Interactive Statlets - Modeling
| Statlet |
| Curve-Fitting |
| Exponential Smoothing |
| Kriging |
| Power Transformations |
| Process Capability Analysis |
| Surface-Fitting |
Curve-Fitting
The Curve-Fitting Statlet fits linear and nonlinear regression models involving a dependent variable Y and an independent variable X. Using the Statlet control bar, you may interactively investigate the effect of individual data points on the fitted model and its confidence and prediction limits. Using a vertical cursor, you can also make predictions at specific values of X. A LOWESS smooth may also be added to the plot to compare it with the fitted model.
Exponential Smoothing
This Statlet applies various types of exponential smoothers to a time series. It generates forecasts with associated forecast limits. Using the Statlet controls, the user may interactively change the values of the smoothing parameters to examine their effect on the forecasts.
The types of exponential smoothers included are:
- Brown’s simple exponential smoothing with smoothing parameter a.
- Brown’s linear exponential smoothing with smoothing parameter a.
- Holt’s linear exponential smoothing with smoothing parameters a and b.
- Brown’s quadratic exponential smoothing with smoothing parameter a.
- Winters’ seasonal exponential smoothing with smoothing parameters a, b, and g.
This Statlet implements a procedure called Kriging, which is widely used to analyze geospatial data. Given a set of measurements taken on a variable at various locations within a two-dimensional region, estimates are derived for the value of that variable throughout the region. The primary output is a map of the estimated value, together with the variance of the estimate.
This Statlet may be used to explore the effect of applying various power transformations to a column of numeric data. It may be used to find the transformation that makes the transformed data most closely characterized by a normal distribution. The controls on the toolbar allow the user to interactively change the power. Alternatively, the Box-Cox approach may be used to find an optimal power.
This Statlet performs a capability analysis on measurement data. The data may be collected one at a time (individuals data) or in groups. Any of 21 probability distributions may be selected, although the normal distribution is used by default.
The Statlet will calculate:
- Capability indices (both long-term and short-term).
- DPM (defects per million).
- Goodness-of-fit tests for the selected distribution.
- Statistical tolerance limits (for many of the available distributions).
The data may also be transformed using a standard power transformation.
The Surface-Fitting Statlet fits linear and nonlinear regression models involving a dependent variable Y and two independent variables X1 and X2. Using the Statlet control bar, you may interactively investigate the effect of transforming one or more of the variables. A LOWESS smooth may also be added to the plot to compare it with the fitted model.
