The STEYX function in Google Sheets is a powerful tool for statistical analysis, specifically designed to compute the standard error of the predicted y-values in a linear regression model. This function is particularly useful for assessing the accuracy of predictions made by the regression equation, providing insights into the variability of predicted values based on given x-values.

Syntax

STEYX(known_y's, known_x's)

• known_y’s: An array or range representing the dependent variable (y-values) in your dataset.
• known_x’s: An array or range representing the independent variable (x-values) in your dataset.

Example #1

STEYX(A1:A10, B1:B10)

This function calculates the standard error of the predicted y-values based on y-values found in cells A1 through A10 and corresponding x-values in B1 through B10. For example, if the standard error is calculated as 2.5, this indicates the average error in predicting y-values from x-values in this range.

Example #2

STEYX(D1:D20, E1:E20)

In this instance, the function evaluates the standard error of the predictions using D1 to D20 for the dependent variable and E1 to E20 for the independent variable. A result of 1.8 would suggest that the predictions made are relatively precise within an average error margin of 1.8 units on the y-axis.

Example #3

STEYX(G1:G15, H1:H15)

This example assesses the standard error with y-values in G1 to G15 and x-values in H1 to H15. A result calculated as 3.1 indicates a broader range of uncertainty in the predicted y-values derived from the regression analysis.

Error handling

• N/A: This error arises if either known_y’s or known_x’s ranges are empty or do not contain any numbers.
• VALUE!: Occurs when the inputs provided are not valid ranges or contain non-numeric data.
• DIV/0!: This error is triggered if there is no valid data in known_x’s or known_y’s after processing the input, typically when all values are the same.

Conclusion

The STEYX function is an essential tool for anyone working with statistical data, especially within regression analysis. It facilitates an understanding of the error associated with predictions, thereby enhancing the reliability of data-driven decisions. By accurately calculating the standard error for predicted values, users can gain deeper insights into the precision of their regression models.