TestInfo_svd | R Documentation |

The test information curve is the trajectory of joint variation of all the surprisal curves within the ambient space of dimension the total number of curves. But usually a very high percent of the shape variation in the curve can be represented in either two or three dimensions using the singular value decomposition of a matrix of total curve values over a fine mesh. The resulting approximation is converted to a set of surprisal curve values.

```
TestInfo_svd(scrfine, SfdList, itemindex=1:n, nharm=2)
```

`scrfine` |
A fine mesh of values over which the image is plotted. This is usually either the score index theta or the test arc length. |

`SfdList` |
A list vector of length n, the number of test items. Each list in the vector contains values of the surprisal curves for that item. |

`itemindex` |
A vector of item indices to be used in the approximation. |

`nharm` |
The number of dimension in the approximation, usually either two or three. |

The approximation is returned as a surprisal functional data object, and so are the percentages of the total variation fit by each dimension in the approximation.

Juan Li and James Ramsay

Ramsay, J. O., Li J. and Wiberg, M. (2020) Full information optimal scoring. Journal of Educational and Behavioral Statistics, 45, 297-315.

Ramsay, J. O., Li J. and Wiberg, M. (2020) Better rating scale scores with information-based psychometrics. Psych, 2, 347-360.

Embedding an R snippet on your website

Add the following code to your website.

For more information on customizing the embed code, read Embedding Snippets.