## Excel Example Problem

The data below show the refusal rates in mortgage lending by 20 banks in major cities. The data are categorized for high income minority and high income white applicants.

Data are from Association of Community Organizations for Reform Now (ACORN), Banking on Discrimination: Executive Summary, October, 1991, in Joint Hearings Before the Committee on Banking, Finance, and Urban Affairs, House of Representatives, 102nd Congress, 2nd Session, Serial 102-120, May 7 and May 14, 1992, pp 236-246.

Use Excel to calculate the mean, standard deviation, and standard error for each of the following data sets.

Using either confidence intervals or significance tests (or both), report whether there is a significant difference between refusal rates of minority and white applicants. You should look at this in two ways. First, assuming that these are the only banks that people go to, is there a significant difference in what a minority person can expect as opposed to a white person? Second, taking these banks as a random sample of all banks (a very questionable assumption), is there evidence that metropolitan banks in the U.S. systematically treat minorities and whites differently? (Make sure you understand the difference between these two questions, both from a statistical standpoint and from the perspective of race relations. For additional information about these issues, see www.hud.gov/offices/fheo/lending/fairlend.cfm and www.clev.frb.org/research/com/081596.htm.)

These data are available as an Excel file.

After working on it, you may view the answer.

BANK MINORITY WHITE
HARRIS TRUST 21.4 2.2
NCNB TEXAS 8 8
CRESTAR 11.3 3.6
MERCANTILE 17.3 5.5
FIRST NB COMMERCE 38 7.6
TEXAS COMMERCE 33.3 10.3
COMERICA 33.6 9.4
FIRST OF AMERICA 29.5 7.3
BOATMAN'S NAT'L 21.7 7.4
1ST COMM'L 39.1 15.8
PROVIDENT NAT'L 36.6 15.3
WORTHEN 28.6 10.1
HIBERNIA NAT'L 32.9 9.2
SOVRON 21 13
BELL FEDERAL 5.8 4.2
SEC PAC AZ 24.2 14.1
CORE STATES 38.3 15
CITIBANK AZ 27.3 16.1
MF'ERS HANOVER 41.3 25.1
CHEMICAL 41.1 26.8