# Calcalating a confidence interval in excel

• Feb 23rd 2009, 10:23 AM
Smf16
Calcalating a confidence interval in excel
I'm not sure if I am posting this in the correct place but...I really need some help..I need to calculate a confidence interval in excel for this set of data. I am not sure how to do this in excel ?This is for my statistic class and basically we (my teammates) are trying to prove the hypothesis that "Older workers typically make more than younger workers"...So with this data set of 30 samples I have to figure the confidence interval..?? I am so lost in this class and I am terrible with Math...if anybody can please help I would greatly appreciate it...TIA

WageIndustryOccupationEducationExperienceAge\$11,18 6.00 0012018\$20,852.00 0012119\$10,997.00 0414020\$13,787.00 0411421\$19,452.00 0413322\$39,888.00 0312523\$20,793.00 0012624\$16,789.00 0313625\$11,451.00 1012826\$29,191.00 0012927\$24,509.00 05141535\$33,498.00 01102036\$29,390.00 00131837\$33,411.00 12122038\$22,485.00 03122240\$83,601.00 05171841\$33,389.00 01142242\$31,799.00 03122543\$66,738.00 0092944\$9,879.00 03122846\$46,646.00 2054455\$32,235.00 03123856\$50,171.00 05123957\$36,178.00 03124058\$15,160.00 0484559\$12,285.00 01124260\$45,976.00 02124361\$18,752.00 04114562\$17,626.00 03124563\$19,981.00 0445464
• Feb 23rd 2009, 03:13 PM
awkward
Quote:

Originally Posted by Smf16
I'm not sure if I am posting this in the correct place but...I really need some help..I need to calculate a confidence interval in excel for this set of data. I am not sure how to do this in excel ?This is for my statistic class and basically we (my teammates) are trying to prove the hypothesis that "Older workers typically make more than younger workers"...So with this data set of 30 samples I have to figure the confidence interval..?? I am so lost in this class and I am terrible with Math...if anybody can please help I would greatly appreciate it...TIA

WageIndustryOccupationEducationExperienceAge\$11,18 6.00 0012018\$20,852.00 0012119\$10,997.00 0414020\$13,787.00 0411421\$19,452.00 0413322\$39,888.00 0312523\$20,793.00 0012624\$16,789.00 0313625\$11,451.00 1012826\$29,191.00 0012927\$24,509.00 05141535\$33,498.00 01102036\$29,390.00 00131837\$33,411.00 12122038\$22,485.00 03122240\$83,601.00 05171841\$33,389.00 01142242\$31,799.00 03122543\$66,738.00 0092944\$9,879.00 03122846\$46,646.00 2054455\$32,235.00 03123856\$50,171.00 05123957\$36,178.00 03124058\$15,160.00 0484559\$12,285.00 01124260\$45,976.00 02124361\$18,752.00 04114562\$17,626.00 03124563\$19,981.00 0445464

Hi Smf16,

You can use the Excel worksheet functions AVERAGE and STD to find the sample average and standard deviation, then use the function CONFIDENCE to find the width of a confidence interval. You can read about these functions in Excel's on-line help.

This is assuming that you want to find a confidence interval on the mean. But it may be, given your problem statement ("Older workers typically make more than younger workers"), that what you really want is a test of hypothesis. Have you thought about this?
• Feb 23rd 2009, 07:08 PM
Smf16
Yes, I have been tinkering with Excel and managed to figure out how to use these functions. I am just not sure I am getting the correct calculations. So do you think I should be looking to calculate the mean and confidence intervals for the wages and ages rows of my data to test my hypothesis? This is what I have done so far. I am sorry if I am asking stupid questions..I am just terrible with Math...and Excel! I need a Statistics for Dummies book on this stuff...(Doh)

• Feb 24th 2009, 04:41 PM
awkward
OK, let's see if I understand your problem. You have several rows of data, with column headings Wage, Industry, Occupation, Education, Experience, Age. You want to know if older workers earn more than younger workers. Is that correct?

How much statistics have you studied? If all you know is how to find a confidence interval, then you will need to make a decision as to which ages are "younger" and which are "older". Find confidence intervals on the mean for the two groups and see if the intervals overlap. This is not the best way to proceed, though-- you should do at least a test of hypothesis if you know how, especially given that you want to know if older workers earn more.

Even better, you may have enough data to conduct an analysis of variance or multilinear regression. This would give you a way to account for the other factors: industry, occupation, experience. But that takes more statistical know-how.