Hypothesis Testing
Dec 26, 2015
Central Limit Theorem
To understand the Central Limit Theoremwe must understand the difference between
three types of distributions…..
There are three types of distributions:1. Population distributions2. Sample distributions
3. Sampling distributions
2. Sample distributionsThe frequency distributions of samples.
The sample distribution should look likethe population distribution…..
Why?
2. Sample distributionsThe frequency distributions of samples.
The sampling distribution should NOT look likethe population distribution…..
Why?
Say the mean was equal to 40, if we tooka random sample from this population of a certainsize n… over and over again and calculated themean each time……
We could make a distribution of nothing butthose means. This would be a samplingdistribution of means.
2. If the population mean was 40, how manyof the sample means would be larger than 40,and how many would be less than 40?
Regardless of the shape of the distributionbelow, the sampling distribution would be symmetrical around the population mean of 40.
The means of all the samples will be closertogether (have less variance) if the variance of
the population is smaller.
The means of all the samples will be closertogether (have less variance) if the size of
each sample (n) gets larger.
So the sampling distribution will have a mean equal to the population mean, and a varianceinversely proportional to the size of the sample (n), and proportional to the variance of the population.
http://www.khanacademy.org/math/statistics/v/central-limit-theorem
http://www.khanacademy.org/math/statistics/v/sampling-distribution-of-the-sample-mean
Central Limit Theorem
If samples are large, thenthe sampling distribution created by those
samples will have a mean equal to thepopulation mean and a standard deviation
equal to the standard error.
This makes inferential statistics possiblebecause all the characteristics of a normal curveare known.
http://www.statisticalengineering.com/central_limit_theorem.htm
A great example of the theorem in action….
https://www.khanacademy.org/math/probability/statistics-inferential/sampling_distribution/v/sampling-distribution-example-problem
Another great example of the theorem in action….
Hypothesis Testing:
A statistic tests a hypothesis: H0
The alternative or default hypothesis is: HA
100: AH
Hypothesis Testing:
A statistic tests a hypothesis: H0
The alternative or default hypothesis is: HA
A probability is established to test the “null” hypothesis.
Hypothesis Testing:
95% confidence: would mean that therewould need to be 5% or less probability ofgetting the null hypothesis; the nullhypothesis would then be dropped infavor of the “alternative” hypothesis.
Hypothesis Testing:
95% confidence: would mean that therewould need to be 5% or less probability ofgetting the null hypothesis; the nullhypothesis would then be dropped infavor of the “alternative” hypothesis.
1 - confidence level (.95) = alpha
Errors:
Type I Error: saying something ishappening when nothing is: p = alpha
Type II Error: saying nothing is happening when something is: p = beta
http://www.intuitor.com/statistics/T1T2Errors.html
An example from court cases:
http://www.youtube.com/watch?v=taEmnrTxuzo
Care must be taken when using hypothesis testing…
PROBLEMS
I hypothesize that a barking dog is hungry.
To answer that questions, I would have to have someprior information.
For example, how often does the dog bark when it is not hungry.
No….
Because of the Z-test finds that the probability of doingthat is equal to 0.0228.
We would reject the Null Hypothesis!
But we have now thrown thecoin two hundred times, and…
It came up tails 100 times.
Is it a fair coin?
Paired Samples Statistics
Mean N Std. Error MeanPair 1 Right 5.4167 12 .70128 Left 4.9167 12 .62107
t(11) = 2.17, p = 0.053
What do you conclude?
Paired Samples Statistics
Mean N Std. Error MeanPair 1 Right 5.4167 12 .70128 Left 4.9167 12 .62107
t(11) = 2.17, p = 0.053
Now suppose you did this againwith another sample of 12 people.
t(11) = 2.10, p = 0.057
But the probability of independent events is:p(A) X p(B) so that:
The Null hypothesis probability for both studies was:0.053 X 0.057 = 0.003
What do you conclude now?
Paired Samples Statistics
Mean N Std. Error MeanPair 1 Right 5.4167 12 .70128 Left 4.9167 12 .62107
t(22) = 0.53, p = 0.60
What do you conclude now?