Friday, November 10, 2006
Chapter 1

Statistics – science of data – collection of, organization, analysis and interpretation.

Population – entire group of individuals
Variable – a characteristics of an individual

Variables are
Quantitative – numerical
Qualitative – non-numerical

Statistics are:
Descriptive – get the informational and report
Inferential – get the information and draw parts of it and interpret it.

Sample – subset of population
Should be random, but how do we get a random sample?

1000 people, sample of 100 that needs to be random.
Number the sample, then take 100 out of that (draw them out of a hat so to speak)
We can also use a random table. (p. 6 in book)(instructions are there)

Chapter 2
Central Tendency

• Mean
• Medium
• Mode

Range, variance and standard deviation

p. 44

Stem and leaf know what it is

whole number as the stem. the decimal points become the leafs.

sometimes the stems must be broken in to seperat parts.

30 could be .0 to .4 and then .5 to .9

Frequency distribution -

1. tabular summery
2. frequency of observation in each class

p. 46

65 invoices

need to figure out how many classes are needed.

you do not want to have too large a sample or too many samples.

general rule is 2^k > N where k is number of classes

2^6 = 64

2^7 = 128

2^7 is greater than the 65 observations

so we use 7 classes. Now class length

high number - low number / number of classes

29 - 10 /7 = 2.7147 take next highest number 3

make your table

10 - 12
13 - 15
16 - 18
19- 21
22 - 24
25 - 27
28 - 30

then add the frequencies in the table

10 - 12 3 3/65 =
13 - 15 14 14/65
16 - 18 23 23/65
19- 21 12
22 - 24 8
25 - 27 4
28 - 30 1

this would be 65 and the last collumn relativity , should be 1 totaled

Class bounteries, take .5 on either side of the number. this makes sure that you get all the numbers

next a histogram (p. 48 in book)

connect the midpoints on the blocks to get a distribution

population parameter - a number calculated from a population and discribes a population.

population mean - mu

standard deviation - sigma

sample statistics - calculated for a sample and describes them

x-bar - sample means

S -sample standard deviation

point estimates.

measure of central tendencies -

1. mean
2. medium
3. mode

paper notes 1

sample means - if you have n as size of sample, then

xBAR = EXi/n sumation size...

30. 8 31.7 30.1 31.6 32. 1

n = 5

xBAR = add them all/devide by 5 = 156.5/5 = 31.31

46 54 42 46 32 sample observation

xBAR = all/5

= 44

X mean - average

2) median

midpoint of distribution

1. arrange the numbers in some order (ascending or decending)
2. if n is odd then median is the middle observation
3. if n is even then middle two observations are devided by 2

42, 32, 54, 46, 46

32 42 46 46 54

n= 5 2.5 is 54

2210 2255 2350 238- 2390 24320 2440 2450 2350 2630 2825

n is 12

numbers are ordered, middle two are 2390 + 2420/ 2 = 2405 medium

Mode

Mode is the observation that has greater frequency

in the 5 2 digit numbes above it would be 46

mediam and mode are not affected by extreme values

the mean will be affected by extreme values

Normal distribution the symetric curve around the mean. 1/2 above and 1/2 below.

if normal mean = medium = mode

skewed distribution

skewed right left to right mean medium mode

skewed right mode medium mean

measure of central tendencies we have just looked at.

measure of variations

1. range

2. variance

range take the largest and subtract the smallest is the range

variance - population variance sigma^2

paper notes 2

Sample variance S^2 = sum of (Xi - xBAR)^2 / n - 1

this n - 1 gives us an unvbiased estimate of sigma^2

sigma is population standard variation

s is sample

sigma is sqrt of sigma^2

s = sqrt of s^2

from book profit margin of french fries (p. )

8 % 10% 15% 12 % 5%

mu = sumx/5

mean