Professional Documents
Culture Documents
http://www.economicpopulist.org/content/peek-employment-report-
establishment-survey
http://espn.go.com/mlb/player/_/id/28513/adam-jones Population
http://baltimore-
maryland.org/history/baltimore-
population.png
Why Study Statistics?
Statistical analysis is also an integral part of scientific research!
Are your experimental results believable?
A variable can be more random or more deterministic depending on the degree to which
you account for relevant parameters:
Mostly deterministic: Only a small fraction of the outcome cannot be accounted for.
Length of a table - only slightly dependent upon:
• Temperature/humidity variation
• Measurement resolution
• Instrument/observer error
• Quantum-level intrinsic uncertainty
Mostly Random: Most of the outcome cannot be accounted for.
• Trajectory of a given molecule in a solution
Random variables
Can be described as discrete or continuous:
• A discrete variable has a countable number of values.
Number of customers who enter a store before one purchases a product.
k k
Pr( X x ) f ( x ) 1
i 1
i
i 1
i for k possible discrete outcomes
Where: F ( x) Pr( X x)
Discrete Probability Distributions
Example: Waiting for a success
Consider an experiment in which we toss a coin until heads turns up.
Outcomes, w = {H, TH, TTH, TTTH, TTTTH…}
Let X(w) be the number of tails before a heads turns up.
What is the Probability Distribution Function for the sample space?
1
f ( x) x 1 For x = 0, 1, 2…. Pr(a X b) F (b) F (a) f (x )
a xi b
i
2
k k
Pr( X x ) f ( x ) 1
0.5
0.45
0.4 i i
0.35 i 1 i 1
0.3
f(x) 0.25
0.2
0.15
0.1
0.05
0
0 1 2 3 4 5 6
Number of tails before a heads is tossed
Discrete Probability Distributions
Example: Distribution Function for Die/Dice
Distribution function for throwing a die:
Outcomes, w = {1, 2, 3, 4, 5, 6} f(xi) = 1/6 for i = 1,6
0.180
0.160
0.140
0.120
0.100
0.080
0.060
0.040
0.020
0.000
1 2 3 4 5 6
Discrete Probability Distributions
Example: Distribution Function for Die/Dice
Distribution function for the sum of two thrown dice:
f(xi) = 1/36 for x1 = 2
2/36 for x2 = 3
… 0.180
0.160
0.140
0.120
0.100
0.080
0.060
0.040
0.020
0.000
2 3 4 5 6 7 8 9 10 11 12
Cumulative Discrete Probability
Distributions
j
Where xj is the largest discrete
Pr( X x' ) F ( x' ) f ( xi )
i 1 value of X less than or equal to x’
Pr( X xk ) 1
Continuous Probability
Distributions
Properties of the cumulative distribution function:
F () 0
0 F ( x) 1 F ( x) Pr( X x)
F () 1
For continuous variables, the events of interest are intervals rather than
isolated values.
Consider waiting time for a bus which is equally likely to arrive anytime in the next ten
minutes:
Not interested in probability that the bus will arrive in
3.451233 minutes, but rather the probability that the bus
will arrive in the subinterval (a,b) minutes:
ba
P(a T b) F (b) F (a)
F(t)
10
t
10
Continuous Probability
Distributions X
Z
Example: Gaussian (normal) distribution:
1 ( x )2
f ( x) exp
2 2 2
X X Z
Z
1 ( x )2
f ( x) exp
2 2 2
X Z
( X ) 2
Standard Deviation: Standard measures the spread of data about the mean.
2
deviation
N
( X )
N
Variance: Variance is second moment about the mean; the average squared distance of the d
from the mean. ( X ) 2
2
N
Practice!
Team A Team B
183
182
183.0
183.5
• Which team did the better job?
185
181
182.7
182.5
• Why do you think so?
183 183.1
184 183.3
avg = avg =
183 183.0
std dev = std dev =
1.41 0.37
Normal / Gaussian Distribution
Importance:
Used as a simple model for complex phenomena – statistics, natural science, social
science [e.g., Observational error assumed to follow normal distribution]
Examples of experiments/measurements
that will produce Gaussian distribution?
http://en.wikipedia.org/wiki/Standard_deviation
Standard Error
N
How do we reduce the size of our standard error?
1) Repeated Measurements
2) Different Measurement Strategy
Assumptions/Procedures
2 1 𝑁 2
The sample variance: 𝑠 = 𝑖=1 𝑋𝑖 − 𝑋
𝑁−1
𝑿 and s2 are estimates of the mean, , and variance, σ2, of the underlying p.d.f.
𝑋 and s2 are estimates for the sample
and σ2 are characteristics of the population from which the sample was taken
𝑋 and s2 are random variables
Expected Value, E(X)
The value that one would obtain if a very large number of samples were averaged together.
𝐸 𝑋 =
The expected value of the sample mean is the population mean
𝐸 𝑠 2 = σ2
The expected value of the sample variance is the population variance
L = 8.5 ± 0.3 cm
L = 11.8 ± 0.1 cm
3.1 ±0.1 cm
http://scidiv.bellevuecollege.edu/physics/measure&sigfigs/C-Uncert-Estimate.html
Accuracy vs. Precision
• Accuracy refers to the agreement between a measurement and the true or
accepted value
• Cannot be discussed meaningfully unless the true value is known or knowable
• The true value is not usually known or may never be known)
• We generally have an estimate of the true value
Three or four?:
40.05 cm
41.20 cm
42.43 cm
42.72 cm
http://serc.carleton.edu/quantskills/methods/quantlit/DeepTime.html
Significant Figures
• Be clear in your communication
• Which is it?
• 40 cm
• 40.0 cm
• 4 x 101 cm
http://serc.carleton.edu/quantskills/methods/quantlit/DeepTime.html
Significant Figures
• State the number of significant figures:
Calculator: 12.6892
Estimated Error: +/- 0.07
Quote: 12.69 +/- 0.07
Error Analysis
What is an error?
• No measurements – however carefully made- can be completely free of errors
• In data analysis, engineers use
• error = uncertainty
• error ≠ mistake.
• Mistakes in calculation and measurements should always be corrected before
calculating experimental error.
• Measured value of x = xbest δx
• xbest = best estimate or measurement of x
• δx = uncertainty or error in the measurements
• Experimental uncertainties should almost always be rounded to one sig. fig
• Uncertainty in any measured quantity has the same dimensions as the measured
quantity itself
Error
• Error – difference between an observed/measured value and a
true value.
• We usually don’t know the true value
• We usually do have an estimate
• Systematic Errors
• Faulty calibration, incorrect use of instrument
• User bias
• Change in conditions – e.g., temperature rise
• Random Errors
• Statistical variation
• Small errors of measurement
• Mechanical vibrations in apparatus
Accuracy and Error
• Which type of error, systematic or random?
• Relative Error
How do you account for errors in calculations?
• The way you combine errors depends on the math function
• added or subtracted –
• The sum of two lengths is Leq = L1 + L2. What is the error in Leq?
• multiplied or divide –
• The area is of a room is A = L x W. What is error in A?
• other functions (trig functions, power relationships)
• A simple error calculation gives the largest probable error.
Sum or difference
• What is the error if you add or subtract numbers?
x x y y z z
w x yz
w x y z upper bound
What is the error in length of
molding to put around a room?
• L1 = 5.0cm 0.5cm and L2 = 6.0cm 0.3cm.
• The perimeter is
L L1 L2 L1 L2
5.0 cm 6.0 cm 5.0 cm 6.0 cm
22 cm
• The error (upper bound) is:
L L1 L2 L1 L2
0.5cm 0.3cm 0.5cm 0.3cm
1.6cm
Errors can be large when you
subtract similar values.
• Weight of container = 30 ± 5 g
• Weight of container plus nuts = 35 ± 5 g
• Weight of nuts?
x x y y z z
x y
w
z
( x x) ( y y )
w
z z
• The relative error is the sum of the relative errors.
w x y z
upper bound
w x y z
What is the error in the area
of a room?
• L = 5.0cm 0.5cm and W = 6.0cm 0.3cm.
A L W 5.0cm 6.0cm 30.0cm 2
• What is the relative error?
A L W
A L W
0.5cm 0.3cm
.15 or 15%
5.0cm 6.0cm
• What is the absolute error?
w B x
What is the error in the
circumference of a circle?
• C=2πR
• For R = 2.15 ± 0.08 cm
• C = 2 π (0.08 cm)
= 0.50 cm
Powers and exponents
w sin( x )
w sin( x x ) sin( x )
Remote Measurement Lab
“Calculus of Errors” Explanation