You are on page 1of 32

Observed values

Name 18-30 31-44 45-58 Over 58


Jessica Chastain 51 50 41 42 184
Jennifer Lawrence 63 55 37 50 205
Emmanuelle Riva 15 44 56 74 189 Sample Size is =
Quvenzhané Wallis 48 25 22 31 126 Yes since 205 is maximum but respo
Naomi Watts 36 65 62 33 196
213 239 218 230 900

Expected values

Name 18-30 31-44 45-58 Over 58


Jessica Chastain 43.54667 48.86222 44.56889 47.02222 Ho: People's attitude towards actres
Jennifer Lawrence 48.51667 54.43889 49.65556 52.38889 Ha: People's attitude is not independ
Emmanuelle Riva 44.73 50.19 45.78 48.3
Quvenzhané Wallis 29.82 33.46 30.52 32.2 Assuming Ho is true, the expected v
Naomi Watts 46.38667 52.04889 47.47556 50.08889

(Observed - expected)^2/Expected

Name 18-30 31-44 45-58 Over 58


Jessica Chastain 1.275693 0.026494 0.285782 0.5364 Test statistics
Jennifer Lawrence 4.323606 0.005783 3.225482 0.108931 We are using chi-square test of inde
Emmanuelle Riva 19.76018 0.763421 2.281529 13.67474
Quvenzhané Wallis 11.08358 2.13902 2.378453 0.04472 Degree of freedom
Naomi Watts 2.32573 3.222572 4.443539 5.830238 p-value

So Ho is rejected in favor of strong s


900
205 is maximum but respondents of age 45+ didn't favor Jennifer Lawrence

e's attitude towards actress is independent of their age


e's attitude is not independent of their age.

Ho is true, the expected values of each pair is given by table on left

77.735896072
sing chi-square test of independence for hypothesis testing.

12 12
1.11345E-11

ejected in favor of strong statistical evidence.


Observed Values

Flight Delta United US Airways


Late 39 51 56 146
On-time 261 249 344 854
Total 300 300 400 1000

Expected Values

Flight Delta United US Airways


Late 43.8 43.8 58.4
On-time 256.2 256.2 341.6
Total 300 300 400

(Observed- Expected)^2/Expected
Flight Delta United US Airways
Late 0.526027397260273 1.1835616438 0.09863
On-time 0.0899297423887592 0.2023419204 0.016862

Test statistics 2.117353


d.f 2
p-value 34.69%

c) Delta United US Airway Overall


Sample proportion 0.13 0.17 0.14 0.146
Number of samples 300 300 400 1000
S.E. 0.0194164878389476 0.0216871698 0.017349 0.011166
Level of confidence 90% 90% 90% 90%
MOE 0.0319372804445521 0.0356722199 0.028537 0.018367
Upper Interval 0.161937280444552 0.2056722199 0.168537 0.164367
Lower Interval 0.0980627195554479 0.1343277801 0.111463 0.127633

d) Ho: p_delayed_flight = 0.15


Ha: p_delayed_flight > 0.15

S.E. 0.0112915898
test statistics -0.354245954

p-value 63.84%
Ho: p_late_delta = p_late_united = p_late_us_airways
Ha: they are not equal

Ho cannot be rejected at 5% level of significance.

No statistically significant data to conclude that flight is delayed more than 15% of time.
3 6
p_afghan 0.29
p_odessa 0.41 Kolkata
Bangalore
alpha 0.05
a.
Ho P_afghan = P_odessa b.
Ha P_afghan<P_odessa

Pooled proportion 0.35


S.E. (p_afghan - p_odessa) 0.067454 Assuming Ho is true

Test statistic -1.778998


P-value 3.76%

So, Ho rejected.

5
Horror Comedy Drama c.
No. of shows 21 24 27 72

Mean viewership 8.492 8.509 8.568 8.526167

Standard deviation of
viewership 1.698 1.543 1.737
Variance 2.883204 2.380849 3.017169
df 20 23 26
Difference from grand mean 0.001167 0.000295 0.00175

SS df MS F P-value
Between Groups 0.078838 2 0.039419 0.01425 98.59%
Within Groups 190.87 69 2.766232

Ho is not rejected
Jan Feb Mar Apr May Jun Jul Aug
22 33 36 34 33 34
24 27 27 26 25 26
9 8 8 8

X_d 7.833333333333
SD_X_d 0.98319208025
n 6
S.E._X_d 0.40138648596

Ho Xd = 5
Ha Xd!= 5 8
a. 9.89
t 7.058865787568 b. -0.693147180559945
df 5 a1 median/0.69315
P-value 0.09% 10.01226
c. a is better because sample mean is unbiased estimato
Ho is rejected at 1% significance level.
d. n 100
Ho: T_Kol - T_Ban = 5 mean 9.89
Ha: T_Kol - T_Ban != 5 S.E. 0.989

S.E. 1.492780982505 P(mean <7.9) 2.21%

Sample variances are not equal


t 0.669890634808 790 Probability that in 790 seco
d.f. 17.82716049383 17 MEAN
P-value 51.19%
0.013169

e. 1.01112234580384
f.
Cars 0
Interval 101
Variance per interval 1.159211

Mean Cars 1.076667

S.E. (X_bar) 0.018183


test statistics 3.604793
P-Value 0.03%
Ho is not rejected
Sep Oct Nov Dec
33 32 27 31.55556 18.77778 9 2.08642
25 26 24 25.55556 1.277778 9 0.141975
8 6

median/0.69315

e mean is unbiased estimator of population mean.

Probability that in 790 seconds more than 100 cars pass


79.87867

1 2 3 4 5
114 56 20 8 1 300
0.005878 0.852544 3.699211 8.545878 15.39254 29.65527

Ho mean = 1.011122
Ha mean != 1.011122
Observed values

Extremely Extremely
dissatisfied Dissatisfied Neutral Satisfied satisfied
Government 18 5 12 8 5 48
Private 8 7 13 15 12 55
Freelancer 5 1 2 7 10 25
31 13 27 30 27 128

Expected values

Extremely Extremely
dissatisfied Dissatisfied Neutral Satisfied satisfied
Government 11.625 4.875 10.125 11.25 10.125
Private 13.3203125 5.5859375 11.60156 12.89063 11.6015625
Freelancer 6.0546875 2.5390625 5.273438 5.859375 5.2734375

(Observed - Expected )^2/Expected

Extremely Extremely
dissatisfied Dissatisfied Neutral Satisfied satisfied
Government 3.495967741935 0.00320513 0.347222 0.938889 2.5941358025 So we can reject Ho at 5% leve
Private 2.125004582111 0.35796547 0.168566 0.34517 0.0136837121
Freelancer 0.183719758065 0.93290865 2.031956 0.222042 4.236400463

Test statistics 17.9968364


d.f. 8
p-value 2.13%
Ho: Level of satisfaction is independent of type of job.
Ha: Level of satisfaction is dependent on type of job.

So we can reject Ho at 5% level of significance and conclude that level of satisfaction and type of job are not independent.
not independent.
Probability (Observed -
Category Observed Distribution Expected Expected)^2/Expected
ABC 95 0.29 87 0.735632183908046
CBS 70 0.28 84 2.33333333333334
NBC 89 0.25 75 2.61333333333333
Independents 46 0.18 54 1.18518518518519
300

Test statistics 6.867484


d.f. 3
p-value 7.62% Mild statisticaly significant data to conclude that
ificant data to conclude that the proportion has changed.
Region 4

a) Ho: mean_rented = mean_owned


Ha: mean_rented < mean_owned

b) Rented Owned
Mean 209.08 254.19
Variance 86.3041 117.0724
Count 90 37
df 89 36

Ho: Population variance are equal. test stat 0.737186


Ha: Population variance are not equal. Ho cannot be rejected

Pooled Variance 95.1653704


S.E. 1.905106307
test statistics -23.6784687
d.f 125
p-value 4.9573E-48

So reject Ho , that is sufficient evidience to conclude that mean rented and mean -owned is not equal and mean_re

c) Ho: population variance = 80


Ha: population variance != 80

test statistics 52.68258


d.f 36
p-value 7.17%

At 7% Ho cannot be rejected. So population variance is not significantly different from 80.

d) Ho: p_owned_1 = p_owned_2


Ha: p_owned_1 < p_owned_2

P_owned_1 0.689655172
P_owned_2 0.710144928
P_pooled 0.700787402

S.E. 0.057912745
test statistics -0.3538039
p-value 36.17%

Not significant evidence to reject Ho.


25%
t be rejected

ned is not equal and mean_rented is less than mean_owned.


9
Region 4
a Ho mean_rented = mean_owned
Ha mean_rented<mean_owned

b X_bar S.D Variance n


Rented 209.08 9.29 86.3041 90 0.958934
Owned 254.19 10.82 117.0724 37 3.164119

Assuming population variance are different

Test statistic -22.21587122


d.f. 172.29280747
1.020389E-52
Ho is rejected.

Testing population variance are equal or not.

Ho Var_rented = Var_owned
Ha Var_rented != Var_owned

Test statistic 0.7371857073


p-value 0.2507946557

Ho is not rejected so variances are equal.

S.D. pooled 9.7552739787


test-statistic -23.67846866 d.f. 125

p-value 2.47865E-48
Ho is rejected.

c. Ho Variance = 80
Ha Variance != 80

n 37
test-statistic 52.68258
p-value 5.58%

At 7 % Ho is rejected. Sufficient evidence to conclude that region 4 variance of owned apartments is significantly di

d. Ho p_owned_region_1 = p_owned_region_2
Ha p_owned_region_1 < p_owned_region_2

Observed vp_owned_regio0.6896551724 116


p_owned_regio0.7101449275 138
p_pooled 0.7007874016

S.E. of difference in proportion 0.057681

test statistic -0.355226508


p-value 36.12%

So Ho is not rejected.
ed apartments is significantly different from 80.
Hostel 5488 6167 6529 4657 3817 5980 3909 4729 4944
Wicketgate 5788 6700 5015 3805 4141 5025 6132 5136 8532

a.
Ho S.D. wicket gate = 2 * S.D. hostel
Ha S.D. wicket gate != 2 * S.D. hostel

test statist 1.4341186724


p-value 42.71%

Ho is not rejected

b.
diff. 1471.2
S.E. w-h 408.53410345
MOE -1.959963985

UL 2271.9121292
LL 670.48787078
4603 5290 4205 4487 5130 4388 4699 4536 5015 4827
6348 6361 8220 8625 4231 5459 9751 5696 7074 8678
Mean Variance
4970 4918.5 495511.7
7077 6389.7 2842491
Matching sets
Difference in scores
1
4
-2
-6 test statist 0.814192
0 p-value 43.14%
-3
-6
8 Can't reject Ho that there is no significant difference between round 1 and round 2 scores
2
7
-1
8
2
1.076923 4.7690239823 13
X_d_bar S.D. sample n
round 2 scores
Boys Girls
Count 50 41
Mean 2.55 3.25 2.865385
S.D. 1.6 1.9
Variance 2.56 3.61 d
d.f 49 40
X_bar - grand
mean square 0.099467 0.147929

SS
Between Group 11.03846
Within Group 269.84
Total 280.8785
Variance 3.120872
S.D. 1.766599 a.

b. Ho S.D. = 2
Ha S.D. < 2

test statist 70.21962


p-value 6.08%

At 5 % Ho is not rejected so not sufficient evidence to conclude that standard deviation is less than 2 hrs

Ho rejection criteria CV < 69.12603


S^2 < 3.072268

c. P(S^2 <3.072268 | s.d. = 1.75)


P(chi^2 < ) 90.28706
52.83%
C.V. Upper 56.94585

C.V. Lower 25.79888

U.L. 2.365828
L.L. 1.592401

dard deviation is less than 2 hrs


Assistant Professor Salaries Variance 21.32
S.D. 4.6173585522
d.f. 49

C.I. 92%
Lower Chi-SQ 33.119239914
Upper Chi-SQ 67.627074197

Lower Estimate 3.9303510372


Upper estimate 5.616315022

c.
Ho: S.D. of salaries = 5
Ha: S.D. of salaries != 5

Test Statistic 41.7872


P-VALUE 48.42%

Ho not rejected

d.
Ho: mu_full_prof - mu_assoc_prof <= 20
Ha: mu_full_prof - mu_assoc_prof > 20

Full Associate
X_bar 73.91 51.43
Variance 103.29 32.5
2.0658 0.65

Ho: Variance of Full = Variance of associate test statist 3.1781538462


Ha: Variance of full != Variance of associate p-value 0.00876%

So variance not equal.

S.E. X_bar_full - X_bar_assoc_prof 1.6646995194


test statistic 1.4897583445
p-value 6.81% 6.93%
z-approach t-approach d.f. 133.0742 133

Reject Ho at 7% significance
Category Count Sum Variance df Mean Difference from grand mean
Dry fruit 6 870 362 5 145 212.3265
Ghee 8 1318 908 7 164.75 26.8176
Khova 7 1163 243 6 166.1429 43.18367
Grand mean 159.5714

SS df MS f-test stat p-value


Between Group 1790.78571 2 895.3929 1.674675 21.53%
Within Group 9624 18 534.6667

Not reject Ho at 10%


Home Away
Mean 2.3 3.5
S.D 0.4 0.707107
Variance 0.16 0.5

For a random match odd is given by 0.5 H + O.5 A (M)

M random variable
Mean 2.9
Variance 0.165

P(odds less than 2) 1.34%

c
Ho: p_win_home = p_win_away
Ha: p_win_home != p_win_away

p_win_home 0.631579
p_win_away 0.578947

Assuming Ho to be true , p pooled is given by


p_pooled 0.605263 Ho is not rejected, that is same performance

S.E. p_win_home - p_win_away 0.158586

test statistic 0.331881


p-value 74%
d.

Goals 0 1 2 3 4 1.789474
Frequency 3 14 11 8 2 38
Difference from mean 3.202216066 0.623269 0.044321 1.465374 4.886427 10.22161

Variance 0.27626

Ho: mean = 1.35


Ha: mean != 1.35

test-stat 5.154255615
p-value 0.000025%
so Ho is rejected
Acceptance condition

C.V. > -2.326348


(P-0.1)/S.E. (P) > -2.326348

P> 0.1 + S.E.(P=0.1) *(-2.32635)

P type II error

(P - 0.05)/S.E. (P=0.05) 1.880794


P = 0.05 + 1.880794 * S.E.(P=0.05)

Solving both
0.05 = 1.107814 root(n)
n= 490.9006 ~491
If the application is truly random the distribution of digits should be distributed uniformly so Zoobi can use application 1000 ti
The expected frequency for each digit is 100 so we can do Chi-Square test of goodness of fit to see if uniform distribution fits t
obi can use application 1000 times and record observed frequencies for each digit.
ee if uniform distribution fits the observed values significantly.
Italian Seafood Steakhouse
12 16 24
13 18 19
15 17 23
17 26 25
18 23 21
20 15 22
17 19 27
24 18 31
Mean 17 19 24 20
Variance 14.85714 13.71429 14
Squared di 9 1 16
Count 8 8 8
df 7 7 7

SS df MS test stat P-value


Between 208 2 104 7.328859 0.385%
Within 298 21 14.19048

Ho is rejected

You might also like