions (Box's M)
Tests for equivalence of centroids (Wilk's Lambda and Rao's F)
Multivariate Correlation Ratio (Eta)

11. STEPWISE MULTIPLE DISCRIMINANT MODULE

Requires: DATA BASE MODULE; CORRELATION MATRIX MODULE; MULTIVARIATE ANALYSIS OF VARIANCE MODULE
Capacity: Up to 120 Variables .

Wilk's Lambda and Chi-Square test on Lambda at each step
F to remove, F to enter for each variable at each step
Group Discriminant Coefficients for each variable at each step
Provision to either enter or remove a variable at each step using the Sweep algorithm

12. CANONICAL DISCRIMINANT MODULE

Requires: DATA BASE MODULE; CORRELATION MATRIX MODULE; MULTIVARIATE ANALYSIS OF VARIANCE MODULE
Capacity: Up to 120 Variables .

Eigenvalue, %Trace, Canonical R, Wilk's Lambda, and Chi Square Test on Lambda for each canonical root extracted
Discriminant function coefficients for each variable on each canonical root
Structure correlations for each variable on each root
Group centroids for each group on each root

13. PERCEPTUAL MAPPING & HI-CLUS

Requires: SCREEN EDITOR MODULE
Capacity: Up to 50 Objects and 80 Variables .

Means, Standard deviations, Correlation Matrix
Preliminary solution using Principal Components
Euclidean distance matrix between objects
Multidimensional Scaling Solution using KYST
Hierarchical Clustering of objects based on distance matrix
Graphics (Perceptual map of objects and variables; Dendrogram of clustering process)
Ability to handle both OBJECT x OBJECT and OBJECT x VARIABLE matrices

14. ANALYSIS OF VARIANCE (ANOVA) MODULE

Requires: DATA BASE MODULE
Capacity: Up to 5 factors .

1-way, 2-way, randomized, split-plot, Latin square, and randomized complete block designs
Post Hoc LSD test, Tukey HSD test, Sheffe' test
Complete ANOVA summary tables

15. TIME SERIES ANALYSIS MODULE

Requires: DATA BASE MODULE
Capacity: Up to 400 time periods for all procedures except Double Precision Multiple Regression, which allows up to 80 variables on up to 10,000 observations.

Spectral Analysis (POWER SPECTRUM)
CORRELOGRAM
CURVE FITTING
FILTERING (high pass; low pass; band pass)
Generalized Exponential Smoothing with adaptive parameters (X-SMOOTHING)
Residual analysis
Double Precision Multiple Regression (DP REGRESSION)

16. LOGIT MODEL MODULE

Requires: SCREEN EDITOR MODULE
Capacity: Up to 40 treatments .

Weighted maximum likelihood fit
Displays actual points vs. theoretical curve
Full range of probabilities and 95% fiducial limits
Chi Square Goodness-of-fit estimate

17. NON-PARAMETRIC STATISTICS MODULE

Requires: DATA BASE MODULE
Capacity: Up to 500 observations and 20 categories/groups .

Wilcoxon signed ranks test (WILCOXON TEST)
SIGN TEST
KENDALL'S TAU
SPEARMAN'S RHO
FRIEDMAN 2-way AnOVA
Kendall's Coefficient of Concordance
MANN-WHITNEY U test
KOLMOGOROV-Smirnov 2 sample test
KRUSKAL-WALLIS 1-way AnOVA

18. ASCII GRAPHICS MODULE

Requires: DATA BASE MODULE; SCREEN EDITOR MODULE; ELEMENTARY STATISTICS MODULE
Capacity: 3-D labeled graphs- 3 variables (any 3) and 10 objects. 2-D labeled graphs- Up to 50 objects and 2 variables (out of a maximum choice set of 80). Up to 10K observations for non-labeled graphs..

LABELED 3-D MAPping
LABELED 2-D MAPping with interactive control for modifications
SCATTERPLOT with associated statistics
FREQUENCY PLOT with associated statistics (HISTOGRAM)
Box and WHISKER PLOT
STEM & LEAF diagram

19. HIGH-RESOLUTION GRAPHICS MODULE

Requires: CGA,EGA,VGA, or Hercules graphics board. Epson FX-85 or work-alike, or HP Laser or DeskJet for HARD COPY. Also needs SCREEN EDITOR, updated MAIN, and updated ASCII GRAPHICS.
Capacity: 3-D labeled graphs- 3 variables (any 3) and 10 objects. 2-D labeled graphs- Up to 50 objects and 2 variables (out of a maximum choice set of 80). Up to 100 observations for non-labeled graphs..

Reads .DPM files.
Produces 32 different types of graphs including three types of 3-D graphs, a labeled 2-D scatterplot, 2-D bar, scatter, and line graphs with optional semi-log and log-log scaling with or without grids, windowed polynomial curve fit (1-6 degree) with raw data, fitted curve, and error bars, labeled bar and pie charts.
Can also be accessed from updated CONTINGENCY-TABS module to produce a 3-D representation of a CROSS-TAB.
Written in TURBO C using BGI.

20. MARQUARDT NON-LINEAR FIT MODULE

Requires: CGA,EGA,VGA, or Hercules graphics board. Epson FX-85 or work-alike, or HP Laser or DeskJet for HARD COPY. Also needs SCREEN EDITOR MODULE.
Capacity: 100 cases ; 2 variables selected from up to 20 variables..

Uses LEVENBERG/MARQUARDT algorithm
User supplied function definition, starting values, parameter limits
Uses numerical derivatives. No user derivatives needed.
ANOVA, R squared, Marquardt's LAMBDA, Standard ERRORS
Plots data, fitted curve, and residuals in HI-RES

NOTE: In all instances where the DATABASE MODULE is required, it's also possible to use the SCREEN EDITOR to generate the data. However, doing it this way restricts you to Observations x Variables <= 10K, while using the DATABASE MODULE allows up to 10,000 observations and 500 variables (i.e. 5 million data points).

NON-STATISTICAL PROCEDURES

In addition to the statistical procedures described in the previous section, non-statistical procedures are available in the TURBO Spring-Stat(c) system:

21. EXPERT SYSTEM MODULE

Requires: NO ADDITIONAL MODULES.
Capacity: More than 50 rules and 100 conditions in Knowledge Base..

Cursor controlled pop-up menu interface. Just point and shoot.
System matches user's analytical needs to TURBO Spring-Stat© procedures through an interactive dialog session. When needs have been ascertained, a procedure is recommended.
User answers all questions with simple yes/no responses.
User can query system at any point to see why a particular question is being asked.
Logic based system. Knowledge base is expressed as predicate-logic clauses (attributes), and rules for combining the clauses for different conclusions.
Uses backward chaining.
User can modify the knowledge base with a text editor or word processor.

22. TEXT EDITOR MODULE

Requires: NO ADDITIONAL MODULES; Supports mouse if available.
Capacity: As many 64K windowed edit buffers as free memory allows..

Reads/writes ASCII text files.
Movable, resizable, tiled or cascaded multiple windows
Scrollbars and mouse support
Local and extended cursor movement commands
Insert/delete commands
Block commands
Miscellaneous commands
Menu operation and help file available on-line
Use it to create, view, or modify ASCII files (all TURBO Spring-Stat© data files are ASCII files. All output from a procedure can also be routed to an ASCII file instead of the printer.)

If you'd like to examine a very small sampling of the GRAPHICS available in each of our software products, JUMP to our GRAPHICS SAMPLER.

If you want to 'Try via DOWNLOAD', by all means link to our: FREE DEMO SOFTWARE.

o Return to: 'SPRING SYSTEMS HOME PAGE'