Sampling And Sampling Distributions Flashcards
What is bias in statistics?
The tendency of a sample statistic to systematically overestimate or underestimate a population parameter.
What is the common cause for bias in a sample?
Samples that are not being reflective of the population
What is selection bias?
When certain groups in the population are over represented in the sample. For example if a car manufacturer only asks for advise in vintage car dealerships and gets all kinds of niche ideas
What is nonresponse bias?
A systematic difference between those who are likely to respond, and those who are unlikely to respond
What is social desirability bias?
When there is a systematic difference between the socially acceptable choice, and the ultimate choice that the population actually choose
What is stratified random sampling?
When the population first is divided into mutually exclusive and exhaustive groups called strata that are proportionally repersented in the sample.
What is cluster sampling
When the population is divided into groups and than some groups are randomly selected to be included in a sample. For example if researching grades you could say a school is a group that could be used as a same of schools in general.
When should stratified random sampling be used vs cluster sampling
Stratified is better for accuracy while cluster is cheaper
What is the difference between a parameter and a statistic?
A parameter is a constant that is unknown while a statistic is a random variable whose value depends on the sample choosen
What are some other words for the sample mean
The estimator or the point estimator, a particular value of the estimator is called an estimate
When is a sample mean an unbiased estimator
When its expected average equals that of the population mean
What is the standard error of the sample mean
The standard deviation if the sample which equals the population standard deviation divided by the square root of the sample size for some reason
Does a sample inherit normal distribution from the population?
Yes
What is the central limit theorem
That any sample that numbers over 30 observations approaches normal distribution among the sample means even if the underlying population is not normally distributed
Is the sample proportion an unbiased estimator of the population proportion
Yes
Does the central limit theorem also apply to proportion
Yes, if np is larger than 5
When should you use a finite population correction factor
When the sample is at least 5% of the population the sample means variance from the population mean must be reduced
If the correction factor is close to one when adjusting the sample mean variance from the population what foes that mean
That the sample is close to the size of the population
Is a finite population correction factor also applicable for the proportions of outcomes
Yes
What is the statistical quality control
Statistical techniques used to develop and maintain a firms ability to produce high-quality goods and services
What is acceptance sampling in statistical quality control.
To gather a sample of finished products and inspect them for defects
What is the detection approach to statistical quality control.
To inspect the production process to find out where faults are caused
What is chance variation in statistical quality control
When variation occurs randomly in the production process out of the control of employee and machine
What is assignable variation in statistical quality control
Variations that are caused by events that can be identified and eliminated
What are the characteristics of a statistical control chart?
It measures a stat in relation to the center line which is its expected value and it also includes an upper and lower control limit normally three standard deviations from the center line
When is the production procedure out of control when using a control chart
When the expected value is outside the control limits indicating that things need to be adjusted
What is a sign of the sample estimates veering out of control in a control chart
When they are not randomly spread around the center line but trends towards the upper or lower limit
When is an estimator considered efficient
When it does not vary so much between samples
What does the property of consistency mean in the context of estimators
That the variance of the sample mean decrease with the size of the sample as it follows the law of large numbers in probability
