# Liner regression interpretation

#### amandeepsharma89

##### New Member
Hello Seniors,

In my regression analysis I want to find, how “% change” is affected by other variables, the day of the month (Sunday, Monday etc.) and the occurrence number of that that day in that particular month (first occurrence of Sunday=1, second occurrence=2 so on and so forth for other days too). Please note and not confuse yourself by thinking the number as the week number in which the particular days is in (Sunday of week one, Sunday of week two and so on).

I am in a fix and am really confused. I am running regression for the attached data in excel. As you will see in the sheet "%change&day" var2 has no values similarly the case for the other sheets. Can someone explain why is that happening?

Also, I ran the regression in Stata and one of my friends mentioned that it is considering one of the days as a base case. What is that? How to interpret the result using base case?

Below is the result of regression in stata:

1) Considering tuesday and occr4 as base case

. reg change mon wed thurs fri occ1 occ2 occ3 occ5

Source | SS df MS Number of obs = 108
-------------+------------------------------ F( 8, 99) = 2.48
Model | .001364278 8 .000170535 Prob > F = 0.0171
Residual | .006814135 99 .00006883 R-squared = 0.1668
Total | .008178412 107 .000076434 Root MSE = .0083

------------------------------------------------------------------------------
change | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
mon | .0016258 .0025603 0.64 0.527 -.0034544 .0067061
wed | .0014551 .0025345 0.57 0.567 -.0035739 .0064842
thurs | .0005811 .0025345 0.23 0.819 -.0044479 .0056101
fri | .0071553 .0025345 2.82 0.006 .0021263 .0121843
occ1 | .0045453 .0023466 1.94 0.056 -.0001108 .0092014
occ2 | .0053931 .0023466 2.30 0.024 .000737 .0100492
occ3 | .0010458 .0023466 0.45 0.657 -.0036103 .0057019
occ5 | .0065914 .003379 1.95 0.054 -.0001132 .0132961
_cons | -.0051836 .002316 -2.24 0.027 -.009779 -.0005882
------------------------------------------------------------------------------

2)considering Friday as base case

. reg change mon tue wed thu

Source | SS df MS Number of obs = 108
-------------+------------------------------ F( 4, 103) = 2.56
Model | .000738564 4 .000184641 Prob > F = 0.0432
Residual | .007439849 103 .000072232 R-squared = 0.0903
Total | .008178412 107 .000076434 Root MSE = .0085

------------------------------------------------------------------------------
change | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
mon | -.0056959 .0025928 -2.20 0.030 -.0108382 -.0005536
tue | -.0073217 .0025928 -2.82 0.006 -.012464 -.0021794
wed | -.0057001 .0025625 -2.22 0.028 -.0107823 -.000618
thurs | -.0065742 .0025625 -2.57 0.012 -.0116563 -.001492
_cons | .0050673 .001812 2.80 0.006 .0014737 .0086609
------------------------------------------------------------------------------

3)Considering Tuesday as base case

. reg change mon wed thu fri

Source | SS df MS Number of obs = 108
-------------+------------------------------ F( 4, 103) = 2.56
Model | .000738564 4 .000184641 Prob > F = 0.0432
Residual | .007439849 103 .000072232 R-squared = 0.0903
Total | .008178412 107 .000076434 Root MSE = .0085

------------------------------------------------------------------------------
change | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
mon | .0016258 .0026228 0.62 0.537 -.0035759 .0068276
wed | .0016216 .0025928 0.63 0.533 -.0035207 .0067639
thurs | .0007476 .0025928 0.29 0.774 -.0043947 .0058899
fri | .0073217 .0025928 2.82 0.006 .0021794 .012464
_cons | -.0022545 .0018546 -1.22 0.227 -.0059327 .0014237
------------------------------------------------------------------------------

Please help me out in this I cannot move forward with this. I have many similar analysis to do.
Waiting for replies.

Amandeep