Google Answers Logo
View Question
 
Q: quants / excel (2) ( Answered,   0 Comments )
Question  
Subject: quants / excel (2)
Category: Business and Money > Economics
Asked by: k9queen-ga
List Price: $25.00
Posted: 18 Nov 2003 15:44 PST
Expires: 18 Dec 2003 15:44 PST
Question ID: 277207
Run the regression and verify that the R-squared is low.  Why does
this make sense? Explain/show your work
 

Market	           "Occupancy Rate (%)"	         "Average Room Rate ($)"
=========================================================================
Los Angeles-Long Beach	67.9	                       75.91
Chicago         	72	                       92.04
Washington	        68.4	                       94.42
Atlanta	  	        67.7                           81.69
Dallas	                69.5	                       74.76
San Diego	        68.7	                       80.86
Anaheim-Santa Ana	69.5	                       70.04
San Franciso	        78.7	                       106.47
Houston	                62	                        66.11
Miami-Hialeah	        71.2	                        85.83
Oahu Island	        80.7	                        107.11
Phoenix	                71.4	                        95.34
Boston	                73.5	                        105.51
Tampa-St. Petersburg	63.4	                        67.45
Detroit	                68.7	                        64.79
Philadelphia	        70.1	                        83.56
Nashville	        67.1	                        70.12
Seattle	                73.4	                        82.6
Minneapolis-St. Paul	69.8	                        73.64
New Orleans	        70.6	                          99
	1336.4	1601.34

Clarification of Question by k9queen-ga on 18 Nov 2003 16:03 PST
Ignore the initial directions.
It should read:
a)Is this a causal relationship? If so, what is the direction of causation?  
b)Run a regression and look at r-squared; What does this tell you?
C)Should the value of r-squared depend upon which variable was made
the independent and which the dependent?
d)Explain and then switch the variables to verify the answer.

Clarification of Question by k9queen-ga on 18 Nov 2003 16:50 PST
delete the last set of numbers
1336.4 and 1601.34

Clarification of Question by k9queen-ga on 18 Nov 2003 22:30 PST
I am supposed to clarify these are studying purposes.
Answer  
Subject: Re: quants / excel (2)
Answered By: elmarto-ga on 19 Nov 2003 06:12 PST
 
Hi k9queen!
Here are the answers to your questions.

a) The direction of causation is not clear in this case, as in most
supply/demand situations. For instance, it would be possible to argue
that the direction of causation is from avg. room rate to occupancy
rate. A plausible argument would be that a higher room rate makes
tourists want to travel to somewhere cheaper, so that a higher room
rate causes a lower occupancy rate. On the other hand, it's also be
possible to argue that the direction of causation is from occupancy
rate to room rate. In this case, the idea could be: that room rates
are high *because* occupancy rate is high. Since the supply of
available rooms is small (when occupancy rate is high), one would
expect that room prices should go up. Therefore, the direction of
causation is not clear. Moreover, it's not clear wether these
variables should be positively correlated (higher occupancy rates go
in hand with higher room rates) or negatively correlated (higher
occupancy rates go in hand with lower room rates).

b,c and d) Here I ran a regression in Excel using the occupancy rate
as a dependent variable and the room rate as an independent variable.
The R-squared I got was 0.62. The R-squared is a measure that compares
the variance of the errors of the regression with the variance of the
dependent variable (Y). In this case, it's telling us that the
variance of the errors is 38% of the variance of Y, so that the
regression model accounts for the other 62% of the variance of Y.
However, this has nothing to do with causation. Therefore, since the
R-squared measure is independent of the direction of causation, it's
exactly the same if we decide that the dependent variable is the
occupancy rate or that the dependent variable is the avg. room rate.
In other words, R-squared is also another way to measure the
correlation between both variables. Recall that correlation between 2
variables has nothing to do with causation: it's possible that A
causes B, or that B causes A, or that A and B are both caused by C.
Since causation doesn't matter to R-squared, it doesn't matter wether
we consider the room rate or the occupancy rate to be the "exogenous"
variable; the R-squared will be exactly the same.

In order to verify this, I ran a regression using the room rate as the
dependent variable and the occupancy rate as the independent (or
exogenous) variable. I got that the R-squared is 0.62, exactly the
same as before.


I hope this helps! If you have any questions regarding my answer,
please don't hesitate to request a clarification before rating it.
Otherwise I await your rating and final comments.

Best wishes!
elmarto
Comments  
There are no comments at this time.

Important Disclaimer: Answers and comments provided on Google Answers are general information, and are not intended to substitute for informed professional medical, psychiatric, psychological, tax, legal, investment, accounting, or other professional advice. Google does not endorse, and expressly disclaims liability for any product, manufacturer, distributor, service or service provider mentioned or any opinion expressed in answers or comments. Please read carefully the Google Answers Terms of Service.

If you feel that you have found inappropriate content, please let us know by emailing us at answers-support@google.com with the question ID listed above. Thank you.
Search Google Answers for
Google Answers  


Google Home - Answers FAQ - Terms of Service - Privacy Policy