Skip to main content

Wide Sense Stationary Signal (WSS)


Q & A and Summary

Stationary and Wide Sense Stationary Process

A stochastic process {…, Xt-1, Xt, Xt+1, Xt+2, …} consisting of random variables indexed by time index t is a time series.

The stochastic behavior of {Xt} is determined by specifying the probability density or mass functions (pdf’s):

p(xt1, xt2, xt3, …, xtm)

for all finite collections of time indexes

{(t1, t2, …, tm), m < ∞}

i.e., all finite-dimensional distributions of {Xt}.

A time series {Xt} is strictly stationary if

p(t1 + Ï„, t2 + Ï„, …, tm + Ï„) = p(t1, t2, …, tm),

∀Ï„, ∀m, ∀(t1, t2, …, tm).

Where p(t1 + Ï„, t2 + Ï„, …, tm + Ï„) represents the cumulative distribution function of the unconditional (i.e., with no reference to any particular starting value) joint distribution. A process {Xt} is said to be strictly stationary or strict-sense stationary if Ï„ doesn’t affect the function p. Thus, p is not a function of time.

A time series {Xt} is called covariance stationary if

E(Xt) = μ

Var(Xt) = σx2

Cov(Xt, Xt+τ) = γ(τ)

(All constant over time t)

Wide Sense Stationary Process

A random process is called weak-sense stationary or wide-sense stationary (WSS) if its mean function and its correlation function do not change by shifts in time.

μx(t) = μx

Rxx(t1, t2) = Rxx(t1 + α, t2 + α) for every α


Main Properties

  1. The mean and autocorrelation do not change over time.
  2. A wide-sense stationary (WSS) process has a constant mean, constant variance, and an autocorrelation function that depends only on the time difference (lag), not the absolute time.


For a WSS input to an LTI system, you are expected to study the output's statistical properties (such as mean, variance, and autocorrelation). You will find that the output signal is also a WSS signal. If your input signal has zero mean and unit variance, then the LTI output will have the same nature as the input signal, but:

  1. The mean of the output is scaled by the DC gain of the LTI system.
  2. The variance of the output is scaled by the total power gain of the system.



















MATLAB Code to Check the Autocorrelation Property of a WSS Signal Over Time

%The code is developed by SalimWireless.com
clc;
clear;
close all;


% Generate a wide-sense stationary (WSS) signal with 0 mean and unit variance
N = 1000; % Length of the signal
X = randn(1, N); % WSS signal


% Define the time indices t1 and t2
t1 = 0; % Time index 1
t2 = 100; % Time index 2


% Initialize autocorrelation value
Rx_val = 0;


% Loop to compute the sum for autocorrelation at (t1, t2)
for n = 1:N
% Ensure indices (n + t1) and (n + t2) are within bounds
if (n + t1 <= N) && (n + t2 <= N)
Rx_val = Rx_val + X(n + t1) * X(n + t2);
else
break; % Stop if indices go out of bounds
end
end


% Normalize by the length of the signal
Rx_val = Rx_val / N;


% Define the time indices t1 and t2
t3 = 100; % Time index 1
t4 = 200; % Time index 2


% Initialize autocorrelation value
Rx_val1 = 0;


% Loop to compute the sum for autocorrelation at (t1, t2)
for n = 1:N
% Ensure indices (n + t1) and (n + t2) are within bounds
if (n + t3 <= N) && (n + t4 <= N)
Rx_val1 = Rx_val1 + X(n + t3) * X(n + t4);
else
break; % Stop if indices go out of bounds
end
end


% Normalize by the length of the signal
Rx_val1 = Rx_val1 / N;
% Display the result
disp(['R_X(', num2str(t2), ') = ', num2str(Rx_val)]);
disp(['R_X(', num2str(t3), ', ', num2str(t4), ') = ', num2str(Rx_val)]);

Output

R_X( 100) = 0.039786
R_X(100, 200) = 0.039786


Copy the MATLAB Code above from here



MATLAB Code for the Output of an ARMA Filter When the Input is a WSS Signal

clc; clear; close all;

% Step 1: Get user input for WSS signal parameters
mu = input('Enter the mean of the WSS signal: ');
sigma2 = input('Enter the variance of the WSS signal: ');
N = 1000; % Length of signal

% Generate WSS signal with specified mean and variance
x = sqrt(sigma2) * randn(1, N) + mu;

% Step 2: Define ARMA filter coefficients
b = [1, -0.5]; % MA coefficients
a = [1, -0.8]; % AR coefficients (assumed stable)

% Step 3: Apply ARMA filter using built-in function
y = filter(b, a, x); % y[n] = (b/a) * x[n]

% Step 4: Calculate mean and variance
mean_x = mean(x);
mean_y = mean(y);
var_x = var(x);
var_y = var(y);

% Step 5: Display results
fprintf('Mean of input signal: %.4f\n', mean_x);
fprintf('Mean of output signal: %.4f\n', mean_y);
fprintf('Variance of input signal: %.4f\n', var_x);
fprintf('Variance of output signal: %.4f\n', var_y);

% Step 6: Plot input and output signals
figure;
subplot(2,1,1);
plot(x); title('Input Signal (WSS)'); ylabel('x[n]');
subplot(2,1,2);
plot(y); title('Output Signal (After ARMA Filter)'); ylabel('y[n]');

% Step 7: Autocorrelation comparison
figure;
subplot(2,1,1);
[R_x, lags_x] = xcorr(x - mean_x, 'biased');
plot(lags_x, R_x); title('Autocorrelation of Input x[n]');
xlabel('Lag'); ylabel('R_x');

subplot(2,1,2);
[R_y, lags_y] = xcorr(y - mean_y, 'biased');
plot(lags_y, R_y); title('Autocorrelation of Output y[n]');
xlabel('Lag'); ylabel('R_y');

Output

Enter the mean of the WSS signal: 0
Enter the variance of the WSS signal: 1
Mean of input signal: -0.0214
Mean of output signal: -0.0545
Variance of input signal: 1.0593
Variance of output signal: 1.3152

Copy the aforementioned MATLAB code from here


Q & A and Summary

1. What is the difference between a random variable and a stochastic process?

Answer:
A random variable is a function that assigns a real number to each outcome of a random experiment, representing a quantity whose value is subject to randomness. Random variables can be either discrete or continuous.

A stochastic process, on the other hand, is a collection of random variables indexed by time, denoted as {Xt | t ∈ T}. Each random variable Xt represents the state of a system at a specific time. It is used to model systems that evolve randomly over time, such as stock prices or weather patterns.

2. What does it mean for a time series to be stationary?

Answer:
A time series is considered stationary if its statistical properties do not change over time. This means that:

  • The mean and variance of the series are constant over time.
  • The covariance between two time points depends only on the time difference (lag), not on the actual time.

In time series analysis, stationarity is an important assumption for many models, like AR, MA, and ARMA, because these models require the statistical properties of the series to remain stable over time.

3. How do White Noise and Gaussian White Noise differ?

Answer:
White Noise is a type of Wide-Sense Stationary (WSS) process where:

  • The mean is zero.
  • The variance is constant.
  • There is no correlation between values at different times.

If the white noise values also follow a Gaussian distribution (i.e., they are normally distributed), it is referred to as Gaussian White Noise. The key difference is that Gaussian white noise specifically refers to white noise where the random variables have a normal distribution, while white noise could follow any distribution as long as it satisfies the properties mentioned above.

4. What is the Wold Decomposition Theorem and how does it relate to time series models?

Answer:
The Wold Decomposition Theorem states that any Wide-Sense Stationary (WSS) time series can be represented as the sum of two components:

  1. A predictable deterministic component (like a trend or seasonality).
  2. A stochastic component, which can be modeled as the output of an LTI (Linear Time-Invariant) system fed by white noise.

This decomposition justifies the use of linear time series models, such as AR, MA, and ARMA, which model the stochastic part of the time series as the output of an LTI system. This allows us to capture the random nature of the series using these models.

5. What is the significance of the z-transform in time series analysis?

Answer:
The z-transform is a mathematical tool used to convert a discrete-time signal (like a time series) into its frequency-domain representation. It is particularly useful for analyzing the properties of time series models, such as ARMA models. The z-transform allows us to represent and manipulate time series models in a more convenient form, especially when working with systems and their stability properties.

  • It helps in deriving the transfer function of a system, which relates the input (error terms) and the output (time series).
  • It also plays a crucial role in analyzing the stability and invertibility of ARMA models by examining the roots of the AR and MA polynomials in the z-plane.

6. What conditions must be satisfied for an ARMA model to be stable?

Answer:
For an ARMA model to be stable (and hence stationary), the roots of the autoregressive polynomial (Φ(z)) must lie outside the unit circle in the z-plane. This ensures that the time series does not exhibit explosive behavior and remains well-behaved over time. Stability is a key property for ensuring that the statistical properties of the time series do not change over time.

7. How is the transfer function of an ARMA model defined and what does it represent?

Answer:
The transfer function of an ARMA model is defined as the ratio of the moving average polynomial (Θ(z)) to the autoregressive polynomial (Φ(z)) in the z-domain:

        H(z) = Θ(z-1) / Φ(z-1)
    

It describes the relationship between the input (white noise error terms) and the output (time series).

  • For a pure AR(p) model, the transfer function is all-pole.
  • For a pure MA(q) model, the transfer function is all-zero.
  • An ARMA(p,q) model has a pole-zero transfer function.

The transfer function is useful in analyzing the behavior of the system, its stability, and how it filters the white noise to produce the observed time series.

8. Why are AR and MA models important in time series analysis?

Answer:
AR (Autoregressive) and MA (Moving Average) models are essential for capturing the underlying structure of time series data.

  • AR models model the current value of the series as a linear combination of its own past values, allowing us to capture patterns such as trends and cycles.
  • MA models model the current value as a linear combination of the current and past white noise error terms, which is useful for modeling short-term shocks or noise in the series.

Together, ARMA (Autoregressive Moving Average) models combine both approaches, providing a more powerful tool for modeling and forecasting time series that exhibit both persistence (from AR) and short-term randomness (from MA).

9. How does an LTI system transform a WSS time series?

Answer:
When a Wide-Sense Stationary (WSS) process (like a time series) is passed through a Linear Time-Invariant (LTI) system, the output of the system will also be WSS. This means the statistical properties (mean, variance, covariance) of the time series remain constant over time, even after transformation.

Additionally, if the input WSS process is Gaussian, the output process will also be Gaussian, because the linear transformation preserves the nature of the distribution. This makes LTI systems useful for modeling how time series data evolves over time under various transformations.

10. What practical applications do AR, MA, and ARMA models have in real-world domains?

Answer:
AR, MA, and ARMA models are widely used across many fields, including:

  • Economics and finance: Forecasting stock prices, inflation rates, and economic indicators.
  • Weather and climate prediction: Modeling temperature, rainfall, and other climate data.
  • Signal processing: Analyzing and filtering signals, including audio and communications signals.
  • Retail and business sales forecasting: Predicting demand for products based on past sales data.
  • Healthcare analytics: Modeling disease spread or patient monitoring data.

These models form the foundation for more complex methods and are critical for both prediction and analysis of time-dependent data.


Further Reading

People are good at skipping over material they already know!

View Related Topics to







Contact Us

Name

Email *

Message *

Popular Posts

BER vs SNR for M-ary QAM, M-ary PSK, QPSK, BPSK, ...

📘 Overview of BER and SNR 🧮 Online Simulator for BER calculation of m-ary QAM and m-ary PSK 🧮 MATLAB Code for BER calculation of M-ary QAM, M-ary PSK, QPSK, BPSK, ... 📚 Further Reading 📂 View Other Topics on M-ary QAM, M-ary PSK, QPSK ... 🧮 Online Simulator for Constellation Diagram of m-ary QAM 🧮 Online Simulator for Constellation Diagram of m-ary PSK 🧮 MATLAB Code for BER calculation of ASK, FSK, and PSK 🧮 MATLAB Code for BER calculation of Alamouti Scheme 🧮 Different approaches to calculate BER vs SNR What is Bit Error Rate (BER)? The abbreviation BER stands for Bit Error Rate, which indicates how many corrupted bits are received (after the demodulation process) compared to the total number of bits sent in a communication process. BER = (number of bits received in error) / (total number of tran...

Calculation of SNR from FFT bins in MATLAB

📘 Overview 🧮 MATLAB Code for Estimation of SNR from FFT bins of a Noisy Signal 🧮 MATLAB Code for Estimation of Signal-to-Noise Ratio from Power Spectral Density Using FFT and Kaiser Window Periodogram from real signal data 📚 Further Reading   Here, you can find the SNR of a received signal from periodogram / FFT bins using the Kaiser operator. The beta (β) parameter characterizes the Kaiser window, which controls the trade-off between the main lobe width and the side lobe level in the frequency domain. For that you should know the sampling rate of the signal.  The Kaiser window is a type of window function commonly used in signal processing, particularly for designing finite impulse response (FIR) filters and performing spectral analysis. It is a general-purpose window that allows for control over the trade-off between the main lobe width (frequency resolution) and side lobe levels (suppression of spectral leakage). The Kaiser window is defined...

MIMO Channel Matrix | Rank and Condition Number

MIMO / Massive MIMO MIMO Channel Matrix | Rank and Condition...   The channel matrix in wireless communication is a matrix that describes the impact of the channel on the transmitted signal. The channel matrix can be used to model the effects of the atmospheric or underwater environment on the signal, such as the absorption, reflection or scattering of the signal by surrounding objects. When addressing multi-antenna communication, the term "channel matrix" is used. Let's assume that only one TX and one RX are in communication and there's no surrounding object. Here, in our case, we can apply the proper threshold condition to a received signal and get the original transmitted signal at the RX side. However, in real-world situations, we see signal path blockage, reflections, etc.,  (NLOS paths [↗]) more frequently. The obstruction is typically caused by building walls, etc. Multi-antenna communication was introduced to address this issue. It makes diversity app...

Constellation Diagrams of ASK, PSK, and FSK

📘 Overview of Energy per Bit (Eb / N0) 🧮 Online Simulator for constellation diagrams of ASK, FSK, and PSK 🧮 Theory behind Constellation Diagrams of ASK, FSK, and PSK 🧮 MATLAB Codes for Constellation Diagrams of ASK, FSK, and PSK 📚 Further Reading 📂 Other Topics on Constellation Diagrams of ASK, PSK, and FSK ... 🧮 Simulator for constellation diagrams of m-ary PSK 🧮 Simulator for constellation diagrams of m-ary QAM BASK (Binary ASK) Modulation: Transmits one of two signals: 0 or -√Eb, where Eb​ is the energy per bit. These signals represent binary 0 and 1.    BFSK (Binary FSK) Modulation: Transmits one of two signals: +√Eb​ ( On the y-axis, the phase shift of 90 degrees with respect to the x-axis, which is also termed phase offset ) or √Eb (on x-axis), where Eb​ is the energy per bit. These signals represent binary 0 and 1.  BPSK (Binary PSK) Modulation: Transmits one of two signals...

Coherence Bandwidth and Coherence Time

🧮 Coherence Bandwidth 🧮 Coherence Time 🧮 Coherence Time Calculator 🧮 Relationship between Coherence Time and Delay Spread 🧮 MATLAB Code to find Relationship between Coherence Time and delay Spread 📚 Further Reading   Coherence Bandwidth Coherence bandwidth is a concept in wireless communication and signal processing that relates to the frequency range over which a wireless channel remains approximately constant in terms of its characteristics. coherence bandwidth is  The inverse of Doppler spread delay time, or any spread delay time due to fading in general.  The coherence bandwidth is related to the delay spread of the channel, which is a measure of the time it takes for signals to traverse the channel. The two are related by the following formulae: Coherence bandwidth = 1/(delay spread time) Or, Coherence Bandwidth = 1/(root-mean-square delay spread time) (Coherence bandwidth in Hertz) For instance, the coherence bandwidth is...

Comparisons among ASK, PSK, and FSK | And the definitions of each

📘 Comparisons among ASK, FSK, and PSK 🧮 Online Simulator for calculating Bandwidth of ASK, FSK, and PSK 🧮 MATLAB Code for BER vs. SNR Analysis of ASK, FSK, and PSK 📚 Further Reading 📂 View Other Topics on Comparisons among ASK, PSK, and FSK ... 🧮 Comparisons of Noise Sensitivity, Bandwidth, Complexity, etc. 🧮 MATLAB Code for Constellation Diagrams of ASK, FSK, and PSK 🧮 Online Simulator for ASK, FSK, and PSK Generation 🧮 Online Simulator for ASK, FSK, and PSK Constellation 🧮 Some Questions and Answers Modulation ASK, FSK & PSK Constellation MATLAB Simulink MATLAB Code Comparisons among ASK, PSK, and FSK    Comparisons among ASK, PSK, and FSK Comparison among ASK, FSK, and PSK Parameters ASK FSK PSK Variable Characteristics Amplitude Frequency ...

What are Precoding and Combining Weights / Matrices in a MIMO Beamforming System

MIMO / Massive MIMO Beamforming Techniques Precoding and Combining Weights...   Figure:  configuration of single-user digital precoder for millimeter  Wave massive MIMO system Precoding and combining are two excellent ways to send and receive signals over a multi-antenna communication process, respectively (i.e., MIMO antenna communication ). The channel matrix is the basis of both the precoding and combining matrices. Precoding matrices are typically used on the transmitter side and combining matrixes on the receiving side. The two matrices allow us to generate multiple simultaneous data streams between the transmitter and receiver. The nature of the data streams is also orthogonal. That helps decrease or cancel (theoretically) interference between any two data streams. The channel matrix is first properly diagonalized. Diagonalization is the process of transforming any matrix into an equivalent diagon...

Simulation of ASK, FSK, and PSK using MATLAB Simulink

📘 Overview 🧮 How to use MATLAB Simulink 🧮 Simulation of ASK using MATLAB Simulink 🧮 Simulation of FSK using MATLAB Simulink 🧮 Simulation of PSK using MATLAB Simulink 🧮 Simulator for ASK, FSK, and PSK 🧮 Digital Signal Processing Simulator 📚 Further Reading ASK, FSK & PSK HomePage MATLAB Simulation Simulation of Amplitude Shift Keying (ASK) using MATLAB Simulink      In Simulink, we pick different components/elements from MATLAB Simulink Library. Then we connect the components and perform a particular operation.  Result A sine wave source, a pulse generator, a product block, a mux, and a scope are shown in the diagram above. The pulse generator generates the '1' and '0' bit sequences. Sine wave sources produce a specific amplitude and frequency. The scope displays the modulated signal as well as the original bit sequence created by the pulse generator. Mux is a tool for displaying b...