Beruflich Dokumente
Kultur Dokumente
(or Example)
*ou wor+ in a cell phone factory and are as+ed to remo"e cell phones at random off of the assembly line and turn it on and off$ Each time you remo"e a cell phone and turn it on and off% you are conducting a random experiment$ Each time you pic+ up a phone is a trial and the result is called an outcome$ If you chec+ ,-- phones% and you find . bad phones% then relati"e fre#uency of failure / .0,-- / -$-,.
Statistics in Engineering
Engineers apply physical and chemical laws and mathematics to design% de"elop% test% and super"ise "arious products and ser"ices$ Engineers perform tests to learn how things beha"e under stress% and at what point they might fail$
Statistics in Engineering
1s engineers perform experiments% they collect data that can be used to explain relationships better and to re"eal information about the #uality of products and ser"ices they pro"ide$
(re#uency 2istribution:
Scores for an engineering class are as follows: .3% 4.% 3-% 5.% 63% 45% 6-% 3.% 5.% 33% 4-% 53% 6,% 37% 57% 5-% 5-% 3.% 6.% 5.% .7% 6,% .6% 5,% 54 To better assess the success of the class% we ma+e a fre#uency chart:
8ow the information can be better analy&ed$ (or example% 7 students did poorly% and 7 did exceptionally well$ 9e +now that 4 students were in the a"erage range of 5-' 54$ 9e can also show this data in a fre#$ histogram P2(!$
Divide each no. by 26
:umulati"e (re#uency
The data can be further organi&ed by calculating the cumulati"e fre#uency :2(!$ The cumulati"e fre#uency shows the cumulati"e number of students with scores up to and including those in the gi"en range$ ;sually we normali&e the data ' di"ide ,6$
Random errors are generated by a number of unpredictable "ariations in a gi"en measurement situation$
<echanical "ibrations of instruments or "ariations in line "oltage friction or humidity could lead to random fluctuations in obser"ations$
9hen analy&ing data% the mean alone cannot signal possible mista+es$ There are a number of ways to define the dispersion or spread of data$ *ou can compute how much each number de"iates from the mean% add up all the de"iations% and then ta+e their a"erage as shown in the table below$
1s exemplified in Table ?4$@% the sum of de"iations from the mean for any gi"en sample is always &ero$ This can be "erified by considering the following:
1 x = xi n i =1
d i = ( xi x )
9here xi represents data points% x is the a"erage% n is the number of data points% and d, represents the de"iation from the a"erage$
d = x x
i =1 i i =1 i i =1
d
i =1
= nx nx = 0
Therefore the a"erage of the de"iations from the mean of the data set cannot be used to measure the spread of a gi"en data set$ Instead we calculate the a"erage of the absolute "alues of de"iations$ (or group 1 the mean de"iation is ,4-% and Aroup B is 3,-$ 9e can conclude that Aroup B is more scattered than 1$
>ariance
1nother way of measuring the data is by calculating the "ariance$ Instead of ta+ing the absolute "alues of each de"iation% you can Bust s#uare the de"iation and find the means$ n'?! ma+es estimate unbiased
v=
2 ( x x ) i i =1 n
n 1
Ta+ing the s#uare root of the "ariance which results in the standard de"iation$
s=
(x x)
i =1 i
n 1
The standard de"iation can also pro"ide information about the relati"e spread of a data set$
( xf ) x= n
9here x / midpoints of a gi"en range f / fre#uency of occurrence of data in the range n / f / total number of data points
(x x)
n 1
8ormal 2istribution
9e could use the probability distribution from the figures below to predict what might happen in the future$ i$e$ next yearCs studentsC performance!
8ormal 2istribution
1ny probability distribution with a bell' shaped cur"e is called a normal distribution$ The detailed shape of a normal distribution cur"e is determined by its mean and standard de"iation "alues$
zi = (xi - x) / s
;sing Table ?4$??% approx$ 63F of the data will fall in the inter"al of -s to s% one std de"iation G 4.F of the data falls between ',s to ,s% and approx all of the data points lie between '7s to 7s (or a standard normal distribution% 63F of the data fall in the inter"al of z / '? to z / ?$
Frequency A 7 6 5 4 3 2 1 0 2 3 4 5 6 7 8 9 10
9 8 7 6 5 4 3 2 1 0 12 13 14
Frequency B
15
16
17
18
19
20