Statistical Significance Testing Why do it When to

Statistical Significance Testing Why do it? When to do it? How to it?

Testing is Important Red shading is not statistically significant

Statements you might want to make • Estimate X is bigger than Y • Estimate X this year is larger than X last year • Estimate X is smaller than Census 2000 value • State A has the highest Value

Comparing SF 3 or CTPP 2000 to current ACS o d s ’ t e L a test

How do I do a significance test? 1. Get the Margin of Error (MOE) from ACS 2. Calculate the Standard Error (SE) [SE = MOE / 1. 645] 3. Solve for Z where A and B are the two estimates 4. If Z < -1. 645 or Z > 1. 645 Difference is Significant at 90% confidence

Obtaining Standard Error from MOE is Key • • • Sum or Difference of Estimates Proportions and Percents Means and Other Ratios There are different formulas Where…. Consult Appendix 3 in the “Compass for Understanding and Using ACS Data: What General Data Users Need to Know” Report Series. JUST CLICK HERE http: //www. census. gov/acs/www/Downloads/ACSGeneral. Handbook. pdf

However HELP is Here PUSH BUTTON SIGNIFICANCE TESTER trbcensus. com/notes/Statistical. Calculations. Menu. xls

But what if I am using 2000 non-ACS Data? ic h p ra G k w c i vie Cl re d r 8 n e a t ap Ch where do I get my SEs?

You will need 2 things the Standard Error and Survey Design Factor X N = Size of publication area (population) Y = Estimate of characteristic Survey Design Factor

Survey Design Factor Mode to Work Get Survey Design Factors from the Census 2000 SF 3 Technical Documentation, Chapter 8 Table C. 1. 4 1. 2 0. 9 0. 7 http: //www. census. gov/prod/cen 2000/doc/tablec-fl. pdf Insert state abbreviation for specific state

Solve for the unadjusted Standard Error (SE) 5 Y = 5* 126, 540 632, 700 N = Size of publication area (population = 362, 563 ) Y = Estimate of characteristic 1 - (Y/N) = 126, 540 / 362, 563 1 - 0. 3490152 0. 6509848 SE = 641. 7772

Adjust the SE by the Survey Design Factor X SE = 641. 777 Survey Design Factor 126, 540 / 362, 563 = 35% 0. 7 = Final Adjusted SE = 449 Survey Design Factor at 35%see slide 10

Populate the adjusted SEs in your worksheet for 2000

Calculate the ACS SE from the MOE Remember at 90% Significance Standard Error equals the MOE / 1. 645

Calculate Z and test is Z < -1. 645 or Z > 1. 645? A B

is Z < -1. 645 or Z > 1. 645? g n i pt m Te Green is Significant This is NOT

Try to do an exercise on your own?