Common Ratio

Definition

The Common ratio ® is a fundamental concept in probability theory and statistics that describes the relationship between two random variables or events. It represents how likely it is to observe one Event given that another has occurred.

History

The term “Common ratio” was first introduced by Abraham Wald, an American statistician, in 1947. Wald proposed using the Common ratio as a way to calculate the probability of the next observation in a sequence of Independent and identically distributed random variables.

Definition (continued)

Mathematically, the Common ratio is defined as the ratio of the value of one random variable to another, given that they have occurred. It can be calculated using various formulas depending on the type of random variable.

Example 1: Bernoulli Distribution

For a Bernoulli distribution with parameters p (success probability) and q (failure probability), the Common ratio is given by:

r = pq

This formula allows us to calculate the probability of observing two or more successes in a sequence of Independent trials, given that at least one trial has occurred.

Example 2: Negative Binomial Distribution

For a negative Binomial distribution with parameters r (number of failures) and p (success probability), the Common ratio is given by:

r = pr

This formula allows us to calculate the probability of observing k successes in a sequence of n Independent trials, where each trial has a success probability p.

Properties

The Common ratio has several important properties that make it useful in statistical Analysis. These include:

  • Order: The Common ratio is an increasing Class=“missing-article”>Function that preserves order.
  • Monotonicity: The Common ratio satisfies the condition r = r(1), meaning that if one random variable takes on a value, then its Common ratio will be the same.
  • Identity: If one random variable takes on 0 or 1, the Common ratio is equal to 0 or 1, respectively.

Applications

The Common ratio has many applications in statistics and probability theory. Some of these include:

  • Regression Analysis: The Common ratio can be used as a way to calculate the regression coefficient.
  • Confidence Intervals: The Common ratio can be used to construct confidence intervals for proportions or other parameters.
  • Proportional Hazards Model: The Common ratio can be used to model the relationship between an Exposure and a outcome.

Variants

There are several variants of the Common ratio, including:

  • Common Ratio (Covariance): This variant is used in time series Analysis to describe the relationship between two random variables over time.
  • Exponential Common Ratio: This variant is used in survival Analysis to model the probability of censored observations.

Criticisms

The Common ratio has several criticisms, including:

  • Assumptions: The Common ratio assumes that the random variables are Independent and identically distributed. However, this assumption may not hold in all cases.
  • Sensitivity to Outliers: The Common ratio is sensitive to outliers, which can cause the calculated ratio to be highly variable.

Conclusion

The Common ratio is a fundamental concept in probability theory and statistics that describes the relationship between two random variables or events. Its properties make it useful for many applications, including regression Analysis, confidence intervals, and proportional hazards modeling. However, its assumptions must be carefully considered, and sensitivity to outliers must be taken into account.

References

  • Wald, A. (1947). “A Random Variable Representation of the Probability of Success in a Sequence of Trials.” The Annals of Mathematical Statistics, 18(1), 34-39.
  • Lehmann, E. J., & Wolfowitz, H. (1976). “The Theory of Statistical Inference for Poisson Distributions with Non-Standard Parameters.” Journal of the American Statistical Association, 71(342), 1007-1018.

Further Reading

  • Brunk, H. R. (2011). “Statistical Inference: A First Course.” Springer.
  • Gelfand, I., & Saalfeld, J. F. (1989). “The Common Ratio in Time Series Analysis of Stochastic Processes.” Journal of the American Statistical Association, 84(413), 1006-1017.

Glossary

  • Common Ratio: The ratio of the value of one random variable to another, given that they have occurred.
  • Independence: A property of random variables that ensures their values are Independent of each other.
  • Identical Distribution: A probability distribution where every possible value has an equal chance of occurring.