Returns values along a trend curve (e.g. linear, quadratic, exponential, etc.) at time T+m.
Syntax
X is the univariate time series data (a one dimensional array of cells (e.g. rows or columns)).
Order is the time order in the data series (i.e. the first data point's corresponding date (earliest date=1 (default), latest date=0)).
Order  Description 

1  ascending (the first data point corresponds to the earliest date) (default) 
0  descending (the first data point corresponds to the latest date) 
Trend_type is the model description flag for the trend function (1 = Linear (default), 2 = Polynomial, 3 = Exponential, 4 = Logarithmic, 5 = Power).
Order  Description 

1  Linear (default) 
2  Polynomial 
3  Exponential 
4  Logarithmic 
5  Power 
POrder is the polynomial order. This is only relevant for a polynomial type of trend and is ignored for all others. If missing, POrder = 1.
Const is the constant or the intercept value to fix (e.g. zero). If missing, an intercept will not be fixed and is computed normally.
Horizon is the forecast time/horizon beyond the end of X. If missing, a default value of 0 (latest or end of X) is assumed.
Return_type is a switch to select the return output (1 = Forecast value (default), 2 = Upper limit, 3 = Lower Limit, 4 = RSquared ).
Method  Description 

1  Forecast value (default) 
2  C.I. upper limit 
3  C.I. lower limit 
4  RSquared 
Alpha is the statistical significance or confidence level (i.e. alpha). If missing or omitted, an alpha value of 5% is assumed.
Remarks
 NxTrend supports the following trend functions:
$$ \begin{cases} \mathrm{Linear} & Y_t=\alpha + \beta \times t \\ \mathrm{Polynomial} & Y_t=\alpha + \beta_1 \times t + \beta_2 \times t^2 + \cdots + \beta_N \times t^N \\ \mathrm{Exponential:} & Y_t= \alpha \times e^{\beta \times t} \\ \mathrm{Logarithm:} & Y_t= \alpha + \beta \times \ln(t) \\ \mathrm{Power:} & Y_t= \alpha \times t^{\beta} \\ \end{cases} $$  For exponential and logarithmic trends, the intercept value is not permitted to be fixed, and thus is ignored.
 The Excel trend builtin function (i.e. "TREND") is a different function, not part of NumXL, and should not be confused with NxTrend.
 The polynomial order argument must be a positive integer.
 The trend function's coefficients that best fit your data are estimated using the "least squares" method.
 The time series may include missing values (e.g. #N/A) at either end.
Examples
Example 1:


Files Examples
References
 Hamilton, J .D.; Time Series Analysis , Princeton University Press (1994), ISBN 0691042896
 Tsay, Ruey S.; Analysis of Financial Time Series John Wiley & SONS. (2005), ISBN 0471690740
Comments
Article is closed for comments.