Texas Instruments TI-82 STATS Manual Book page 227

PwrReg
b
(ax )
Logistic
c / (1+aä ä ä ä e
Lbx )
SinReg
a sin(bx+c)+d
(power regression) fits the model equation y=ax
PwrReg
data using a least-squares fit and transformed values ln(x) and
ln(y). It displays values for
also displays values for
[Xlistname
PwrReg
fits the model equation y=c / (1+aäe
Logistic
an iterative least-squares fit. It displays values for
[Xlistname
Logistic
(sinusoidal regression) fits the model equation
SinReg
y=a sin(bx+c)+d to the data using an iterative least-squares fit. It
displays values for
required. At least two data points per cycle are required in order
to avoid aliased frequency estimates.
[iterations,Xlistname,Ylistname,period,regequ]
SinReg
iterations is the maximum number of times the algorithm will
iterate to find a solution. The value for iterations can be an
integer ‚ 1 and  16; if not specified, the default is 3. The
algorithm may find a solution before iterations is reached.
Typically, larger values for iterations result in longer execution
times and better accuracy for
A period guess is optional. If you do not specify period, the
difference between time values in Xlistname must be equal and
the time values must be ordered in ascending sequential order. If
you specify period, the algorithm may find a solution more
quickly, or it may find a solution when it would not have found
one if you had omitted a value for period. If you specify period,
the differences between time values in Xlistname can be
unequal.
Note: The output of
Radian/Degree
mode setting.
A example is shown on the next page.
SinReg
and ; when
a b
2
and .
r r
Ylistname freqlist
, ,
Ylistname freqlist
, ,
, , , and . At least four data points are
a b c d
SinReg
SinReg
is always in radians, regardless of the
DiagnosticOn
regequ]
,
Lbx ) to the data using
, , and
a b
regequ]
,
, and vice versa.
Statistics 12–27
b
to the
is set, it
.
c