生物统计分析软件GraphPad Prism 8 已正式发布
2018年10月，生物统计分析软件GraphPad Prism 8版本已正式发布。新版本Windows及Mac两种平台，增强了数据可视化及图形定制功能，导航也直观，统计分析功能。
1、的组织您的数据。GraphPad Prism有八种不同类型的数据表，为用户要运行的分析而格式化。这样用户可以更、更正确的输入数据，选择合适的分析并创建令人惊喜的图形。
2、执行正确的分析。GraphPad Prism提供了广泛的分析库，从常见到特异性非线性回归，t检验，非参数比较，单因素，双因素和三因子方差分析，列联表，生存分析等等。分析都有清单，以帮助您了解所需的统计假设，并确认您已选择的测试。
3、一键式回归分析。选择方程式，Prism进行曲线的其余拟合，显示结果和函数参数表，在图形上绘制曲线，并插入未知值。
4、编程即可自动完成工作。减少分析和绘制一组实验的繁琐步骤。通过创建模板，复制系列或克隆图表可以复制您的工作，从而节省您数小时的设置时间。使用Prism Magic一键单击，对一组图形应用的外观。
5、无数种自定义图表的方法。GraphPad Prism可以创建所需的图形。选择图形类型，并自定义部分 - 数据的排列方式，数据点的样式，标签，字体，颜色等等。定制选项是的。
6、现在有八种数据表。新：多变量数据表。每行代表不同的主题，每列是不同的变量，允许您执行多元线性回归（泊松回归），将数据子集提取到表类型，或选择和转换数据的子集。
新增内容：嵌套数据表。分析和可视化相关组内子集的数据; 使用这些表中的数据执行嵌套t检验和嵌套单向ANOVA。
Discover the Breadth of Statistical Features Available in Prism 8
Statistical Comparisons
· Paired or unpaired t tests. Reports P values and confidence intervals.
· Automatically generate volcano plot (difference vs. P value) from multiple t test analysis.
· Nonparametric Mann-Whitney test, including confidence interval of difference of medians.
· Kolmogorov-Smirnov test to compare two groups.
· Wilcoxon test with confidence interval of median.
· Perform many t tests at once, using False Discovery Rate (or Bonferroni multiple comparisons) to choose which comparisons are discoveries to study further.
· Ordinary or repeated measures ANOVA followed by the Tukey, Newman-Keuls, Dunnett, Bonferroni or Holm-Sidak multiple comparison tests, the post-test for trend, or Fisher’s Least Significant tests.
· One-way ANOVA without assuming populations with equal standard deviations using Brown-Forsythe and Welch ANOVA, followed by appropriate comparisons tests (Games-Howell, Tamhane T2, Dunnett T3)
· Many multiple comparisons test are accompanied by confidence intervals and multiplicity adjusted P values.
· Greenhouse-Geisser correction so repeated measures one-, two-, and three-way ANOVA do not have to assume sphericity. When this is chosen, multiple comparison tests also do not assume sphericity.
· Kruskal-Wallis or Friedman nonparametric one-way ANOVA with Dunn's post test.
· Fisher's exact test or the chi-square test. Calculate the relative risk and odds ratio with confidence intervals.
· Two-way ANOVA, even with missing values with some post tests.
· Two-way ANOVA, with repeated measures in one or both factors. Tukey, Newman-Keuls, Dunnett, Bonferroni, Holm-Sidak, or Fisher’s LSD multiple comparisons testing main and simple effects.
· Three-way ANOVA (limited to two levels in two of the factors, and any number of levels in the third).
· Analysis of repeated measures data (one-, two-, and three-way) using a mixed effects model (similar to repeated measures ANOVA, but capable of handling missing data).
· Kaplan-Meier survival analysis. Compare curves with the log-rank test (including test for trend).
· Comparison of data from nested data tables using nested t test or nested one-way ANOVA (using mixed effects model).
Nonlinear Regression
· Fit one of our 105 built-in equations, or enter your own. Now including family of growth equations: exponential growth, exponential plateau, Gompertz, logistic, and beta (growth and then decay).
· Enter differential or implicit equations.
· Enter different equations for different data sets.
· Global nonlinear regression – share parameters between data sets.
· Robust nonlinear regression.
· Automatic outlier identification or elimination.
· Compare models using extra sum-of-squares F test or AICc.
· Compare parameters between data sets.
· Apply constraints.
· Differentially weight points by several methods and assess how well your weighting method worked.
· Accept automatic initial estimated values or enter your own.
· Automatically graph curve over specified range of X values.
· Quantify precision of fits with SE or CI of parameters. Confidence intervals can be symmetrical (as is traditional) or asymmetrical (which is more accurate).
· Quantify symmetry of imprecision with Hougaard’s skewness.
· Plot confidence or prediction bands.
· Test normality of residuals.
· Runs or replicates test of adequacy of model.
· Report the covariance matrix or set of dependencies.
· Easily interpolate points from the best fit curve.
· Fit straight lines to two data sets and determine the intersection point and both slopes.
Column Statistics
· Calculate descriptive statistics: min, max, quartiles, mean, SD, SEM, CI, CV, skewness, kurtosis.
· Mean or geometric mean with confidence intervals.
· Frequency distributions (bin to histogram), including cumulative histograms.
· Normality testing by four methods (new: Anderson-Darling).
· Lognormality test and likelihood of sampling from normal (Gaussian) vs. lognormal distribution.
· Create QQ Plot as part of normality testing.
· One sample t test or Wilcoxon test to compare the column mean (or median) with a theoretical value.
· Identify outliers using Grubbs or ROUT method.
· Analyze a stack of P values, using Bonferroni multiple comparisons or the FDR approach to identify "significant" findings or discoveries.
Linear Regression and Correlation
· Calculate slope and intercept with confidence intervals
· Force the regression line through a specified point.
· Fit to replicate Y values or mean Y.
· Test for departure from linearity with a runs test.
· Calculate and graph residuals in four different ways (including QQ plot).
· Compare slopes and intercepts of two or more regression lines.
· Interpolate new points along the standard curve.
· Pearson or Spearman (nonparametric) correlation.
· Multiple linear regression (including Poisson regression) using the new multiple variables data table.
Clinical (Diagnostic) Lab Statistics
· Bland-Altman plots.
· Receiver operator characteristic (ROC) curves.
· Deming regression (type ll linear regression).
Simulations
· Simulate XY, Column or Contingency tables.
· Repeat analyses of simulated data as a Monte-Carlo analysis.
· Plot functions from equations you select or enter and parameter values you choose.
Other Calculations
· Area under the curve, with confidence interval.
· Transform data.
· Normalize.
· Identify outliers.
· Normality tests.
· Transpose tables.
· Subtract baseline (and combine columns).
· Compute each value as a fraction of its row, column or grand total.
