Chapter 6: Introduction to Inference
description
Transcript of Chapter 6: Introduction to Inference
![Page 1: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/1.jpg)
1
Chapter 6: Continuous Probability Distributions
http://stats.stackexchange.com/questions/423/what-is-your-favorite-data-analysis-cartoon
A visual comparison of normal and paranormal distribution
Lower caption says 'Paranormal Distribution' - no idea why the graphical artifact is occurring.
![Page 2: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/2.jpg)
2
6.1: Probability Distributions for a Continuous Random Variable - Goals
• Describe the basis of the probability density function (pdf).
• Use the probability density function (pdf) and cumulative distribution function (cdf) of a continuous random variable to calculate probabilities and percentiles (median) of events.
• Be able to use a pdf to find the mean of a continuous random variable.
• Be able to use a pdf to find the variance of a continuous random variable.
![Page 3: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/3.jpg)
3
Density Curve
(a) (b) (c)
![Page 4: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/4.jpg)
4
Probability Distribution for Continuous Random Variable
• A probability distribution for a continuous random variable X is given by a smooth curve called a density curve, or probability density function (pdf).
f(x)dx 1
y = f(x)
Area = 1
![Page 5: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/5.jpg)
5
Probabilities Continuous Random Variable
• The curve is defined so that the probability that X takes on a value between a and b (a < b) is the area under the curve between a and b.
b
aP(a X b)= f(x)dx
![Page 6: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/6.jpg)
6
Properties of pdf
• f(x) ≥ 0
![Page 7: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/7.jpg)
Example: Continuous Random VariableWe know that the distribution of the grade of a
particular road in a particular 2 mile region is a continuous r.v. X with a functional form which is proportional to x2. What is f(x)?
![Page 8: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/8.jpg)
Example: Continuous Random VariableThe distribution of the grade of a particular road
in a particular 2 mile region is a continuous r.v. X with density
a) Is this a valid density curve?b) What is the probability that the grade is in
the last quarter mile of the region?
![Page 9: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/9.jpg)
9
Formulas for the Mean of a Random Variable
• Discrete – Mean Discrete – Rule 3
• Continuous Continuous – Rule 3
![Page 10: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/10.jpg)
10
Variance of a Random Variable
= E(X2) – (E(X))2
![Page 11: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/11.jpg)
Example: Continuous Random VariableThe distribution of the grade of a particular road
in a particular 2 mile region is a continuous r.v. X with density
c) What is the expected value?d) Calculate E(X2).e) Calculate the standard deviation.
![Page 12: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/12.jpg)
12
Cumulative Distribution Function (cdf)
• F(x) = P(X ≤ x) =
![Page 13: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/13.jpg)
13
pdf – Percentiles
• Percentiles– Let p be a number between 0 and 1. The
100pth percentile is defined by
• The median of a pdf is the equal – areas point.
![Page 14: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/14.jpg)
Example: Continuous Random VariableThe distribution of the grade of a particular road
in a particular 2 mile region is a continuous r.v. X with density
f) Calculate the cdf.g) What is the median of this distribution?
![Page 15: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/15.jpg)
15
6.2 Normal Distribution
http://delfe.tumblr.com/
![Page 16: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/16.jpg)
16
6.2/6.5: The Normal DistributionThe Normal Approximation to the Binomial
Distribution - Goals• Be able to sketch the normal distribution.• Be able to standardize a value.• Be able to use the Z-table.• Be able to calculate probabilities.• Be able to calculate percentiles (Inverse
calculations).• Determine when you can use the normal
approximation to the binomial and perform calculations using this approximation.
![Page 17: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/17.jpg)
17
Normal Distribution
where -∞ < < ∞, σ > 0X ~ N(,σ2)
![Page 18: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/18.jpg)
18
Shapes of Normal Density Curve
http://resources.esri.com/help/9.3/arcgisdesktop/com/gp_toolref/process_simulations_sensitivity_analysis_and_error_analysis_modeling/distributions_for_assigning_random_values.htm
![Page 19: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/19.jpg)
19
Graph of Normal Distribution
![Page 20: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/20.jpg)
20
Normal Distribution
where -∞ < < ∞, σ > 0
![Page 21: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/21.jpg)
21
Standard Normal or z curve
𝑓 (𝑧 )= 1√2𝜋
𝑒− 𝑧
2
2
![Page 22: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/22.jpg)
22
Cumulative z curve area
![Page 23: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/23.jpg)
Z-table
23
![Page 24: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/24.jpg)
24
Using the Z table
area right of z = 1 area left of z
area between z1 and z2 = area left of z1 – area left of z2
![Page 25: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/25.jpg)
25
Procedure for Normal Distribution Problems
1. Sketch the situation and shade the area to be found. Optional but extremely useful.
2. Standardize X to state the problem in terms of Z.3. Use Table III to find the area to the left of z.4. Calculate the final answer.5. Write your conclusion in the context of the
problem.
![Page 26: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/26.jpg)
26
Normal Distribution: ExampleA particular rash has shown up in an elementary
school. It has been determined that the length of time that the rash will last is normally distributed with mean 6 days and standard deviation 1.5 days.
a) What is the percentage of students that have the rash for longer than 8 days?
b) What is the percentage of students that the rash will last between 3.7 and 8 days?
![Page 27: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/27.jpg)
27
Percentiles
![Page 28: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/28.jpg)
28
Normal Distribution: ExampleA particular rash has shown up in an elementary
school. It has been determined that the length of time that the rash will last is normally distributed with mean 6 days and standard deviation 1.5 days.
c) How long would the student’s rash have to have lasted to be in the top 10% of the number of days that the students have the rash?
![Page 29: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/29.jpg)
29
Symmetrically Located Areas
![Page 30: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/30.jpg)
30
Normal Distribution: ExampleA particular rash has shown up in an elementary
school. It has been determined that the length of time that the rash will last is normally distributed with mean 6 days and standard deviation 1.5 days.
d) What interval symmetrically placed about the mean will capture 95% of the times for the student’s rashes to have lasted.
![Page 31: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/31.jpg)
31
Why Approximate the Binomial Distribution?
1. Intervals2. Computation (n large)3. Inference
![Page 32: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/32.jpg)
32
Difficulties with the Normal Approximation to the Binomial
1. Skewedness of the Binomial Distribution.2. The Binomial Distribution is discrete.
![Page 33: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/33.jpg)
Continuity Correction
http://wiki.axlesoft.com/index.php?title=Continuity_correction
33
![Page 34: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/34.jpg)
Continuity Correction – ExtraActual Value Approximate ValueP(X = a) P(a – 0.5 < X < a +0.5)P(a < X) P(a + 0.5 < X)P(a ≤ X) P(a – 0.5 < X)P(X < b) P(X < b – 0.5)P(X ≤ b) P(X < b + 0.5)
34
![Page 35: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/35.jpg)
35
Example: Normal Approximation to the Binomial
The ideal size of a first-year class at a particular college is 150 students. The college, knowing from past experience that on the average only 30 percent of those accepted for admission will actually attend, uses a policy of approving the applications of 450 students.
Compute the probability that more than 150 students attend this college.
![Page 36: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/36.jpg)
36
6.3: Checking the Normality Assumption- Goals
• Be able to state why it is important to be able to check to see whether a data set is normal or not.
• Be able to determine if a distribution is normal (normal quantile plots)
![Page 37: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/37.jpg)
37
Methods for Checking Normality
1. Graphs2. Backward Empirical Rule3. IQR/s4. Normal Probability Plot
![Page 38: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/38.jpg)
38
Procedure: Normal Quantile Plot
1) Arrange the data from smallest to largest.2) Record the corresponding percentiles
(quantiles).3) Find the z value corresponding to the
quantile calculated in part 2.4) Plot the original data points (from 1) vs. the z
values (from 3).
![Page 39: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/39.jpg)
39
6.4: The Exponential Distribution (and Uniform Distribution) - Goals
• Be able to recognize situations that may be described by uniform or exponential distributions.
• Be able to recognize the sketches of the pdfs for uniform and exponential distribution.
• Calculate the probability, mean and standard deviation when X has a uniform or exponential distribution.
![Page 40: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/40.jpg)
40
Uniform Distribution
• In a (continuous) uniform distribution, the probability density is distributed evenly between two points.
![Page 41: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/41.jpg)
41
Uniform DistributionThe density function of the uniform distribution
over the interval [a,b] is
![Page 42: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/42.jpg)
42
Example: UniformA packaging line constantly packages 200 cartons
per hour. After weighing every package variation the distribution of the weights was found to be uniform with weights ranging from 18.2 lbs. – 20.4 lbs., measured to the nearest tenths. The customer requires less than 20.0 lbs. for ergonomic reasons.
a) What is the probability that the package weights less than 20 lbs.?
b) What are the mean and the standard deviation of the package weights?
![Page 43: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/43.jpg)
43
Exponential Distribution• Uses: amount of time until some specific
event occurs (the amount of time between successive events)
![Page 44: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/44.jpg)
44
Exponential Distribution
• • Var
![Page 45: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/45.jpg)
45
Example: Exponential
The time that it takes to repair a machine takes on average 2 hours. Assume that that the repair time has an exponential distribution. a) What is the probability that the repair time will
take at most 1 hour?b) What is the probability that the repair time will
be more than 1.5 hours?c) What is the standard deviation of the
distribution of these bacteria?
![Page 46: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/46.jpg)
46
Gamma Distribution
• Generalization of the exponential function• Uses
– probability theory– theoretical statistics– actuarial science– operations research– engineering
![Page 47: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/47.jpg)
47
Beta Distribution
• This distribution is only defined on an interval– standard beta is on the interval [0,1]
• uses– modeling proportions– percentages– Probabilities
• Uniform distribution is a member of this family.
![Page 48: Chapter 6: Introduction to Inference](https://reader033.fdocuments.net/reader033/viewer/2022061517/5681687b550346895ddeee75/html5/thumbnails/48.jpg)
48
Other Continuous Random Variables
• Weibull– exponential is a member of family– uses: lifetimes
• lognormal– log of the normal distribution– uses: products of distributions
• Cauchy– symmetrical, long straggly tails