Statistics How To

Correlation > Cross Correlation in Statistics In statistics, a cross-correlation function (a specific type of correlation function) is a measure of association. For example, the most common correlation coefficient, the Pearson product-moment correlation coefficient (PPMC), is a normalized version of a cross-correlation. The PPMC gives a measure of temporal similarity for two time series. Cross … Read more

Descriptive Statistics > Measures of position give us a way to see where a certain data point or value falls in a sample or distribution. A measure can tell us whether a value is about the average, or whether it’s unusually high or low. Measures of position are used for quantitative data that falls on … Read more

Statistics Definitions > An identification key is an identification tool primarily used to find taxonomic levels (e.g. species or genus) in the biological sciences. The keys have a wide variety of applications, including identification of plants, nuts, and amphibians as well as in forensic analysis. As an example, let’s say you found a moth in … Read more

Probability Distributions > The exponential power distribution is a generalization of the normal distribution. Therefore, it’s also known as the generalized normal distribution. Other names include the General Error Distribution and the Generalized Power Distribution. PDF of the Exponential Power Distribution The Probability Density Function (PDF) of the Exponential Power Distribution is: Where: λ = … Read more

Statistics Definitions > What is Mean Absolute Scaled Error? Mean Absolute Scaled Error (MASE) is a scale-free error metric that gives each error as a ratio compared to a baseline’s average error. The advantages of MASE include that it never gives undefined or infinite values and so is a good choice for intermittent-demand series (which … Read more

Regression Analysis > Lack of Fit tells us whether a regression model is a poor model of the data. This may be because we made a poor choice of variables, or it may be because important terms weren’t included. It can also be because of poor experimental design. If unusually large residuals or errors appear … Read more

Charts and Graphs > A gain and lift chart is a visual way to evaluate different the effectiveness of different models. As well as helping you to evaluate how good your predictive model might be, it can also show visually how the response rate of a targeted group might differ from that of a randomly … Read more

Statistics Definitions > A sample statistic is a piece of statistical information you get from a handful of items. A sample is just a part of a population. For example, let’s say your population was every American, and you wanted to find out how much the average person earns. Time and finances stop you from … Read more

ANOVA > Huynh-Feldt Correction The Huynh-Feldt correction is a correction for violations of sphericity. If Mauchly’s Sphericity Test test returns a small p-value, you should apply a correction to the index of non sphericity (called the Box index, ε): When ε ≤ 0.75 (or you don’t know what the value for the statistic is), use … Read more

Types of Bias > Spectrum Bias What is Spectrum Bias? Spectrum bias (or case-mix bias) is the variability of medical test performance that happens when tests are given to different mixes of patients at different locations. Test performance may differ between groups, making it a challenge to interpret test. There is some debate about whether … Read more