Thanks to Kit Baum, version 5.7 of ASROL is available on SSC now. To install
Major Updates
There are three major updates in version 5.7 which I would like to highlight here.
1. Changes made to the window() option
asrol’s version 5.0 and above introduces a more flexible window to identify observation in a given range. Previously, the window() option of asrol would take two inputs: the first one being the range variable (such as date) and the second input as the length of the rolling window. In the older versions, the window would always look backward. This has changed in version 5.
The window argument can now take up to three arguments. The window can now look backward, forward, and both back and forward. More details can be read in the help file or online here https://fintechprofessor.com/asrol-f...option-window/
2. Improved algorithm for rolling window indices
This version of asrol (version 5.7) significantly improves the calculation speed of the required statistics, thanks to the development of a more efficient algorithm for extracting rolling window indices. This has resulted in significant speed advantage for asrol compared to its previous versions or other available programs. The speed efficiency matters more in larger datasets. While writing the source code of asrol, I took utmost care in making choices among available options. Therefore, every line of code had to undergo several tests to ensure accuracy and speed. In fact, there is a long list of of built-in routines in asrol which are meant to handle different data structures. asrol intelligently identifies data structures and applies the most relevant routine from its library. Hence, asrol speed efficiency is ensured whether the data is rectangular (balanced panel), non-rectangular, has duplicates, has missing values, or has both duplicates and missing values.
3. More statistics
This version of asrol has added seven additional statistics, taking the total number of supported statistics to 20. The additional statistics are:
2.1 skewness: Returns skewness of non-missing values
2.2 kurtosis: Returns kurtosis of non-missing values
2.3 max: Returns the largest value in a given window
2.4 max2: Returns the second largest value in a given window
2.5 max3: Returns the third largest value in a given window
2.6 max4: Returns the fourth largest value in a given window
2.7 max5: Returns the fifth largest value in a given window
For examples and uses of asrol, visit this page https://fintechprofessor.com/asrol-f...tics-in-stata/
Code:
ssc install asrol, replace
Major Updates
There are three major updates in version 5.7 which I would like to highlight here.
1. Changes made to the window() option
asrol’s version 5.0 and above introduces a more flexible window to identify observation in a given range. Previously, the window() option of asrol would take two inputs: the first one being the range variable (such as date) and the second input as the length of the rolling window. In the older versions, the window would always look backward. This has changed in version 5.
The window argument can now take up to three arguments. The window can now look backward, forward, and both back and forward. More details can be read in the help file or online here https://fintechprofessor.com/asrol-f...option-window/
2. Improved algorithm for rolling window indices
This version of asrol (version 5.7) significantly improves the calculation speed of the required statistics, thanks to the development of a more efficient algorithm for extracting rolling window indices. This has resulted in significant speed advantage for asrol compared to its previous versions or other available programs. The speed efficiency matters more in larger datasets. While writing the source code of asrol, I took utmost care in making choices among available options. Therefore, every line of code had to undergo several tests to ensure accuracy and speed. In fact, there is a long list of of built-in routines in asrol which are meant to handle different data structures. asrol intelligently identifies data structures and applies the most relevant routine from its library. Hence, asrol speed efficiency is ensured whether the data is rectangular (balanced panel), non-rectangular, has duplicates, has missing values, or has both duplicates and missing values.
3. More statistics
This version of asrol has added seven additional statistics, taking the total number of supported statistics to 20. The additional statistics are:
2.1 skewness: Returns skewness of non-missing values
2.2 kurtosis: Returns kurtosis of non-missing values
2.3 max: Returns the largest value in a given window
2.4 max2: Returns the second largest value in a given window
2.5 max3: Returns the third largest value in a given window
2.6 max4: Returns the fourth largest value in a given window
2.7 max5: Returns the fifth largest value in a given window
For examples and uses of asrol, visit this page https://fintechprofessor.com/asrol-f...tics-in-stata/
