ࡱ> 9;8M 9bjbj== ^WW"lXXXl8R,~<l#Fll"n"n"n"n"n"n"$/% O'x"X'"#VlXl"l"!h,,XH"  *>l ("H"$#0#8"''H"llTopic: Normal Distribution Recap: Continuous random variable: takes all possible values in an interval Probability density function (pdf): f(x) such that P(a0 for all x and  EMBED Equation.3  Note: P(X=x)=0 and P(X>x) = P(X>x) Cumulative distribution function: F(x) = P(X Tile to rearrange the graphs.) What is common about these distributions? (b) What are the key differences among these distributions? Suggest two characteristics that could be used as parameters of this distribution (what two things do you think best differentiate the distributions from each other).  These mound-shaped, symmetric distributions are often modeled by normal distributions. The pdf for the normal distribution with parameters m and s is EMBED Equation.3 , -( < x < (. Note that this distribution is unimodal and symmetric about its mean m. You can show that the inflection points of the normal curve correspond to x = m+s and x = m-s. (c) Type MTB> describe c1-c7 and suggest models for each distribution. (d) Suppose that the index finger lengths of criminals follow a normal distribution with mean m=11.546 cm and standard deviation s =.55 cm. (Prisons used to record data on prisoners such as finger lengths in an attempt to classify traits of criminals that differed from noncriminals.) Let X = length (in centimeters) of a randomly selected criminal index finger. How would you determine P(X<11)? Clearly, you do not want to want to integrate the above probability density function. Unfortunately that function cannot be integrated in closed form. Luckily we have alternatives. First, we will standardize the data by subtracting the mean and dividing by the standard deviation. Do this for the data in C2, storing the results in C9: MTB> let c9=(c2-11.546)/.55 (e) Produce a histogram and numerical summaries (describe) for this new variable. Describe the shape, center, and spread (location of inflection points) of this distribution. (f) Suppose sizes of Arbys sandwiches follow a normal distribution with mean m=7.518 and standard deviation s=1.662. Standardize the data in C5 storing the results in C10 and describe this distribution (stemplot). How does this distribution compare to the distribution in (e)? Def: The normal distribution with parameters m=0 and s=1 is called a standard normal distribution. We reserve the letter Z to denote a random variable that has a standard normal distribution. Any normal distribution can be  standardized to the standard normal distribution. (g) Use the let command to determine how many of the observed finger lengths are less than 10.5cm: MTB> let c11=(c2<10.5) MTB> tally c11 Divide the number of 1s by 3000 to find the proportion of lengths that fall below 10.5 cm. (h) With your calculator, standardize the value of 10.5 by subtracting the mean m =11.546 and dividing by the standard deviation s =.55. Use the let command (creating C12) to determine how many of the standardized values in C9 fall below the standardized value for 10.5. How does this proportion compare to what you found in (g)? z = proportion below: Calculating Probabilities and Percentiles from Normal Distributions We will use the fact that P(X<x)=P(Z<(x-m)/s) to find P(X<x). We will first standardize the observation and then find P(Z<z) where these probabilities have been tabulated in Table A.3. We can also denote P(Z<z)=F(z). (i) Use Table A.3 to calculate the proportion of the standard normal distribution that lies below z=-1.90. Compare to the observed proportion.  (j) Assuming the college entrance exam scores follow a normal distribution with mean m=51.1 and standard deviation s=19.29. Calculate the probability a randomly selected student scores above 70%. [Sketch and label the distribution, standardize, use table to find probability below.]  (k) How much would someone need to score to fall in the top 10% of the distribution? Hint: Work backwards. (l) Determine the probability that randomly selected student scores within one standard deviation of the mean. (m) You can also use Minitabs cdf command to find this probability by using: MTB> cdf 31.8; MTB> cdf 70.4; SUBC> normal 51.1 19.29. SUBC> normal 51.1 19.29. or Calc > Probability Distribution > Normal specifying the mean, SD, and input constant. (n) See how this prediction matches our exam data in C1: MTB> let c13= (c1>31.8 & c1<70.4) MTB> tally c13 (o) Do a similar tally with the Arby s sandwiches (use the sample mean and standard deviation of C5 to determine the two values  EMBED Equation.3  and  EMBED Equation.3  and then use the let command to determine how many data values fall in the interval). What percentage of the observations fall within one standard deviation of the mean? (p) What percentage of the observations fall within two standard deviations of the mean?  While these calculations have been approximations, the general empirical rule is that with data that roughly follow a normal distribution: Roughly 68% of the observations fall within 1 standard deviation of the mean Roughly 95% of the observations fall within 2 standard deviations of the mean Roughly 99.7% of the observations fall within 3 standard deviations of the mean These can be verified for the theoretical normal distribution using Table A.3 or Minitab. Normal Approximation to Binomial Now examine the data in C8, let X = number of boys in a family of four children. (q) Is X a discrete or continuous random variable? Explain. (r) Can X follow an exact normal distribution? Explain. (s) What distribution does X follow exactly? (Give the name and the parameter values.) Often we can approximate a binomial distribution with the normal distribution. In general, the rule of thumb is that this approximation applies well when np> 10 and n(1-p)>10. When this rule of thumb is satisfied, we can approximate a binomial(n, p) distribution with a Normal(m=np, s= EMBED Equation.3 ) distribution. (t) Simulate 500 observations from a Binomial distribution with n=50 and p=.5 MTB> random 500 c15; SUBC> bino 50 .5. Examine a histogram of this distribution. Does it appear approximately normal? Does it satisfy the above conditions for the normal approximation to the binomial to be valid? (u) Simulate 500 observations from a Binomial distribution with n=50 and p=.05. Examine a histogram of this distribution. Does it appear approximately normal? If not, what shape does it have? Does it satisfy the above conditions for the normal approximation to be valid? (v) Return to the scenario in (t). Suppose we wanted to calculated P(X< 20). Use the binomial distribution to find this probability exactly: MTB> cdf 20; SUBC> bino 50 .5. Use the normal distribution with mean =50(.5) and SD= EMBED Equation.3  to approximate this probability: MTB> cdf 20; SUBC> normal 25 3.54. To see why this approximation is not very accurate, consider P(X=20). (w) What is P(X=20) in the binomial distribution? What is P(X=20) in the normal distribution? (x) To make sure X=20 is included in the probability, we will make a continuity correction and actually calculate P(X<20.5) for the normal approximation. Use the cdf command to calculate this probability. Is the approximation more reasonable now? Interpretation of Z Scores on the Scholastic Aptitude Test (SAT) follow roughly a normal distribution with mean m=1000 and standard deviation s =200. Scores on the American College Test (ACT) follow roughly a normal distribution with mean m =20.6 and standard deviation s=6.2. Suppose Bobby scores 1180 on the SAT but Kathy scores 28 on the ACT. (l) To compare these two performances we can standardize them. Subtract the corresponding mean and divide by the corresponding standard deviation to see how many standard deviations above the mean each student falls compared to their peers. (m) Based on these z-scores, which student would you say performed better? Explain how this relates to the probabilities lying below these z values. GHRowell  PAGE 5 _____________________________________________________________________________________ ( 2002 Rossman-Chance project, supported by NSF Used and modified with permission by Lunsford-Espy-Rowell project, supported by NSF Using Minitab: MTB> cdf  1.90; SUBC> norm 0 1. or Calc>Prob Dist > Normal specifying m, s, x Using Minitab: MTB> cdf 70; SUBC> norm 51.1 19.29. Using Minitab: MTB> invcdf .90; SUBC> norm 51.1 19.29. #,-456ABEFIJ]^_`benopq02dfhjnpOJQJ j<EHUj? CJUV jEHUj\? CJUV jUH*H* j>*65N$iC8! J  ! & F & F h^ & F$a$A7f89p FHJLNpr7w  %     < > @ B H J R T Z \  j j EHUjA9= CJUV56jCJUmHnHuOJQJ 5OJQJ5H* jEHUj? CJUV juEHUj? CJUV jUOJQJH*6<  PR &W_>@$\Flbd  ,.0\^`dfhj@ B | ~ !!!!B"C"G""" #r# $n$p%r% jUjCJUmHnHu6565OJQJ>*OJQJOJQJT DFHJLN &Fl`#$d%d&d'dNOPQ !020pr!!!!!!B"Y"Z"["\"]""""""" !" #@#r### $n$p$&&&&&&&&''!(q((?)|)})))* ! & F^r%%%%%%%%%%%%%&&&:'H'q(((>)*********+++ +,,,, ,,,,8,:,<,>,,,,,,P-....///00 >*OJQJOJQJ jhEHUjQ? CJUV>*6556jCJUmHnHuOJQJ jTEHUj? CJUVOJQJ jU j@ EHUj? CJUV=***^,`,,*-P-V.W.X.g/h/i///0000000 & F8^8 & F !#$d%d&d'dNOPQ00O0P0c0d0e0f00000123333444455667787A7K7L7R7S7T7U7V7W777`888999999@99999 jCJCJ0JmHnHu0J j0JU6OJQJOJQJ >*OJQJ jEHUj邉? CJUV jUOJQJ40V1W1X1222222j56666A7V7W777b8d8f88888 9"9"9@9Z999999999 / =!"#$%<DdB  S A? 226xM~).jDp`!z26xM~).j %@CHxcdd``dd``baV d,FYzP1n:L B@?b p00sC0&dT20 KXB2sSRs|1X r3q=`VX@|M83Q>& Ma(w Lڄ>F0^gv [=2L '=s+ 0B1g< 6w)Ԟ,BFT .I OL:7k O.8@LEN3LLJ% H  f8p<9DdB  S A? 2m%V$ڽۄbwp`!wm%V$ڽۄbw@0= @CExcdd``ed``baV d,FYzP1n:LB@?b cg`熪aM,,He`( @2@penR~CP`B@Vg$u m%T 1^&sq-n#77 K+a`{t1 M-VK-WMcn=P{ͭDEwɬJX@:*;L ~Z%x?9YA*4,b5* R @% N[LLJ% H X,Vx1DdB  S A? 2ZYfRt}e8Xwp`!oZYfRt}e8X @C=xcdd``dd``baV d,FYzP1n:L ؅,56~) @ k?'30sC0&dT20 KP 27)?(5'ky(30I] Hq090d>UB;׼Y\\,c1b*cDV$7$37X/\!(?71? 2B})0z 8H" K`/0&Th`{5Ҹa)=4Ĥ\Y\ t0.?3jcDd}B  S A? 2RlȺ[>p`!RlȺ[>@ hxtoxcdd``> @c112BYL%bpu_C΀H9@ڈˆɁ$g`bu+!kr.V3p{OY ^@,@{C2sSRsp b/#?Ӹ@ARGptTA48_"%|Ipx@*45|[6T6&8^C4"EW?| 3"~e)?x8ӒgObpߖ\ c3{ (.hyq{w}5XXX:/Ӽx[VBvV:?/ߧN\'$uN?Sa\-zB b_mݯDfu B_s64w-4xu:33@Dh~^KKEՏAw%MY^?hގ[WT:oOGa嘃Y^2 ~ 2 Q苷-/DdP  S A? "2p1X[Y5pt%L `!D1X[Y5pt%`:xcdd``~$d@9`,&FF(`Tic A?d=bf6aP5< %!  @_L ĺE",a L *'] ZZ< f22r`dW> ~E%`Bܤr]..3H][98t v 0y{Ĥ\Y\ qAC:t@bPBXDdP  S A? "2pB1d;, dL`!DB1d;, d`:xcdd``~$d@9`,&FF(`Tic A?d=bf6aP5< %!  @_L ĺE",a L *'] ZZ< f22  !"#$%&'()*+,-./1234567N:=>?A@BDCEFGIHJLKMQgOPRTUVWXYZ[\]^_`abcdefRoot Entry2 F  *><Data 0WordDocument1^ObjectPool4 @ *>  *>_1065980764,F@ *>`Y *>Ole CompObjfObjInfo !&+.146789:;=>?@AC FMicrosoft Equation 3.0 DS Equation Equation.39quG1 f(x)dx """ +" =1 FMicrosoft Equation 3.0 DS EqEquation Native c_1065980804' F`Y *>`Y *>Ole CompObj fuation Equation.39qu>@ l f(y)dy ""x +" FMicrosoft Equation 3.0 DS Equation Equation.39qObjInfo Equation Native  Z_1065980830F`Y *>`Y *>Ole  CompObj fObjInfoEquation Native ^_1065980852F`Y *>`Y *>uB"l  xf(x)dx """ +" FMicrosoft Equation 3.0 DS Equation Equation.39qu``9\# (x") 2 f(x)dx """ +"Ole CompObjfObjInfoEquation Native |_1033845057F`Y *>`Y *>Ole CompObjfObjInfo FMicrosoft Equation 3.0 DS Equation Equation.39qt f(x)=1 2  e "12 2 x"() 2Equation Native _1065981856"F`Y *>`Y *>Ole CompObj f FMicrosoft Equation 3.0 DS Equation Equation.39qu 2x"s FMicrosoft Equation 3.0 DS Equation Equation.39qObjInfo!"Equation Native #5_1065981849$F`Y *>`Y *>Ole $CompObj#%%fObjInfo&'Equation Native (5_1065976401)F`Y *>`Y *>u` 2x+s FMicrosoft Equation 3.0 DS Equation Equation.39qu.  np(1"p) Ole )CompObj(**fObjInfo+,Equation Native -J_1065976553.F`Y *>`Y *>Ole /CompObj-/0fObjInfo02 FMicrosoft Equation 3.0 DS Equation Equation.39qu:  50(.5)(.5)  Oh+'0 $ @ L X dpxEquation Native 3V1TableS'SummaryInformation(35DocumentSummaryInformation8<Hr`gW> ~E%`Bܤr}.3H]]98t v 0y{Ĥ\Y\ qAC:t@b5BKDd`J  C A? "2O)H*\ֿ`!O)H*\ֿX hOxڕR1KPM P;TQT P:nqpȨExKb_8}w߻//* J!ZeFbsBW)AyQ˫*d"y#vY_Ǘ=D2;d44ZTKV{ mR:ӧI/օ\$?|?AлQ84ø?}rʡe}Hێb˓J[.+ P~/?G~D>{(#$ B_ aω[;q +Nizf ٳ#H8vj|6L^x0DdJ   C A ? "2q/+3b!.|n`!fq/+3b!.|@0= h4x]KP.ij҂:8 %RcuhbQN N.. ƻG{w ^>D3$*p+I :Xuu؆J`ٗ^oX ǓXO27$|}47Zm-aѲwLM>mZڳ!tԜ[ ;ŷ?A<,irϓu1Sеxɞr&B'i;D3rw#Hؼoe HMgy!.{_ԞsOiFStat 321 Lecture tat Beth ChanceethethNormala M. Rowelle3 RMicrosoft Word 9.0@@TDL@F=@~T)> ՜.+,0 hp  Cal Poly State University SLO=4# Stat 321 Lecture Title  FMicrosoft Word Document MSWordDocWord.Document.89q i4@4 NormalCJ_HmH sH tH 0@0 Heading 1$@&5<A@< Default Paragraph Font(>@( Title$a$5,@, Header  !, @, Footer  !<C"< Body Text Indent ^&)@1& Page Number^$^$^$iC< @ABCDE' D     % &  YZvwv'EGHIJK+,-./0~)*cTUVWY1Jlmn,:z 34{9!,"-"."/""""1#a######$$$$$1$H$I$X$i$$$      0 000   0  0@0@@0@@0 0p r%09"%&*, "*0"99#'()+-.9$I]_Qegz(<>*,2FH$::::::::: !8@\(  D   "D   "\  3 " b  C "I \  3 " B S  ?'EW$$#tC%Kt()td)t$tH`ei #79Lhiq4:9=nvT`  OR-.IJM   $"8#?#############)$,$]$c$$$*,CELNDFxz' 6 k r @ C @ A [\24S@BZc+TVy{'*TVy{02.qsRTv!x!"$""######$ $1$G$i$$$33333333333333333333333333333333333333333333333333333333333Default9C:\My Documents\Classes\Stat 321 - W02\Lectures\day15.docDefault`C:\Documents and Settings\Default\Application Data\Microsoft\Word\AutoRecovery save of day15.asdDefault9C:\My Documents\Classes\Stat 321 - W02\Lectures\day15.docDefault9C:\My Documents\Classes\Stat 321 - W02\Lectures\day15.docDefault9C:\My Documents\Classes\Stat 321 - W02\Lectures\day15.docDefault9C:\My Documents\Classes\Stat 321 - W02\Lectures\day15.docDefault9C:\My Documents\Classes\Stat 321 - W02\Lectures\day15.docDefault9C:\My Documents\Classes\Stat 321 - W02\Lectures\day15.doc M. Rowell8C:\WINDOWS\Desktop\math2050\Final\07_normaldist_bc15.docGinger Holmes RowellcC:\My Documents\_Ginger\_Grants\NSF A&I\2002 Fall math2050\_coursepack\Final\07_normaldist_bc15.docH~y V#% ?, fr  z  hh^h`OJQJo( hh^h`OJQJo( hh^h`OJQJo( hh^h`OJQJo( hh^h`OJQJo(H~yfrV#% z?,"##$@Ao D D D ^^^^^^^ !#$`@``@` `` @```0@```` `D@`$`L@`,`\@`2`4`l@`8UnknownG:Times New Roman5Symbol3& :ArialO1CourierCourier New?5 :Courier New"1hA5hF:hfhbf=Q204#2Stat 321  Lecture Beth Chance M. RowellCompObjBj