Dataplot Reference Manual, Volume 1, Chapter 3 Introduction

Dataplot Reference Manual
Volume 1: Commands

Chapter 3: Analysis Commands Introduction

Analysis commands carry out mathematical and statistical analyses such as fitting, transformations, statistical tests, and smoothing. Examples of such commands include FIT, LET, and SMOOTH. The commands in this category are:

Data and Function Transformations

EXECUTE	Execute an external program.
LET	Define variables and parameters, transform data, calculate statistics, roots, derivatives, integrals and more.
LET FUNCTION	Define and operate on functions.
FUNCTION BLOCK	Defines a function via a group of Dataplot commands.
STATISTIC BLOCK	Defines a statistic via a group of Dataplot commands.

Fitting and Smoothing

BEST CP	Perform a best subsets CP analysis.
BOOTSTRAP FIT	Perform a bootstrap linear or multilinear fit.
CALIBRATION	Compute a linear or quadratic calibration using multiple methods.
EQUAL SLOPES TEST	Test two or more linear regression lines to see if they have equal slopes.
EXACT ... RATIONAL FIT	Perform an exact rational function fit.
FIT NON-LINEAR FIT LINEAR FIT REGRESSION DIAGNOSTICS	Perform linear and non-linear least squares fits.
LOWESS SMOOTH	Performs locally-weighted least squares time series and scatter plot smoothing for both equispaced and non-equispaced data.
... PRE-FIT	Perform a pre-fit analysis for starting values.
... SMOOTH	Perform a least squares, moving average or robust (based on moving medians) smooth of equi-spaced data.
... SPLINE FIT	Perform a spline fit.
DEX PHD	Compute the principle Hessian directions for a Yates analysis.
MEDIAN POLISH	Perform a robust analysis of variance.
ORTHOGONAL DISTANCE FIT	Estimate the parameters for an orthognal distance fit (also known as errors in variables fitting).
RECIPE	Compute REgression Confidence Intervals on PErcentiles (RECIPE).
YATES ANALYSIS	Perform a Yates analysis of 2-level factorial designs.

Experiment Design and Analysis of Variance

ANOVA	Perform a fixed effects analysis of variance (ANOVA) for balanced data.
COCHRAN TEST	Perform a Cochran test that c treatments have identical effects for a binary response.
DURBIN TEST	Perform a Durbin test that k treatments in a two-way balanced incomplete block design have identical effects.
F LOCATION TEST	Perform a 1-factor F location test for the homogeneity of locations across samples.
FRIEDMAN TEST	Perform a Friedman test that k treatments are identical in a randomized complete block design.
KRUSKAL WALLIS TEST	Perform a Kruskal Wallis test that k samples come from identifical populations.
K SAMPLE PERMUTATION TEST	Perform a k sample permutation test for a given statistic.
K SAMPLE PERMUTATION TEST	Perform a k sample permutation test for a given statistic.
MEDIAN TEST	Perform the k-sample test for equal medians.
PAGE TEST	Perform a Page test that k treatments have identical effects against the alternative of ordered treatment effects.
QUADE TEST	Perform a Quade test that k treatments are identical in a randomized complete block design.
VAN DER WAERDEN	Perform a Van Der Waerden (normal scores) test that k population distribution functions are equal.

Statistical Intervals, Tests and Summaries

BARTLETT TEST	Perform a Bartlett test for equal variances.
BIWEIGHT CONFIDENCE LIMITS	Generate biweight confidence limits for the mean.
CHI-SQUARE TEST	Carry out a 1-sample chi-square test for the standard deviation equal to a specified value.
COEFFICIENT OF DISPERSION CONFIDENCE LIMITS	Generates a confidence interval for the coefficient of dispersion.
COEFFICIENT OF QUARTILE DISPERSION CONFIDENCE LIMITS	Generates a confidence interval for the coefficient of quartile dispersion.
COEFFICIENT OF VARIATION CONFIDENCE LIMITS	Generates a confidence interval for the coefficient of variation.
COEFFICIENT OF VARIATION TEST	Perform either a one sample coefficient of variation test or a two sample coefficient of variation test.
COMMON COEFFICIENT OF VARIATION CONFIDENCE LIMITS	Generates a confidence interval for the common coefficient of variation for two or more groups for normally distributed data.
COMPLETE SPATIAL RANDOMNESS	Perform several tests for complete spatial randomness in the two-dimensional case.
CONFIDENCE LIMITS	Generate confidence limits for the mean.
CORRELATION CONFIDENCE LIMITS	Generates a confidence interval for the correlation between two response variables based on Fisher's normal approximation.
CROSS TABULATE (or TABULATE)	Tabulate counts or a specified statistic for one to eight group-id variables.
COX STUART TEST	Perform a Cox-Stuart test for trend for a univariate data set.
DIFFERENCE OF MEANS CONFIDENCE LIMITS	Generates confidence limits for the difference between two means.
DIFFERENCE OF PROPORTIONS CONFIDENCE LIMITS	Generates confidence limits for the difference between two proportions.
FISHER TWO SAMPLE RANDOMIZATION TEST	Perform a Fisher two sample randomization test for the equality of the means of two independent samples.
FLIGNER POLICELLO TEST	Perform a two sample Fligner-Policello test for equal medians.
F TEST	Perform a 2-sample F test for the equality of the standard deviations.
HEDGES G CONFIDENCE LIMITS	Generates a confidence interval for the Hedge's g statistic.
KENDALL TAU INDEPENDENCE TEST	Perform a Kendall tau test for whether two samples are independent (i.e., not correlated).
KLOTZ TEST	Perform a Klotz test that k samples have equal variances.
LEVENE TEST	Perform a Levene test that k samples have equal variances.
LIMITS OF DETECTION	Perform a limits of detection (LOD) analysis based on the ASTM E-2677 standard.
MEDIAN CONFIDENCE LIMITS	Generates confidence intervals for the median of a variable.
POSITIONAL TABULATION	Generate a position tabulation for one of Dataplot's supported univariate statistics for either a list of variables or a list of matrices.
PREDICTION BOUNDS	Generates prediction bounds for all m new observations given a previous sample.
PREDICTION LIMITS	Generates a prediction interval for the mean of one or more new observations given a previous sample.
PROPORTION CONFIDENCE LIMITS	Generates a confidence interval for proportions.
RANK CORRELATION INDEPENDENCE TEST	Perform a Spearman rho rank correlation test for whether two samples are independent (i.e., not correlated).
RANK SUM TEST	Perform a two sample rank sum test.
RATIO OF MEANS CONFIDENCE INTERVAL	Generates a confidence interval for the ratio of two means for paired samples.
RATIO OF STANDARD DEVIATIONS CONFIDENCE INTERVAL	Generates a confidence interval for the ratio of two standard deviations.
RATIO OF VARIANCES CONFIDENCE INTERVAL	Generates a confidence interval for the ratio of two variances.
RUNS	Perform a runs test for randomness.
SIEGEL TUKEY TEST	Perform a two sample Siegel-Tukey test that the standard deviations of two samples are equal.
SIGN TEST	Perform a one sample or a paired two sample sign test.
SIGNED RANK TEST	Perform a one sample or a paired two sample signed rank test.
SQUARED RANK TEST	Perform a squared ranks test that k samples have equal variances.
SD CONFIDENCE LIMITS	Generates a confidence interval for the standard deviation.
SD PREDICTION LIMITS	Generates a prediction interval for the standard deviation.
SUMMARY	Compute summary statistics.
TOLERANCE LIMITS	Generates normal, lognormal and non-parameteric tolerance intervals.
TRIMMED MEAN CONFIDENCE LIMITS	Generates a confidence interval for a trimmed mean.
T TEST	Perform a 1- or 2-sample t test for the mean.
TWO SAMPLE LINEAR RANK SUM TEST	Perform a two sample linear rank sum test for various scores.
TWO SAMPLE PERMUTATION TEST	Perform a two sample permutation test for a specified statistic.

Quality Control

CAPABILITY ANALYSIS	Generate a table of capability analysis statistics.
SINGLE SAMPLE ACCEPTANCE PLAN	Generates a single sample acceptance plan.

Multivariate

CLUSTER

Perform a cluster analysis.

Time Series Analysis

ARMA	Fit an autoregressive/moving average (ARMA) model (Box_Jenkins models).
SEASONAL LOWESS	Decompose a time series into trend, seasonal and residual components using techniques based on locally weighted least squares.

Distributional Analysis

ANDERSON DARLING K SAMPLE TEST	Perform a k-sample Anderson Darling test for equal distributions.
BASIS TOLERANCE LIMITS	Generates A-basis and B-basis tolerance intervals for the Weibull, normal and lognormal distributions.
BEST DISTRIBUTIONAL FIT	Perform a best distributional fit analysis.
CHI-SQUARE TWO SAMPLE TEST	Perform a two-sample chi-square test for common distribution.
COMMON WEIBULL SHAPE PARAMETER	Test whether k samples that follow a 2-parameter Weibull distribution have a common shape parameter.
DISTRIBUTIONAL LIKELIHOOD RATIO TEST	Distinguish which of two specified distributions better fit a data set based on the likelihood ratio test.
... GOODNESS OF FIT	Perform Anderson-Darling, Kolmogorov-Smirnov, chi-square, or PPCC distributional goodness of fit tests.
JARQUE BERA TEST	Perform a Jarque-Bera test for normality.
KOLMOGOROV SMIRNOV TWO SAMPLE TEST	Perform a two-sample Kolmogorov-Smirnov test for common distribution.
MAXIMUM LIKELIHOOD	Estimate the parameters of a distribution via maximum likelihood.
MCCOOL WEIBULL LOCATION TEST	Perform the McCool test to distinguish between a 2-parameter and a 3-parameter Weibull distribution.
POISSON DISPERSION TEST	Perform a Poisson dispersion test for Poissonality.
WILKS SHAPIRO NORMALITY TEST	Perform a Wilks-Shapiro test for normality.

Reliability/Extreme Value Analysis

CME	Estimate the parameters of a generalized Pareto distribution using the conditional mean exceedance (CME) method.
DEHAAN	Estimate the parameters of a generalized Pareto distribution using the de Haan method.
RELIABILITY TREND TEST	Compute tests to determine whether or not the repair times of a system show significant trend (either improvement or degradation). Specifically, it computes the reverse arrangement test, the military handbook test and the Laplace test.

Randomness

CUSUM TEST	Perform a cumulative sum test for randomness.
FREQUENCY TEST	Perform a frequency test for randomness.
LJUNG-BOX TEST	Perform a Ljung-Box test for randomness.
MEAN SUCCESSIVE DIFFERENCES TEST	Perform a mean successive differences test for randomness for a univariate data set (also known as the Durbin-Watson test).

Outliers

DAVID TEST	Perform the David, Hartley and Pearson test for univariate outliers from a normal distribution.
DIXON TEST	Perform the Dixon test for univariate outliers from a normal distribution.
EXTREME STUDENTIZED DEVIATE TEST	Perform a generalized extreme studentized deviate (ESD) test for outliers in a normal distribution.
GRUBBS TEST	Perform the Grubbs test for a univariate outlier from a normal distribution.
KURTOSIS OUTLIER TEST	Perform the kurtosis test for a univariate outlier from a normal distribution.
SKEWNESS OUTLIER TEST	Perform the skewness test for a univariate outlier from a normal distribution.
TIETJEN MOORE TEST	Perform a Tietjen-Moore test for outliers.

Interlaboratory Analysis

COCHRAN VARIANCE OUTLIER TEST	Perform Cochran's variance outlier test to assess the homogeneity of variances in the one-factor case.
CONSENSUS MEANS	Generate the tables for either a one-sample or a two-sample proficiency test as defined by the ASTM E 2489 - 06 standard.
E691 INTERLAB	Generate the tables for an interlab analysis as described by the ASTM E 691 - 99 standard.
PROFICIENCY TEST	Generate the tables for either a one-sample or a two-sample proficiency test as defined by the ASTM E 2489 - 06 standard.

Classification/Categorical Analysis

BINOMIAL PROPORTION TEST	Perform a large sample hypothesis test for the equality of two binomial proportions.
CHI-SQUARE TEST OF INDEPENDENCE	Perform a chi-square test of independence for a two-way contingency table.
FISHER EXACT TEST	Perform a Fisher exact test of independence for a two-way contingency table.
MANTEL-HAENSZEL TEST	Perform a Mantel-Haenszel test of a series of fourfold (2x2) tables.
MCNEMAR TEST	Perform a McNemar test for independence in a 2x2 table.
ODDS RATIO CHI-SQUARE TEST	Perform an odds ratio chi-square test of a series of fourfold (2x2) tables.
ODDS RATIO INDEPENDENCE TEST	Perform a log odds ratio test of independence for a 2x2 contingency table.

The ... in some of the commands indicates user-defined options for the command, as in:

Many mathematical, statistical, and matrix capabilities are available as subcommands under the LET command. The individual subcommands available under LET are documented in Volume II of the DATAPLOT Reference Manual.