# Intuitive explanation of stationarity

I was wrestling with stationarity in my head for a while... Is this how you think about it? Any comments or further thoughts will be appreciated.

Stationary process is the one which generates time-series values such that distribution mean and variance is kept constant. Strictly speaking, this is known as weak form of stationarity or covariance/mean stationarity.

Weak form of stationarity is when the time-series has constant mean and variance throughout the time.

Let's put it simple, practitioners say that the stationary time-series is the one with no trend - fluctuates around the constant mean and has constant variance.

Covariance between different lags is constant, it doesn't depend on absolute location in time-series. For example, the covariance between t and t-1 (first order lag) should always be the same (for the period from 1960-1970 same as for the period from 1965-1975 or any other period).

In non-stationary processes there is no long-run mean to which the series reverts; so we say that non-stationary time series do not mean revert. In that case, the variance depends on absolute position in time-series and variance goes to infinity as time goes on. Technically speaking, auto-correlations to not decay with time, but in small samples they do disappear - although slowly.

In stationary processes, shocks are temporary and dissipate (lose energy) over time. After a while, they do not contribute to the new time-series values. For example, something which happened log time ago (long enough) such as World War II, had an impact, but, it the time-series today is the same as if World War II never happened, we would say that shock lost its energy or dissipated. Stationarity is especially important as many classical econometric theories are derived under the assumptions of stationarity.

A strong form of stationarity is when the distribution of a time-series is exactly the same trough time. In other words, the distribution of original time-series is exactly same as lagged time-series (by any number of lags) or even sub-segments of the time-series. For example, strong form also suggests that the distribution should be the same even for a sub-segments 1950-1960, 1960-1970 or even overlapping periods such as 1950-1960 and 1950-1980. This form of stationarity is called strong because it doesn't assume any distribution. It only says the probability distribution should be the same. In the case of weak stationarity, we defined distribution by its mean and variance. We could do this simplification because implicitly we assumed normal distribution, and normal distribution is fully defined by its mean and variance or standard deviation. This is nothing but saying that probability measure of the sequence (within time-series) is the same as that for lagged/shifted sequence of values within same time-series.

• Well I do not understand the question, do you want to simplify the informal description of stationarity concept you quoted here? If you ask is this explanation correct, yes it is. Though non-stationarity has much more forms, any time-dependence in up-to second order moments will be the source for such in weak case (structural changes could be added, for example). Are you looking for some other quotes? – Dmitrij Celov Apr 25 '11 at 16:37
• Thanks. I was hoping to get feedback pointing to important aspects of the stationarity (as a concept) which aren't there... – user333 Apr 25 '11 at 20:04

First of all, it is important to note that stationarity is a property of a process, not of a time series. You consider the ensemble of all time series generated by a process. If the statistical properties¹ of this ensemble (mean, variance, …) are constant over time, the process is called stationary. Strictly speaking, it is impossible to say whether a given time series was generated by a stationary process (however, with some assumptions, we can take a good guess).

More intuitively, stationarity means that there are no distinguished points in time for your process (influencing the statistical properties of your observation). Whether this applies to a given process depends crucially on what you consider as fixed or variable for your process, i.e., what is contained in your ensemble.

A typical cause of non-stationarity are time-dependent parameters – which allow to distinguish time points by the values of the parameters. Another cause are fixed initial conditions.

Consider the following examples:

• The noise reaching my house from a single car passing at a given time is not a stationary process. E.g., the average amplitude² is highest when the car is directly next to my house.

• The noise reaching my house from street traffic in general is a stationary process, if we ignore the time dependency of the traffic intensity (e.g., less traffic at night or on weekends). There are no distinguished points in time anymore. While there may be strong fluctuations of individual time series, these vanish when I consider the ensemble of all realisations of the process.

• If I we include known impacts on traffic intensity, e.g., that there is less traffic at night, the process is non-stationary again: The average amplitude² varies with a daily rhythm. Every point in time is distinguished by the time of the day.

• The position of a single peppercorn in a pot of boiling water is a stationary process (ignoring the loss of water due to evaporation). There are no distinguished points in time.

• The position of a single peppercorn in a pot of boiling water dropped in the exact middle at $t=0$ is not a stationary process, as $t=0$ is a distinguished point in time. The average position of the peppercorn is always in the middle (assuming a symmetric pot without distinguished directions), but at $t=ε$ (with $ε$ small), we can be sure that the peppercorn is somewhere near the middle for every realisation of the process, while at a later time, it can also be closer to the border of the pot.

So, the distribution of positions changes over time. To give a specific example, the standard deviation grows. The distribution quickly converges to the respective distributions of the previous example and if we only take a look at this process for $t>T$ with a sufficiently high $T$, we can neglect the non-stationarity and approximate it as a stationary process for all purposes – the impact of the initial condition has faded away.

¹ For practical purposes, this is sometimes reduced to the mean and the variance (weak stationarity), but I do not consider this helpful to understand the concept. Just ignore weak stationarity until you understood stationarity.
² Which is the mean of the volume, but the standard deviation of the actual sound signal (do not worry too much about this here).

For clarity, I would add that any time series where the datapoints are normally distributed through time with a constant mean and variance is considered a strong stationary time series since given the mean and standard deviation the normal distribution will always have the same probability distribution curve (the inputs to the normal equation only depend on the mean and the standard deviation).

This is not the case with a t-distribution, for example, where an input to the t-distribution equation is gamma which impacts the shape of the distribution curve despite a constant mean and constant standard deviation.

• In the case of normal marginals you describe a form of second-order stationarity, which I suspect is not what you mean by "strong" stationarity. For stationarity to hold, you must additionally assume the process is Gaussian ( that is, the joint distribution of any finite number of values must be multivariate Normal) and that the covariances depend only on the time differences. It is unclear what you mean by "an input to the t-distribution equation" or to what "gamma" might refer. – whuber Nov 13 '16 at 21:12