At the end of this lesson, the students shall be able to:
1) Recognize the theory of probability 2) Distinguish the properties of the normal distribution curve 3) Solve problems on % probable error Introduction
The adjustment of measured quantities containing
random errors is a major concern to people involved in the geospatial sciences.
Again, what are random errors?
Theory of probability
Probability is the ratio of the number of times that
an event should occur to the total number of possibilities. When an event can occur in m ways and fail to occur in n ways, the probability of its occurrence is m/(m+n), and the probability of its failure is n/(m+n). Theory of probability
A compound event is the simultaneous occurrence
of two or more independent events. For example, random errors from angles and distances (compound events) cause traverse misclosures. The probability of the simultaneous occurrence of two independent events is the product of their individual probabilities. Theory of probability
Consider this example…
There are two boxes containing combinations of red and white balls. Box A contains four balls, one red and three white. Box B contains five balls, two red and three white. What is the probability that two red balls would be drawn if one ball is drawn randomly from each box? How about if two white balls? Theory of probability
Thus the probability of the simultaneous occurrence
of two independent events is the product of the individual probabilities of those two events. Or: 𝑷 = 𝑷𝟏 × 𝑷𝟐 × ⋯ × 𝑷𝒏 Theory of probability
If the number of combining measurements, n, is
increased progressively to larger values, the plot of error sizes versus probabilities would approach a smooth curve of the characteristic bell shape. Normal error distribution curve or probability density function of a normal random variable. Normal probability density function PROPERTIES OF THE NORMAL PROBABILITY CURVE 50% Probable Error
For any group of observations, the 50% probable
error establishes the limits within which 50% of the errors should fall. In other words, any measurement has the same chance of coming within these limits as it has of falling outside them. For any set of observations, the 50% probable error can be obtained by computing the standard error and then multiplying it by 0.6745: 𝑬𝟓𝟎 = 𝟎. 𝟔𝟕𝟒𝟓σ USES FOR PERCENT ERRORS
Standard errors and errors of other percent probabilities
are commonly used to evaluate measurements for acceptance. EXAMPLE
Suppose that the following values (in feet) were obtained in 15
independent distance observations, 𝐷𝑖 : 212.22, 212.25, 212.23, 212.15, 212.23, 212.11, 212.29, 212.34, 212.22, 212.24, 212.19, 212.25, 212.27, 212.20, and 212.25. Calculate the mean, S, 𝐸50 , 𝐸95 , and check for any observations outside the 99.7% probability level.