At the start of the year, the Chief Medical Officer announced new guidelines for alcohol consumption. The communication of these new guidelines was recently identified as being of concern by the Royal Statistical Society. In this blog we investigate what these concerns are and how they impact the interpretation of these guidelines.
read moreClassification means assigning an outcome to an individual or case, usually for the purpose of making a decision. Examples include predicting which individuals will default on personal debt to decide who could be offered a credit card, or predicting which visitors to a retail website will make a purchase. In this blog we will discuss some ways of measuring the performance of a classification model.
read moreA recent BBC article discussed an apparent north-south divide in GCSE attainment. We've investigated these data in more detail to find out whether there is statistical evidence of this divide and whether it has changed over time.
read moreIn a recent blog we introduced binary regression models as a method for predicting the probability of a binary outcome. Here, we examine some methods for assessing the performance of these models together with strategies for improving them.
read moreMost statistical analyses assume that the data collected are from a simple random sample of the population of interest. However, it’s not always possible or practical to take a SRS, and complex samples can be used to create more efficient or cheaper sampling designs.
read moreWe recently discussed how a logistic regression can be used to model a binary response and predict the probability of a binary outcome. However, there are instances when we need to take this a step further and classify the outcome based on a cut-off probability threshold.
read more