Past exam of the mathematics course of the University of Cambridge 2001 ib Paper 4 3D Solution Created 2026-09-24 Updated 2026-10-14
Assume , so the slope in this linear regression through the origin is identifiable. Expanding the residual sum of squares givesDifferentiation gives the unique least-squares estimator and its normal distribution:For , estimate the unknown variance byThe fitted component and orthogonal residual of the Gaussian vector are independent, and has the chi-squared distribution with degrees of freedom. Under the null hypothesis,The Student t test for regression through the origin rejects at significance level when , where the subscript denotes the corresponding quantile of Student's t-distribution. If all , the data contain no information about ; if , no residual degree of freedom is available for this unknown-variance test.
Past exam of the mathematics course of the University of Cambridge 2004 ib Paper 4 9H Solution Created 2026-09-24 Updated 2026-10-14
Write . When , minimizing gives the strictly convex quadratic normal equation . The least-squares estimator is thereforeThis is linear regression through the origin, with no fitted intercept. For , let and . An orthonormal change of coordinates in the Gaussian vector separates the unit design direction from its orthogonal residual directions. The first coordinate is normal with mean and variance ; the remaining coordinates are independent centered normals with that variance. Consequentlyand these variables are independent. Thus under the null, the Student t test for regression through the origin statistic isFor a prescribed significance level , reject the two-sided null when . The two-sided p-value is . There is one fitted coefficient, so the variance degrees of freedom are , not .
The assumptions and matter. If all , the distribution contains no information about and no informative test is possible. With one nonzero design observation there is no residual variance degree of freedom, so the stated unknown-variance t test cannot be constructed.
Past exam of the mathematics course of the University of Cambridge 2005 ib Paper 4 19D i Solution Created 2026-09-24 Updated 2026-10-14
Assume , which is necessary to identify the slope in linear regression through the origin. The joint normal likelihood has logarithm, apart from a constant,Complete the square in . With and ,The maximum likelihood estimation therefore first minimizes at ; differentiating in then maximizes atThis is a genuine finite maximum when . If all , the slope is unidentifiable. If , the likelihood is unbounded as , so no positive-variance maximum exists. For nonzero design and , zero residual has probability zero under the stated positive-variance model.
Past exam of the mathematics course of the University of Cambridge 2019 ib Paper 4 19H a Solution Created 2026-09-24 Updated 2026-09-29
Apart from terms independent of , the Gaussian log-likelihood isDifferentiating with respect to givesThe unique zero, and hence the maximum-likelihood estimate, isThe same value minimizes the residual sum of squares , since maximizing the Gaussian likelihood for fixed is equivalent to minimizing this sum. It is therefore also the least-squares estimator.
Rearrange the given torsion balance equilibrium relation asA useful choice, preserving equal measurement uncertainties on the vertical axis, isWith angle measured in radians, is dimensionless and has units , so has units , as required. The four values, in the order of the original table, areThe corresponding values are , each with standard uncertainty . The uncertainty of is negligible by assumption, making linear regression through the origin appropriate for the proposed model.