def totalSumOfSquares(y): return sum([v**2 for v in stat.de_mean(y)])
def totalSumOfSquares(y): return sum([v ** 2 for v in stat.de_mean(y)])
def leastSquaresFit(x, y): beta = stat.correlation(x, y) * stat.stdDeviation(y) / stat.stdDeviation(x) alpha = stat.mean(y) - beta * stat.mean(x) return alpha, beta
def leastSquaresFit(x, y): beta = stat.correlation(x, y) * stat.stdDeviation(y) / stat.stdDeviation(x) alpha = stat.mean(y) - beta * stat.mean(x) return alpha, beta