Term
|
Definition
-values that are computed from information provided by a sample
-used to estimate the parameter
-S tatistic and S ample |
|
|
Term
|
Definition
-values that are computed from a complete census which are considered to be valid measures of the population
-represent "what we wish to know" about a population
-P arameter and P opulation |
|
|
Term
|
Definition
-form of logic in which you make a general statement about an entire class based on what you have observed about a small set of members of that class
-draw a conclusion from a small amount of evidence |
|
|
Term
|
Definition
-set of procedures in which the sample size and sample statistic are used to make estimates of the corresponding population parameter
-inferring based on statistics |
|
|
Term
type of statistical inference
parameter estimation |
|
Definition
-estimate the population value (parameter) through the use of confidence intervals
-the process of using sample information to compute an interval that describes the range of values of a parameter
- no hypothesis is inovlved
- taking the data and trying to estimate an interval
-Ex: the percent of PC users who listen to musicl online is 30% ± 10%, or from 20-40%
|
|
|
Term
type of statistical inference
hypothesis test |
|
Definition
-compare the sample statistic with what is believed (hypothesized) to be the population value prior to undertaking the study
-compare the sample statistic with what is believed
-test your prediction (supported/not supported)
-Ex: online music listeners listen to an avg of 45 ± 15 mins per day, not 90 as blieved by RealPlayer managers |
|
|
Term
parameter estimation
sample statistic |
|
Definition
-usually the mean or percentage generated from sample data
-used to estimate population parameters
-Categorical scale
If you do a count and say 50% of the class is female
-Metric scale
If you have a sample and am calculating the mean |
|
|
Term
parameter estimation
standard error |
|
Definition
-variance divded by sample size
-formula for standard error of the mean and another formula for standard error of the percentage
-SE is a measure of how much rabdom variation we would expect from samples of equal size drawn from the same population
-measure of the variablility in a sampling distribution
-Given the sample size, the more variability, the greater the SE
-the lower the SE, the more precisely our sample stat will represent the population parameter, closer we are to the truth |
|
|
Term
parameter estimation
standard error of the mean |
|
Definition
sx = s ÷ √n
sx = SE of the mean
s = SD
n = sample size |
|
|
Term
parameter estimation
standard error of the perecentage
|
|
Definition
sp = √(p × q) ÷ n
sp = SE of the percentage
p= sample percentage
q= (100-p)
n= sample size |
|
|
Term
parameter estimation
confidence interval |
|
Definition
-gives us a range within which a sample statistic will fall if we were to reapeat the study many times over
-population parameters are estimated with the use of CI
-the degree of accuracy desired by the researcher and stipulated as a level of confidence in the form of a %
-the range of your estimate of the pop mean/% depends largely on teh sample size and the variability found in the sample
a
Mean: x ± z (sx)
%: p ± z (sp)
|
|
|
