RobertNiles.com
About Robert
Reporting Help
Finding Data on the Internet
Questions for Candidates
Stats Lessons
Mean
Median
Percent
Per capita
Standard Deviation
Margin of Error
Data Analysis
Sample Sizes
Stats Tests
Help Board
Bookstore


The Cartoon Guide to Statistics

This isn't some dumb-downed whitewash. It's a must-read for a beginner taking his or her first steps toward understanding stats.
More information
-->

Home > Statistics Every Writer Should Know > The Stats Board > Discusssion

Standard Errors for Sampling
Message posted by Caroline on January 25, 2001 at 12:00 AM (ET)

Could you help me please! I am learning about standard errors for sampling and the book I have isn't very well written. Could you please explain it to me in plain English? Hope you can help - cheers!


READERS RESPOND:
(In chronological order. Most recent at the bottom.)

Re: Standard Errors for Sampling
Message posted by Bill on January 30, 2001 at 12:00 AM (ET)


The standard error allows us to make probability statements about the true population mean. Assume that prior to the presidential election a pollster found that support for candidate Bush was 49% among a sample of 1000 voters in Florida. The true support for Bush in Florida, however, is not likely to be exactly 49%. To increase our confidence in our estimate for the true support of Bush we could establish confidence intervals about the 49% estimate. To do so, we use the standard error (mean +/- 1.96 standard error) and the 49% estimate to establish a 95% confidence interval. Assume that the confidence interval turned out to be 49% +/- 3% or 46% to 52%. Now we are more confident in our estimate of the true support for Bush in Florida. We can say that "There is a 95% probability that this confidence interval includes the true population mean." Another interpretation is that if we repeatedly obtained samples of 1000 from the state, 95% of the time the support for Bush would be between 46% and 52%.


Re: Standard Errors for Sampling
Message posted by CY on February 12, 2001 at 12:00 AM (ET)

Right, all you need to know are the followings:

1. Within 1 SD of the mean, there are 66% of the population
2. Within 2 SD of the mean, there are 95% of the population
3. Normal distribution would give a bell shape graph

Basically anything that does not fit into these three statements show up standard error, so just follow the rules and you will be fine.



Your $5 contribution helps cover part the $500 annual cost of keeping this site online.

Niles Online Sites:RobertNiles.comTheme Park InsiderViolinist.com

RobertNiles.com™, the site, content and services 咀opyright 1996-2002, Robert Niles.
All rights reserved. Questions? Comments? Read my Privacy Policy, or E-mail me!