![]() ![]() Its internal numerical algorithms can avoid or handle such errors. ![]() It is useful, for example, for analyzing gains and losses over a large data set. In contrast, the chart trendline algorithm works the original data. A polynomial trendline is a curved line that is used when data fluctuates. Part of the reason for that is: the input to LINEST is an array of values raised to powers up to 6 (in your case), which can encounter rounding error and computational limitations. LINEST sometimes returns an error or invalid coefficients (typically zero) when chart trendlines work properly. Apparently, there numerical methods for regression are not identical.Ģ. LINEST and chart trendlines do not always produce the same coefficients. That will ensure that you use values with 15 significant digits of precision, the best that Excel will format.Įven better: use LINEST (or LOGEST) to generate "the coefficients". Why not change the trend line equation insertion function so that it inserts a plain text box with the required text instead of a trend line. But I think it is important to note the following.ĭo not use the coefficients constants as they appear by default in the trendline formula.Īny arithmetic based on those rounded values is likely to be off significantly.Īt a minimum, format the "trendline label" to display coefficients in Scientific format with 14 decimal places. I do not have time to help you with the larger problem. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |