AP Statistics some et ee
Period.
Unit 08 = HW #47
Chi Square: Goodness of Fit Test
1, Acme Toy Company prints baseball cards. The company cicims that 30% of the cards ore
rookies, 60% veterans, and 10% are All-Stars, The cards are sold in packages of 100. Suppose a
randomly selected package of cards has 50 rookies, 45 veterans, and 5 All-Stars. Is this
consistent with Acme's claim? Use a 0.05 level of significance.
Sta: Ho: The Stated dismpunonot Acme Toy Companys
baseball Cards is correct.
A005 a: The StoHed Cismiourion of Acme Toy Company!
Dabo cards W nor Correct.
PIN” Random: randomiy suleced package Y
I07 COME NON. (Cece Fyry SCOCOLL revEKe Card s/A yess ¥
ers gs) USO < CU Vea CALCU
eo J DOL OM ALLSTON COMAY/aiyus
Large (OUMS: expected Count: 3075 ¥ rokies
Grea 2S Goons v vererons
BECAUR Our Condittory art IOVS ¥ A\i-Sters
vine we Wil perfor a YZ veer For goodness oF Fit.
deez
p-valug = 0.000065 42
CONUUAL! BECAULK oUF p-value 0.00005592 15 LSS
tan Our SigniAcanw evel 4 +005, We Feet
HAR WU There (3 Convineivy emaene Har
Hae Sated distmbution oF ACL Toy Companys
DasbOU Caras 1S tinconter.dr, TU NST. OF StU WE equity for Slats Cy fe Wy Ae nanw ebuas
i a
2. Asludy was performed to determine whether or not the name of G Course Ba SAGHES OF rer
student registrations. A statistics course in a lorge schoo! disirict was given 4 different names in
‘a couse catalog. Each name corresponded fo the exact same statistics course. A random
sample of student registrations was recorded and the resulis are given below:
‘Course Name _[ Number of Registrations_| € ype ces
Statistical Applications 25 Wait,
Stalisticai Reasoning 22 21s |
[Statistical Analysis 30 2A26
The Practice of Statistics 40 z 2425
TOTAL nz Wt
Do these data suggest the name of the course has an effect on siudent registrations?
Conduct an appropriate statistical test to support your conclusion.
SHAH: Ho! The NaMus oF Sranstes cours AO Not have
cay eefeer On tu Number oF Studer WhO
register fOr them.
a: Te noes of Sans nes COUN AO rave
on cheer on fue nunber OF SUGLU Wid
register fy tun
BION: Random: yanclom Sane of SHdwNr eqitranon.”
1s. CONAINONE yet WO SAU SMOG who TA Syethonic$
Large COUN: GU Vepece COUN Gre WT YA = 24.28 7/5"
RaQ, OU CONdIMONY Gre YU, We WIL purvovin
A 2 UE fv BNDAKES oF FIt.
WE ye 2 o- smash ,(22-2425)* GO-22S,
As 2425 24,25 fone aipe
vege sranistre = W385
Prva = 9.00435
Contes BECHULK OU PrValue 0044223 WS Greater
Man our SigmiPicanw level ¢=0.08, we tan!
to reyeck HAL MUL. Thert 16 not COnvinelg
OVAL HAE He Names of (tangs
Courtes pave an effect on Hie nuunileer of
SMALLS WD register fOr Hu
A200gy: He pirds Od WET pre eee partrculad tres types vs tt au.
3. Researchers studied the behavior of birds that were searching for seeds and insects in an
Oregon forest. In this forest, 54% of the trees were Douglas firs, 40% were ponderosa pines, and
6% were other types of trees. At a randomly selected time during the day, the reseorchers
observed 156 red-breasted nuthatches: 70 were in Douglas firs, 79 in ponderosa pines, and 7 in
other types of frees. Do these data provide convincing evidence that nuthatches prefer
Particular types of irees when they're searching for seeds and insects?
State? Ho: The Gismounon oF Ked-preasied nuhatcha is
eQual QMdng CU Tree typ (Nan Oregon forcst.
dco.es Bat Mu dismpurion Of Ho- preasied nuthatius is
Nor CUM Among OWA tree Hypes in ah Liev
DIAM: vanclom: randomuy celecita time Y (Aka ISU :
(W/, CONAINEN 1602 OU Fed -breanted TARGoMy Coen
Nelo NUENAACHLS in An OCGA Hen VET)
Large? Counts Iswos4= BUI47, 5 douglas tid ¥
ISW-0HO= Y2.4 % S pondeesa pines
1su'0.0¥* 4.3 7% otuertrees ~
BECaUr our conditons GE Wut, we will pewform
OW? eSt for cod OF Ft
BBs yas Goud, Ga -624), eased? _
e424 wna ‘chad 7.4182
OF 2
P-VALLUA = 0.024499
ConCude : BeCLUL QU pvaLLt 0.0245 6 ks Man
our SIQMIA CANE tewtl A 20.05, we reject Hue
Wun. TUE Convindtry euiaunee Har
rede preasied Mud hatches prefer panictiar fypur
OF ARE WNALN Haye Seorcluing for
; 7 Feed,
invects (ihwir AtsmbUHOA tS hot cien, anory
Cua ave Hypes).|. Faked numbers in tox retums, invoices, or expense account claims often display patterns that
aren't present in legitimate records. Same patterns are obvious and easily avoided by a
Clegver crook. Others are subtler. Its a striking fact that the first digits of numbers in legitimate
records often follow a model knows and Benford's law. Call the first digit of a randomly chosen
record Xfor short. Benford's law gives this probability model for X {note that the first digit
cannot be 0).
1" Digit i ry 3 [4 5 16 - 8 9
Probability | 0.301 10.176 [0.125 [0.097 | 0.079 [0.067 | 0.058 | 0.051 0.046
expected 1$-25 AA B25 2H2s 41s Wis MS 21S WS
A forensic accountant who is familiar with Benfora’'s law inspects a random sample of 250
invoices from a company that is accused of committing fraud. The table below displays the
sample data.
Voigt [1 2 3 4 516 7 {8 9
Probability | 61 50143 [34] 25 16 [7 8 é
a. Are these data inconsistent with Benford’s law? Carry out on appropriate test where
@ = 0.05 level to support your answer.
Save: ATW GIGMipwrTdn OF Ast Cligits oa a parmoutar
Company Fo\lows Ben fords law.
cos TH TAs AismbUtbn OF fist algits at a parnicullar
Company coer not follows Benford LAW
Plan: random: rondom Samp a 2.50 invois 7
WO/, COndITION: N=296 2500¢Q\\ invoices at rns Company
Lage (Oulet: arteypeceed courts (Shown above) ort 7S 4
Because OUV CONaIMOKS are mut we Will
ma xt dest for Goodness of Fit
to yes (uits25)", BoO-HY J?) (43 325)*y
IS. 44
vo
$ Bs
test SrANTNE= YV.AOTS AFF p-vAWL= 0.00000 2104
CONCUUCe: Beca@uye our p-valur 21a’ is Wy Hran our
SIQMMACANLE Hut A =0.05 He Fee CE HAL MULL. There
ConMining CIhEnee HAak He Clismburiba ef Ash aig: tt
for tuls company (oes hor Follow BenfordsLaw. FRAUDS
b. Describe a Type | érror and a Type Il error in this setfing, and give a possible
sequence of each. Which do you think is more serious?
Carel Gist. QoS Follow Hu Law bur we Hunkit
mt SO we ActuKcl tem of fraud wrongly.
Typell: Thy Ast. doesnt follow Hu Law Mut we Kune
CE does So they ger away with Aqua.