least-squares
Error-minimizing fit method
Least-squares is a mathematical method for finding the best-fitting curve or line through a set of data points by minimizing the sum of the squared differences between observed values and predicted values.
The approach underlies linear regression and countless statistical applications: a least-squares fit, least-squares regression.
Squaring the differences ensures that positive and negative errors don't cancel out.
Statistical straight-line fitting method
- curve fittingApproximating data mathematically
- best fitMost suitable option
- residualsOngoing compensation for rebroadcasts
- slopeAngled terrain or steepness
intercept · coefficients · dependent variable · independent variable · trend line · scatter plot · extrapolation · interpolation
Spread around the mean
- standard errorStatistic's expected deviation measure
- confidence intervalEstimated bounds for population parameter
- hypothesis testingStatistical method for evaluating claims
- degrees of freedomNumber of independent variables
ANOVA · correlation · outliers
Matrix as orthogonal-triangular product
- linear algebraMathematics of vector spaces
- MATLABMatrix-focused computing platform
- ill-conditionedBad-tempered, irritable
Making as small as possible
- convergenceProcess of approaching sameness
- regularizationPenalty preventing model complexity
linear regression
Statistical straight-line fitting method
- curve fittingApproximating data mathematically
- best fitMost suitable option
- residualsOngoing compensation for rebroadcasts
slope · intercept · coefficients · dependent variable · independent variable · trend line · scatter plot · extrapolation · interpolation · estimation
variance
Spread around the mean
- standard errorStatistic's expected deviation measure
- confidence intervalEstimated bounds for population parameter
- hypothesis testingStatistical method for evaluating claims
QR decomposition
Matrix as orthogonal-triangular product
- linear algebraMathematics of vector spaces
- MATLABMatrix-focused computing platform
- ill-conditionedBad-tempered, irritable
minimization
Making as small as possible
- convergenceProcess of approaching sameness
- regularizationPenalty preventing model complexity