KEY FORMULAS Chapter 2 Mean for ungrouped data: µ=∑x/N and

advertisement
KEY FORMULAS
Chapter 2
ο‚·
ο‚·
Mean for ungrouped data: µ=∑x/N and π‘₯Μ… =∑x/n
Mean for grouped data: µ=∑mf/N and π‘₯Μ… =∑mf/n
where m is the midpoint and f is the frequency of
a class
ο‚·
Median for ungrouped data = Value of the (
ο‚·
ο‚·
term in a ranked data set
Range = Largest Value-Smallest Value
Standard deviation for ungrouped data:
𝜎=√
2
∑𝑁
𝑖=1(π‘₯𝑖 −µ)
ο‚·
2
∑𝑛
𝑖=1(π‘₯𝑖 −π‘₯Μ… )
2
∑𝐾
𝑖=1 𝑓𝑖 (π‘šπ‘– −µ)
Standard deviation of discrete random variable x:
𝜎 = √∑ π‘₯ 2 𝑃(π‘₯) − πœ‡2
ο‚·
ο‚·
ο‚·
ο‚·
ο‚·
Hypergeometric probability Formula: P(x)=
(π‘₯π‘Ÿ )(𝑁−π‘Ÿ
𝑛−π‘₯ )
(𝑁
𝑛)
𝑒 −πœ† πœ†π‘₯
ο‚·
Poisson probability Formula: P(x)=
ο‚·
Mean and variance of the Poisson probability
distribution: E(x)= πœ‡ = πœ†, Var(x)= πœ‡ = πœ†.
π‘₯!
Chapter 5
ο‚·
2
∑𝐾
𝑖=1 𝑓𝑖 (π‘šπ‘– −π‘₯Μ… )
𝑛−1
𝜎
𝑠
πœ‡
π‘₯Μ…
Chebyshev’s Theorem:
For any population with mean µ, Standard
deviation 𝜎 , and k>1, the percent of observations
that lie within the interval [µ±k 𝜎] is
at least [1-(1/π‘˜ 2 )]%
where k is the number of Standard deviations.
Emprical Rule:
For many large populations the empirical rule
provides an estimate of the approximate
percentage of observations that are contained
within one, two, or three Standard deviations of
the mean:
o Approximately 68% of the observations
are in the interval (πœ‡ ± 𝜎) ,
o
Approximately 95% are in the interval
(πœ‡ ± 2𝜎),
o Almost all of the observations are in the
interval (πœ‡ ± 3𝜎).
Interquartile Range: IQR = 𝑄3 − 𝑄1 where 𝑄3 is
the third quartile and 𝑄1 is the first quartile.
∑(π‘₯𝑖 −π‘₯Μ… )(𝑦𝑖 −𝑦̅)
ο‚·
πΆπ‘œπ‘£(π‘₯, 𝑦) =
ο‚·
Correlation coefficient;
𝑛−1
π‘Ÿπ‘₯𝑦 =
Mean and Standard deviation of the uniform
probability distribution:
πœ‡=
Coefficient of Variation:
πΆπ‘œπ‘£(π‘₯, 𝑦)
𝑠π‘₯ 𝑠𝑦
Chapter 3
ο‚·
(N
)=
n
ο‚·
ο‚·
ο‚·
P(A ∪ B) = P(A) + P(B) − P(A ∩ B)
ο‚·
N!
n!(N−n)!
Bayes′ Theorem: P( Ai ∣ B ) =
P(Ai )P(B∣Ai )
P(A1 )P( B∣∣A1 )+β‹―+P(An )P( B∣∣An )
π‘Ž+𝑏
2
and 𝜎 = √
(𝑏−π‘Ž)2
12
𝑧 value for an x value:
π‘₯−πœ‡
𝜎
Normal Distribution Approximation for Binomial
Distribution:
𝑧=
ο‚·
Z=
𝑋−𝑛𝑃
√𝑛𝑃(1−𝑃)
ο‚·
Exponential Distribution
The probability that the time btw arrivals is π‘‘π‘Ž or
less is as follows:
𝑃(𝑇 ≤ π‘‘π‘Ž ) = (1 − 𝑒 −πœ†π‘‘π‘Ž )
Chapter 6
ο‚·
ο‚·
Standard deviation (Standard error) of 𝑋̅
𝜎
πœŽπ‘‹Μ… =
√𝑛
If n/N>0.05 Standard deviation (Standard error) of
𝑋̅
πœŽπ‘‹Μ… =
ο‚·
𝜎
√𝑛
𝑁−𝑛
.√
𝑁−1
Standard deviation of 𝑝̂
𝑃(1 − 𝑃)
πœŽπ‘Μ‚ = √
𝑛
Chapter 7
Confidence Interval for;
ο‚· population mean with known variance
𝜎
π‘₯Μ… ±π‘§π›Ό/2
√𝑛
ο‚· population mean with unknown variance
𝑠
π‘₯Μ… ± 𝑑𝑛−1,𝛼/2
√𝑛
ο‚· population proportion
𝑝̂ ± 𝑧𝛼/2 √
P(A ∩ B) = P(B)P(A ∣ B)
Chapter 4
Mean and Standard deviation of the binomial
distribution: πœ‡ = 𝑛𝑝 π‘Žπ‘›π‘‘ 𝜎 = √π‘›π‘π‘ž
CV = π‘₯ 100% or π‘₯ 100%
ο‚·
Binomial probability Formula: P(x)=(𝑛π‘₯)𝑝 π‘₯ π‘žπ‘›−π‘₯ ,
where p+q=1.
and
𝑁
𝑠= √
ο‚·
where 𝜎 and 𝑠 are population
𝑛−1
and sample Standard deviations, respectively.
Standard deviation for grouped data:
𝜎=√
ο‚·
2
Mean of a discrete random variable x: πœ‡ =
∑ π‘₯𝑃(π‘₯)
)th
and
𝑁
𝑠= √
𝑛+1
ο‚·
ο‚·
𝑝̂ (1 − 𝑝̂ )
𝑛
Confidence interval for the population variance
(𝑛 − 1)𝑠 2
(𝑛 − 1)𝑠 2
< 𝜎2 < 2
2
ℵ𝑛−1,𝛼/2
ℵ𝑛−1,1−𝛼/2
Chapter 8
Confidence Interval for;
ο‚·
ο‚·
the difference between means
𝑠𝑑
𝑑̅ ± 𝑑𝑛−1,𝛼/2
√𝑛
Independent samples with known population
variances
(π‘₯Μ… − 𝑦̅) ± 𝑧𝛼/2 √
ο‚·
𝜎π‘₯2
𝑛π‘₯
ο‚·
Tests of the variance of a normal distribution;
(𝑛 − 1)𝑠 2
ℵ2 =
𝜎02
Chapter 10
Hypothesis Testing for Two Sample
ο‚·
Tests of the Difference Between Two Population
Means: Dependent Samples;
𝑑̅ − 𝐷0
𝑑(𝒏−𝟏,𝜢) =
𝑠𝑑 /√𝑛
ο‚·
Tests of the Difference Between Two Population
Means: Independent Samples;
1. Known Variances
π‘₯Μ… − 𝑦̅ − 𝐷0
𝑧𝛼 =
𝜎2 𝜎2
√ π‘₯+ 𝑦
𝑛π‘₯ 𝑛𝑦
πœŽπ‘¦2
+
𝑛𝑦
Independent samples with unknown population
variances and the variances are assumed to be
equal
𝑠𝑝2 𝑠𝑝2
(π‘₯Μ… − 𝑦̅) ± 𝑑𝑛π‘₯ +𝑛𝑦−2,𝛼/2 √ +
𝑛π‘₯ 𝑛𝑦
𝑠𝑝2 =
ο‚·
[(𝑛π‘₯ − 1) 𝑠π‘₯2 + (𝑛𝑦 − 1) 𝑠𝑦2 ]
𝑛π‘₯ + 𝑛𝑦 − 2
2.
Independent samples with unknown population
variances and the variances are not assumed to be
equal
𝑠π‘₯2 𝑠𝑦2
(π‘₯Μ… − 𝑦̅) ± 𝑑(πœ—,𝛼/2) √ +
𝑛π‘₯ 𝑛𝑦
[
πœ—=
ο‚·
Unknown Population Variances: Assumed to
be Equal
π‘₯Μ… − 𝑦̅ − 𝐷0
𝑑(𝑛π‘₯ +𝑛𝑦−2,𝛼) =
𝑠2 𝑠2
√ 𝑝+ 𝑝
𝑛π‘₯ 𝑛𝑦
[(𝑛π‘₯ − 1) 𝑠π‘₯2 + (𝑛𝑦 − 1) 𝑠𝑦2 ]
𝑛π‘₯ + 𝑛𝑦 − 2
Population Variances Unknown and Not
Equal;
𝑠 2 𝑠𝑦2
[ π‘₯ + ]2
𝑛π‘₯ 𝑛𝑦
πœ—=
2
2
𝑠𝑦2
𝑠π‘₯2
(
)
( )
𝑛𝑦
𝑛π‘₯
+
𝑛π‘₯ − 1 𝑛𝑦 − 1
𝑠𝑝2 =
3.
𝑠π‘₯2 𝑠𝑦2 2
+ ]
𝑛π‘₯ 𝑛𝑦
2
2
𝑠𝑦2
𝑠2
( )
( π‘₯)
𝑛𝑦
𝑛π‘₯
+
𝑛π‘₯ − 1 𝑛𝑦 − 1
the difference between two population
proportion
𝑝̂π‘₯ (1 − 𝑝̂π‘₯ ) 𝑝̂𝑦 (1 − 𝑝̂𝑦 )
(𝑝̂π‘₯ − 𝑝̂𝑦 ) ± 𝑧𝛼/2 √
+
𝑛π‘₯
𝑛𝑦
𝑑(πœ—,𝜢) =
√
Sample Size determination
ο‚·
ο‚·
for the mean of a normally distributed population
with known population variance
2
zα/2
σ2
n=
ME2
for population proportion
(zα/2 )2 0.25
n=
ME2
Chapter 9
Hypothesis Testing for One Sample
ο‚·
Tests of the mean of a normal distribution:
population variance known;
Μ…Μ…Μ…
(π‘₯ − πœ‡0 )
𝑧𝛼 =
𝜎/√𝑛
ο‚·
Tests of the mean of a normal distribution:
population variance unknown;
Μ…Μ…Μ… − πœ‡0 )
(π‘₯
𝑑(𝑛−1,𝛼) =
𝑠/√𝑛
ο‚·
Tests of the population proportion;
𝑧𝛼 =
𝑝̂ − 𝑃
√𝑃(1 − 𝑃)/𝑛
π‘₯Μ… − 𝑦̅ − 𝐷0
ο‚·
𝑠π‘₯2 𝑠𝑦2
+
𝑛π‘₯ 𝑛𝑦
Tests of the Difference Between Two Population
Proportions;
𝑛π‘₯ 𝑝
Μ‚π‘₯ + 𝑛𝑦 𝑝
̂𝑦
𝑝
Μ‚0 =
𝑛π‘₯ + 𝑛𝑦
𝑧𝛼 =
(𝑝
Μ‚π‘₯ + 𝑝
Μ‚)
𝑦
𝑝
Μ‚(1 − 𝑝
Μ‚) 𝑝
Μ‚(1 − 𝑝
Μ‚)
√ 0 𝑛 0 + 0 𝑛 0
π‘₯
𝑦
Download