Day 10 Flashcards
Technique of hypothesis testing
Hypothesis testing is technique to help determine whether a specific treatment has an effect on te individuals population.
Zpoint
Whenever there is a z point decision, you can either accept or reject the null hypothesis
Type 1 error
Where saying something is significant when it is not significant.
Type 2 error
Failing to reject the null hypothesis when you should
Trying to minimize type 1 and 2 error
Trying to minimize type 1 error the most because you are saying something matter when it does not, giving false support. Type 2 is ignoring a significance.
One-tailed
When there is a direction hypothesis one-tailed may be used. One-tailed test increases probability of a type 1 error. Therefor one-tailed should not used unless there is strong evidence.
Statistical power
probability that a statistic test will correctly reject the null hypothesis. Influence by sample size, effect size, alpha chosen, using one-tailed vs. two-tailed
Distribution of sample means
Samples differ from each other- given a random sample it is unlikely that sample means would always be the same. The distribution of the sample means is the collection of the sample means for all the possible random samples of a particular size(n) that can be obtained from a population
Central limit theorem
The distribution of sample means will have a mean that is equal to the population mean (H). The distribution of sample means will have a SD based on the sample. Bigger means better/ normal curve. As a sample gets large distribution has more cluster shape of the distribution of the sample means.
Standard error
Variability of a distribution of scores is measured by the SD. variability of a distribution of sample means is measured by the standard deviation(SD), of the sample means and is called standard error.
Calculating standard error
standard error is estimated using the SD of a sample and the size of the sample: standard error(SE)/ Square root of the pop.
Hypothesis testing procedure in summary
Ste the hypothesis, set decision criteria, collect and analyze data and decide.
Null hypothesis will be rejected if
Will be rejected when the sample mean is extremely unlikely occurred by chance. How unlikely? P
P vaule
P-value is the probability of getting a sample with a particular mean. Using distribution(curve) see where they to determine what is what.
Assumption of Z test
Random sampling, independent observation, SD is not changed by the treatment and distribution of sample means is normal
