GROWTH in WPS Spreadsheet: Predict an Exponential Growth Curve

For x values 1, 2, 3 and y values 6, 12, 24, =GROWTH(B2:B4,A2:A4,4,TRUE) has an independent expected result of 48. The exact relationship is y=3×2^x: the multiplier is 2 per x-unit, while the fitted constant is 3.

GROWTH(known_y's,known_x's,new_x's,const)

• known_y's: required numeric observations, all strictly positive. The source documents #NUM! when any known y is zero or negative.
• known_x's: optional matching predictor values. If omitted, WPS assumes 1,2,3,… with the size of known_y’s.
• new_x's: optional predictor values at which to calculate fitted y. If omitted, they are the known x values. If both x arguments are omitted, the implicit sequence is used for both.
• const: optional logical value. TRUE or omission fits b normally in y=b×m^x. FALSE fixes b=1, then refits the multiplier. It does not fix b=0.

For one predictor, keep known x and y ranges the same shape and length. With several predictors, the y data must be one row or column. When y occupies one column, each predictor occupies its own column, and new_x’s must have the same predictor-column count. For row-oriented y, the roles of rows and columns are reversed.

Put the following numbers in A1:B4:

Put 4 in D2. In E2 enter =GROWTH(B2:B4,A2:A4,D2,TRUE). The independent expectation is 48. Change D2 to 5 and expect 96. These are model predictions; actual future sales, counts or other observations need not follow the same pattern.

The independent calculation takes logarithms: ln(y)=ln(3)+x ln(2). Exponentiating the fitted line gives y=3×2^x. This shows why multiplying the original y values by a fixed amount is a different model from adding a fixed amount.

=GROWTH(B2:B4,A2:A4) requests fitted values at x=1,2,3, independently expected as 6,12,24. A multi-cell result needs an appropriate array-output workflow in your installed version. WPS’s historical lesson describes selecting the output range and entering an array formula; that does not prove all current builds lack automatic spilling.

To isolate the FALSE switch, use y values 2,4,8 in C2:C4 with the same x values. =GROWTH(C2:C4,A2:A4,4,FALSE) is independently expected to produce 16, since b=1 and m=2. On the original 6,12,24 data, FALSE would refit the model; it would not simply remove the factor 3 from an already fitted prediction.

A zero or negative y cannot be handled by this exponential fit as documented. Do not add a constant just to silence the error without reconsidering what model that changes. Ensure x and y rows represent the same observations and exclude text headings. A date serial is a numeric x value, but rescaling time to periods since a chosen start often makes the intercept easier to interpret.

For multi-point predictions, select enough output cells under the historical array workflow; if only the first result appears, inspect the version’s array behavior. Use local separators when entering formulas. Extrapolation far beyond the observed x range can magnify a poor model rapidly. Inspect residuals and compare with a linear model when a fixed increment, rather than a fixed ratio, better fits the context.

The official WPS GROWTH lesson was checked on October 19, 2026. The captured source does not establish a specific edition or numeric build. This Chinese first-party documentation is not proof of universal English-global, Mac, Linux, web or mobile support. Introduction and retirement versions remain unknown. All numerical results in this guide are independently calculated expectations, not native WPS test results or borrowed Excel outputs. Current GUI access was unavailable; no current-application screenshots or native execution are claimed.

LN, EXP. Browse the WPS function library.