You can make a time series stationary using adjustments and transformations. Adjustments such as removing inflation simplify the historical data making the series more consistent. Transforms like logarithms can stabilize the variance, while differencing transforms stabilize the mean from trend …
You can use visual inspection, global vs. local analysis, and statistics to analyze stationarity. The Augmented Dickey-Fuller (ADF) test is the most commonly used parametric test, and the Zivot-Andrews test is better than the ADF at detecting stationarity through structural …
Stationarity means that a process’s statistical properties that create a time series are constant over time. This statistical consistency makes distributions predictable enabling forecasting, and is an assumption of many time series forecasting models. What Is Stationarity? In mathematics and …
Year-over-year (YoY) is a method of analyzing data between two comparable periods on an annualized basis. Understanding how to calculate and what YoY values are can help you interpret financial and economic data more effectively. But it’s not enough to …
A sample is a smaller representative group selected from a population used to answer a statistical question. Samples allow statisticians to answer questions when surveying or analyzing the entire population is impractical. In this post, I will discuss what a …
Look-ahead bias occurs by using information not available or known in the analysis period for a study or simulation, leading to inaccurate results. An often-overlooked point regarding look-ahead bias is that it isn’t just about when a data observation becomes …
A time series is a sequence of moments-in-time observations. The sequence of data is either uniformly spaced at a specific frequency such as hourly or sporadically spaced in the case of a phone call log. Having an expert understanding of …
Survivorship bias is the risk of analyzing investment performance using only “surviving” constituents of a selected investment universe instead of incorporating all current and historical constituents over the performance period. Survivorship bias artificially increases long performance and detracts from short-selling …