Académique Documents
Professionnel Documents
Culture Documents
1
(i)
(ii)
Positive
Yes.
Positive: High income, can buy more goods
Negative: base on fatheduc, most family have high education and know the danger of smoking, so high
income family with high education tend not to smoke
CIGS
1.000000
-0.173045
CIGS
FAMINC
(iii)
FAMINC
-0.173045
1.000000
cigs
Dependent Variable: BWGHT
Method: Least Squares
Date: 12/20/14 Time: 16:35
Sample: 1 1388
Included observations: 1388
Variable
Coefficient
Std. Error
t-Statistic
Prob.
C
CIGS
119.7719
-0.513772
0.572341
0.090491
209.2668
-5.677609
0.0000
0.0000
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.022729
0.022024
20.12858
561551.3
-6135.457
32.23524
0.000000
118.6996
20.35396
8.843598
8.851142
8.846420
1.924390
faminc
Dependent Variable: BWGHT
Method: Least Squares
Date: 12/20/14 Time: 16:37
Sample: 1 1388
Included observations: 1388
Variable
Coefficient
Std. Error
t-Statistic
Prob.
C
CIGS
FAMINC
116.9741
-0.463408
0.092765
1.048984
0.091577
0.029188
111.5118
-5.060315
3.178195
0.0000
0.0000
0.0015
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
C3.2
0.029805
0.028404
20.06282
557485.5
-6130.414
21.27392
0.000000
118.6996
20.35396
8.837772
8.849089
8.842005
1.921690
(i)
Coefficient
Std. Error
t-Statistic
Prob.
C
SQRFT
BDRMS
-19.31500
0.128436
15.19819
31.04662
0.013824
9.483517
-0.622129
9.290506
1.602590
0.5355
0.0000
0.1127
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
(ii)
(iii)
(iv)
(v)
(vi)
C3.3
0.631918
0.623258
63.04484
337845.4
-487.9989
72.96353
0.000000
$15.198,19
$ 33,17923
R2= 63%
354.600
Estimate price = 354.600
Since actual =300.000
Then
=300.000-354.600=-54.600 (underpaid)
293.5460
102.7134
11.15907
11.24352
11.19309
1.858074
(i)
Coefficient
Std. Error
t-Statistic
Prob.
C
LSALES
LMKTVAL
4.620918
0.162128
0.106708
0.254408
0.039670
0.050124
18.16339
4.086899
2.128880
0.0000
0.0001
0.0347
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
(ii)
0.299114
0.291057
0.510294
45.30966
-130.5594
37.12852
0.000000
6.582848
0.606059
1.509146
1.562979
1.530979
2.092115
Coefficient
Std. Error
t-Statistic
Prob.
C
LSALES
LMKTVAL
PROFITS
4.686924
0.161368
0.097529
3.57E-05
0.379729
0.039910
0.063689
0.000152
12.34280
4.043299
1.531333
0.234668
0.0000
0.0001
0.1275
0.8147
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.299337
0.287186
0.511686
45.29524
-130.5312
24.63628
0.000000
6.582848
0.606059
1.520127
1.591904
1.549237
2.096546
The R2 is almost the same, including variable profits only gives small influence to the model.
70% of variation in log salary is unexplained.
(iii)
C3.4
(i)
Descriptive stat
ATNDRTE
81.70956
87.50000
100.0000
6.250000
17.04699
-1.578799
5.693665
PRIGPA
2.586775
2.560000
3.930000
0.857000
0.544714
0.161246
2.760582
ACT
22.51029
22.00000
32.00000
13.00000
3.490768
0.075404
2.645701
Jarque-Bera
Probability
488.0774
0.000000
4.570791
0.101734
4.200994
0.122396
Sum
Sum Sq. Dev.
55562.50
197317.3
1759.007
201.4684
15307.00
8273.928
680
680
Mean
Median
Maximum
Minimum
Std. Dev.
Skewness
Kurtosis
(ii)
Observations
680
Estimate the model
Atndrte = 75,70 + 17,261 prigpa 1,717 act
The intercept of 75.70 is the predicted percent of classes attended for a student with 0
cumulative GPA prior to the current term and an ACT score of 0. I would not call this particular
meaning useful. The intercept is useful, but its interpretation is not.
Dependent Variable: ATNDRTE
Method: Least Squares
Date: 12/20/14 Time: 20:09
Sample: 1 680
Included observations: 680
Variable
Coefficient
Std. Error
t-Statistic
Prob.
C
PRIGPA
ACT
75.70041
17.26059
-1.716553
3.884108
1.083103
0.169012
19.48978
15.93624
-10.15640
0.0000
0.0000
0.0000
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
(iii)
(iv)
(v)
C3.5
0.290581
0.288486
14.37936
139980.6
-2776.115
138.6513
0.000000
81.70956
17.04699
8.173867
8.193817
8.181589
2.010991
Additional point for GPA will increase the class attendance. However, additional score for ACT
test will decrease the class attendance. Unexpected result. Perhaps gaining high score means
that student thinks they do not have the necessity to attend the class
104,36
would seem to be a very good student. But no student attends more than 100% of classes!
(observation number 569). The model provides residual
The difference in predicted attendance between Student A and Student B is 93.09 - 67.23=
25.86%
Coefficient
Std. Error
t-Statistic
Prob.
C
EDUC
EXPER
TENURE
0.284360
0.092029
0.004121
0.022067
0.104190
0.007330
0.001723
0.003094
2.729230
12.55525
2.391437
7.133071
0.0066
0.0000
0.0171
0.0000
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.316013
0.312082
0.440862
101.4556
-313.5478
80.39092
0.000000
1.623268
0.531538
1.207406
1.239842
1.220106
1.768805
Coefficient
Std. Error
t-Statistic
Prob.
C
EXPER
TENURE
13.57496
-0.073785
0.047680
0.184324
0.009761
0.018337
73.64710
-7.559282
2.600162
0.0000
0.0000
0.0096
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.101342
0.097906
2.629980
3617.483
-1253.487
29.48955
0.000000
12.56274
2.769022
4.777517
4.801843
4.787042
1.869826
C3.6
(i)
EDUC
3.533829
0.192210
18.38530
0.0000
EDUC
0.059839
0.005963
10.03492
0.0000
EDUC
IQ
0.039120
0.005863
0.006838
0.000998
5.720784
5.875413
0.0000
0.0000
(ii)
(iii)
(iv)
C3.7
(i)
Dependent Variable: MATH10
Method: Least Squares
Date: 12/20/14 Time: 21:16
Sample: 1 408
Included observations: 408
Variable
Coefficient
Std. Error
t-Statistic
Prob.
C
LEXPEND
LNCHPRG
-20.36076
6.229691
-0.304585
25.07287
2.972634
0.035357
-0.812063
2.095680
-8.614468
0.4172
0.0367
0.0000
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.179927
0.175877
9.526228
36753.36
-1497.073
44.42926
0.000000
24.10686
10.49361
7.353301
7.382795
7.364972
1.902822
No. for lexpend cannot set to 0 because log 0 = undefined. At least $1 for lexpend. For lnchprg
we can set it to 0
Math10 with lexpend
Coefficient
Std. Error
t-Statistic
Prob.
C
LEXPEND
-69.34108
11.16439
26.53013
3.169011
-2.613673
3.522990
0.0093
0.0005
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.029663
0.027273
10.34953
43487.76
-1531.396
12.41146
0.000475
24.10686
10.49361
7.516649
7.536312
7.524429
1.614623
The magnitude of the slope coefficient has gotten larger. It was previously 6.23 and is now
11.16. This speaks to a negative correlation between log(expend) and lnchprg.
(iv)
LEXPEND
LNCHPRG
LEXPEND
1.000000
-0.192704
LNCHPRG
-0.192704
1.000000
C3.8
(i)
descriptive stat
PRPBLCK
0.113486
0.041444
0.981658
0.000000
0.182416
2.700012
10.56841
INCOME
47053.78
46272.00
136529.0
15919.00
13179.29
0.962831
7.551386
Jarque-Bera
Probability
1473.100
0.000000
416.2135
0.000000
Sum
Sum Sq. Dev.
46.41594
13.57651
19244998
7.09E+10
Observations
409
409
Mean
Median
Maximum
Minimum
Std. Dev.
Skewness
Kurtosis
prpblck = percentage
income = dollar
(ii)
Psoda = 0,956 + 0,115 prpblck + 1,6*10-6
Coefficient
Std. Error
t-Statistic
Prob.
C
PRPBLCK
INCOME
0.956320
0.114988
1.60E-06
0.018992
0.026001
3.62E-07
50.35379
4.422515
4.430130
0.0000
0.0000
0.0000
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.064220
0.059518
0.086115
2.951465
415.7934
13.65691
0.000002
1.044863
0.088798
-2.058820
-2.028940
-2.046988
1.696180
The coefficient on prpblck is 0.1149882. The literal interpretation would be: when prpblck
increases by 1, the price of a medium soda increases by 11 cents. The only problem is, the
notion of increasing prpblck by 1 is not very meaningful. prpblck is the proportion of individuals
in a zip code who are black cannot increase by 1 unless the proportion of individuals in a zip
code starts out as 0. That is, the only zip code that can increase by 1 is a zip code that starts
out with no individuals who are black, and then becomes a zip code that is made up only of
individuals who are black. This is not a very useful marginal effect. In order to interpret the
marginal effect more usefully, look at smaller (more realistically-sized) changes. For instance,
an increase of 0.01 (an increase of 1 in the percentage of individuals who are black in a zip
code) is predicted to increase the price of a medium soda by 0.1149882 0.01 = 0.00114988,
C4.1
(i)
(ii)
(iii)
As expenditure of candidate A increases for 1%, percentage of vote for candidate A will
increase for B1/100
H0: B1=-B2 or H0: B1+B2=0
1% increases expendA and 1% increases expendB leaves voteA unchanged
Estimate model
voteA = 45,079 + 6,083 lexpendA 6,615 lexpendB + 0,152 prtystrA
Coefficient
Std. Error
t-Statistic
Prob.
C
LEXPENDA
LEXPENDB
PRTYSTRA
45.07893
6.083316
-6.615417
0.151957
3.926305
0.382150
0.378820
0.062018
11.48126
15.91866
-17.46321
2.450210
0.0000
0.0000
0.0000
0.0153
R-squared
Adjusted R-squared
S.E. of regression
Sum squared resid
Log likelihood
F-statistic
Prob(F-statistic)
0.792557
0.788874
7.712335
10052.14
-596.8609
215.2266
0.000000
50.50289
16.78476
6.946369
7.019277
6.975948
1.604129
Yes, 1% increases on expend A will probably increase vote for A. 1% increases on expend B
will decrease vote for A.
(iv)
t-test
tB1-B2=(6,083-(-6,615)) / (0,382-0,379)