StatControlCharts.QCPChart Method

Overload List

#	Signature	Description
1	procedure QCPChart(const Data: TVec; const SampleSize: TVec; const DrawVec: TVec; out CL: Double; const UCL: TVec; const LCL: TVec; Confidence: Double);	In this case each sample can have different size. You must store sizes in SampleSize vector.
2	procedure QCPChart(const Data: TVec; SampleSize: Integer; const DrawVec: TVec; out CL: Double; out UCL: Double; out LCL: Double; Confidence: Double);	P-Chart.

Overload 1: procedure QCPChart(const Data: TVec; const SampleSize: TVec; const DrawVec: TVec; out CL: Double; const UCL: TVec; const LCL: TVec; Confidence: Double);

In this case each sample can have different size. You must store sizes in SampleSize vector.

#	Name	Description
1	Data	Data to be analyzed. Each value represents number of defects.
2	Confidence	Confidence level for upper and lower control limit. Confidence must lie in the (0,1) interval.
3	SampleSize	Sample size. Can be integer or vector.
4	DrawVec	Returns values to be drawn.
5	CL	Returns control Chart centerline.
6	UCL	Returns control Chart upper control limit.
7	LCL	Returns control Chart lower control limit.

Result: stored in self (calling object)

Remarks:

An exeption is raised if Data and SampleSize length do not match.

See Also: !:TQCSeries, QCSeries, StatControlCharts.QCNPChart, StatControlCharts.QCUChart, StatControlCharts.QCCChart

Overload 2: procedure QCPChart(const Data: TVec; SampleSize: Integer; const DrawVec: TVec; out CL: Double; out UCL: Double; out LCL: Double; Confidence: Double);

P-Chart.

#	Name	Type	Description
1	Data	TVec
2	SampleSize	Integer
3	DrawVec	TVec
4	CL	Double
5	UCL	Double
6	LCL	Double
7	Confidence	Double	scalar

Result: stored in self (calling object)

Remarks:

Calculates the P-Chart (Control chart for proportions) drawing values, center line, upper and lower control limits. Control limits are based on the normal approximation to the binomial distribution. When p is small, the normal approximation may not always be adequate. In such cases, we may use control limits obtained directly from a table of binomial probabilities. If P is small, the lower control limit obtained from the normal approximation may be a negative number. If this should occur, it is customary to consider zero as the lower control limit.

Note
The assumption is all samples have the same SampleSize.

Examples

Uses StatControlCharts, MtxExp, Math387, MtxVecTee, StatSeries;
procedure Example(Series1: TQCSeries);
var CL, UCL, LCL : double;
Data: Matrix;
DrawVec: Vector;
begin
    Data.LoadFromFile('data.mtx');
    QCPChart(Data,10, DrawVec,CL,UCL,LCL,0.05);
    // setup limit lines
    Series1.UCL := UCL;
    Series1.LCL := LCL;
    Series1.CL := CL;
    // now draw actual data
    DrawValues(DrawVec,Series1);
end;