presentation 4
DESCRIPTION
Presentation 4. Mingwei Lei Econ 201. Last Time…. Examined the relationship between corrcoef ( stock returns and market returns) vs. market returns Used different sampling frequencies to try to find the optimum Linear regression was done in Matlab. This Time…. - PowerPoint PPT PresentationTRANSCRIPT
MINGWEI LEIECON 201
Presentation 4
Last Time…
Examined the relationship between corrcoef (stock returns and market returns) vs. market returns
Used different sampling frequencies to try to find the optimum
Linear regression was done in Matlab
This Time….
Examine the relationship between corrcoef (different stocks’ returns) vs. market returns
Examine the relationship between corrcoef (stock returns and market returns) vs. market realized variance
Uses 11 minute sampling frequency through out
Linear regressions were done in Stata
KO and HPQ Corr vs Market Return (Period- 1 days)
_cons .0713452 .0039031 18.28 0.000 .0636919 .0789985 mktrtn .152157 1.065594 0.14 0.886 -1.937292 2.241607 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .20456 R-squared = 0.0000 Prob > F = 0.8865 F( 1, 2739) = 0.02Linear regression Number of obs = 2741
-.5
0.5
1
-.04 -.02 0 .02 .04MktRtn
Corr Fitted values
KO and HPQ Corr vs Market Return (Period- 5 days)
-.4
-.2
0.2
.4
-.06 -.04 -.02 0 .02 .04MktRtn
Corr Fitted values
_cons .0735542 .0047706 15.42 0.000 .0641833 .0829252 mktrtn -.5438411 .5146737 -1.06 0.291 -1.554824 .4671419 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .11106 R-squared = 0.0018 Prob > F = 0.2911 F( 1, 546) = 1.12Linear regression Number of obs = 548
KO and HPQ Corr vs Market Return (Period- 20 days)
-.1
0.1
.2.3
.4
-.1 -.05 0 .05 .1MktRtn
Corr Fitted values
_cons .0728627 .0066908 10.89 0.000 .0596303 .0860951 mktrtn -.7354039 .3819269 -1.93 0.056 -1.490738 .0199301 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .07878 R-squared = 0.0302 Prob > F = 0.0563 F( 1, 135) = 3.71Linear regression Number of obs = 137
JPM and MS Corr vs Market Return (Period- 1 days)
-.5
0.5
1
-.04 -.02 0 .02 .04MktRtn
Corr Fitted values
_cons .431377 .0084205 51.23 0.000 .4148461 .4479079 mktrtn -1.06494 1.988484 -0.54 0.592 -4.968682 2.838801 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .2286 R-squared = 0.0004 Prob > F = 0.5924 F( 1, 740) = 0.29Linear regression Number of obs = 742
JPM and MS Corr vs Market Return (Period- 5 days)
.2.4
.6.8
-.06 -.04 -.02 0 .02MktRtn
Corr Fitted values
_cons .4346792 .0128499 33.83 0.000 .4092833 .4600751 mktrtn -1.330725 1.332352 -1.00 0.320 -3.963914 1.302464 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .1556 R-squared = 0.0061 Prob > F = 0.3196 F( 1, 146) = 1.00Linear regression Number of obs = 148
JPM and MS Corr vs Market Return (Period- 20 days)
_cons .4364003 .0218035 20.02 0.000 .3921369 .4806638 mktrtn .3309181 .8968651 0.37 0.714 -1.489815 2.151651 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .12892 R-squared = 0.0024 Prob > F = 0.7144 F( 1, 35) = 0.14Linear regression Number of obs = 37
.2.3
.4.5
.6.7
-.06 -.04 -.02 0 .02MktRtn
Corr Fitted values
VZ Correlation vs Market RV (Period- 1 days)
-1-.
50
.51
0 5.00e-06 .00001 .000015 .00002MktRV
Corr Fitted values
_cons .0533568 .00503 10.61 0.000 .0434926 .063221 mktrv 32642.51 7070.829 4.62 0.000 18776.01 46509.02 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .2067 R-squared = 0.0138 Prob > F = 0.0000 F( 1, 2115) = 21.31Linear regression Number of obs = 2117
VZ Correlation vs Market RV (Period- 5 days)
-.2
0.2
.4.6
0 2.00e-06 4.00e-06 6.00e-06MktRV
Corr Fitted values
_cons .0533689 .006308 8.46 0.000 .0409698 .065768 mktrv 44834.13 11501.41 3.90 0.000 22226.78 67441.48 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .11213 R-squared = 0.0557 Prob > F = 0.0001 F( 1, 421) = 15.20Linear regression Number of obs = 423
VZ Correlation vs Market RV (Period- 20 days)
_cons .0512171 .0082119 6.24 0.000 .0349307 .0675034 mktrv 55707.53 18639.73 2.99 0.004 18740.03 92675.03 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .07475 R-squared = 0.1340 Prob > F = 0.0035 F( 1, 103) = 8.93Linear regression Number of obs = 105
HPQ Correlation vs Market RV (Period- 1 days)
-.5
0.5
1
0 5.00e-06 .00001 .000015 .00002MktRV
Corr Fitted values
_cons .0739422 .0046535 15.89 0.000 .0648176 .0830669 mktrv 30677.8 6835.372 4.49 0.000 17274.8 44080.81 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .19659 R-squared = 0.0123 Prob > F = 0.0000 F( 1, 2740) = 20.14Linear regression Number of obs = 2742
HPQ Correlation vs Market RV (Period- 5 days)
-.2
0.2
.4
0 2.00e-06 4.00e-06 6.00e-06MktRV
Corr Fitted values
_cons .0753189 .0053645 14.04 0.000 .0647813 .0858566 mktrv 34947.96 8806.442 3.97 0.000 17649.3 52246.61 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .09633 R-squared = 0.0424 Prob > F = 0.0001 F( 1, 546) = 15.75Linear regression Number of obs = 548
HPQ Correlation vs Market RV (Period- 20 days)
-.1
0.1
.2.3
0 1.00e-06 2.00e-06 3.00e-06 4.00e-06MktRV
Corr Fitted values
_cons .073853 .0075637 9.76 0.000 .0588944 .0888117 mktrv 38965.78 15069.17 2.59 0.011 9163.596 68767.96 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .06132 R-squared = 0.1029 Prob > F = 0.0108 F( 1, 135) = 6.69Linear regression Number of obs = 137
KO Correlation vs Market RV (Period- 1 days)
-.5
0.5
1
0 5.00e-06 .00001 .000015 .00002MktRV
Corr Fitted values
_cons .0570533 .0049197 11.60 0.000 .0474067 .0667 mktrv 33763.15 7859.507 4.30 0.000 18351.99 49174.31 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .2031 R-squared = 0.0139 Prob > F = 0.0000 F( 1, 2740) = 18.45Linear regression Number of obs = 2742
KO Correlation vs Market RV (Period- 5 days)
-.2
0.2
.4
0 2.00e-06 4.00e-06 6.00e-06MktRV
Corr Fitted values
_cons .0547252 .0059221 9.24 0.000 .0430924 .066358 mktrv 43973.05 10047.88 4.38 0.000 24235.82 63710.29 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .10872 R-squared = 0.0528 Prob > F = 0.0000 F( 1, 546) = 19.15Linear regression Number of obs = 548
KO Correlation vs Market RV (Period- 20 days)
-.1
0.1
.2.3
.4
0 1.00e-06 2.00e-06 3.00e-06 4.00e-06MktRV
Corr Fitted values
_cons .0543956 .0086498 6.29 0.000 .037289 .0715022 mktrv 48677.66 17425.98 2.79 0.006 14214.44 83140.88 corr Coef. Std. Err. t P>|t| [95% Conf. Interval] Robust
Root MSE = .07585 R-squared = 0.1047 Prob > F = 0.0060 F( 1, 135) = 7.80Linear regression Number of obs = 137