Hypothesis Testing BasicsWord文档下载推荐.docx

1、Using theoretical sampling probability distributionsSampling distributions allow us to approximate the probability that a particular value would occur by chance alone. If you collected means from an infinite number of repeated random samples of the same sample size from the same population you would

2、 find that most means will be very similar in value, in other words, they will group around the true population mean. Most means will collect about a central value or midpoint of a sampling distribution. The frequency of means will decrease as one travels away from the center of a normal sampling di

3、stribution. In a normal probability distribution, about 95% of the means resulting from an infinite number of repeated random samples will fall between 1.96 standard errors above and below the midpoint of the distribution which represents the true population mean and only 5% will fall beyond （2.5% i

4、n each tail of the distribution）. The following are commonly used points on a distribution for deciding statistical significance: 90% of scores +/- 1.65 standard errors 95% of scores +/- 1.96 standard errors 99% of scores +/- 2.58 standard errors Standard error: Mathematical adjustment to the standa

5、rd deviation to account for the effect sample size has on the underlying probability distribution. It represents the standard deviation of the sampling distributionAlpha and the role of the distribution tailsThe percentage of scores beyond a particular point along the x axis of a sampling distributi

6、on represent the percent of the time during an infinite number of repeated samples one would expect to have a score at or beyond that value on the x axis. This value on the x axis is known as the critical value when used in hypothesis testing. The midpoint represents the actual population value. Mos

7、t scores will fall near the actual population value but will exhibit some variation due to sampling error. If a score from a random sample falls 1.96 standard errors or farther above or below the mean of the sampling distribution, we know from the probability distribution that there is only a 5% cha

8、nce of randomly selecting a set of scores that would produce a sample mean that far from the true population mean. When conducting significance testing, if we have a test statistic that is 1.96 standard errors above or below the mean of the sampling distribution, we assume we have a statistically si

9、gnificant difference between our sample mean and the expected mean for the population. Since we know a value that far from the population mean will only occur randomly 5% of the time, we assume the difference is the result of a true difference between the sample and the population mean, and is not t

10、he result of random sampling error. The 5% is also known as alpha and is the probability of being wrong when we conclude statistical significance. 1-tailed vs. 2-tailed statistical testsA 2-tailed test is used when you cannot determine a priori whether a difference between population parameters will

11、 be positive or negative. A 1-tailed test is used when you can reasonably expect a difference will be positive or negative. If you retain the same critical value for a 1-tailed test that would be used if a 2-tailed test was employed, the alpha is halved （i.e., .05 alpha would become .025 alpha）. Hyp

12、othesis TestingThe chain of reasoning and systematic steps used in hypothesis testing that are outlined in this section are the backbone of every statistical test regardless of whether one writes out each step in a classroom setting or uses statistical software to conduct statistical tests on variab

13、les stored in a database. Chain of reasoning for inferential statistics 1. Sample（s） must be randomly selected 2. Sample estimate is compared to underlying distribution of the same size sampling distribution 3. Determine the probability that a sample estimate reflects the population parameter The fo

14、ur possible outcomes in hypothesis testingActual Population ComparisonNull Hyp. TrueNull Hyp. FalseDECISION（there is no difference）（there is a difference）Rejected Null HypType I error （alpha）Correct DecisionDid not Reject NullType II Error（Alpha = probability of making a Type I error）Regardless of w

15、hether statistical tests are conducted by hand or through statistical software, there is an implicit understanding that systematic steps are being followed to determine statistical significance. These general steps are described on the following page and include 1） assumptions, 2） stated hypothesis,

16、 3） rejection criteria, 4） computation of statistics, and 5） decision regarding the null hypothesis. The underlying logic is based on rejecting a statement of no difference or no association, called the null hypothesis. The null hypothesis is only rejected when we have evidence beyond a reasonable d

17、oubt that a true difference or association exists in the population（s） from which we drew our random sample（s）. Reasonable doubt is based on probability sampling distributions and can vary at the researchers discretion. Alpha .05 is a common benchmark for reasonable doubt. At alpha .05 we know from

18、the sampling distribution that a test statistic will only occur by random chance five times out of 100 （5% probability）. Since a test statistic that results in an alpha of .05 could only occur by random chance 5% of the time, we assume that the test statistic resulted because there are true differen

19、ces between the population parameters, not because we drew an extremely biased random sample. When learning statistics we generally conduct statistical tests by hand. In these situations, we establish before the test is conducted what test statistic is needed （called the critical value） to claim sta

20、tistical significance. So, if we know for a given sampling distribution that a test statistic of plus or minus 1.96 would only occur 5% of the time randomly, any test statistic that is 1.96 or greater in absolute value would be statistically significant. In an analysis where a test statistic was exa

21、ctly 1.96, you would have a 5% chance of being wrong if you claimed statistical significance. If the test statistic was 3.00, statistical significance could also be claimed but the probability of being wrong would be much less （about .002 if using a 2-tailed test or two-tenths of one percent; 0.2%）.

22、 Both .05 and .002 are known as alpha; the probability of a Type I error. When conducting statistical tests with computer software, the exact probability of a Type I error is calculated. It is presented in several formats but is most commonly reported as p or Sig.Signif.Significance. Using as an exa

23、mple, if a priori you established a threshold for statistical significance at alpha .05, any test statistic with significance at or less than .05 would be considered statistically significant and you would be required to reject the null hypothesis of no difference. The following table links p values

24、 with a benchmark alpha of .05:P AlphaProbability of Type I ErrorFinal Decision.055% chance difference is not significantStatistically significant.1010% chance difference is not significantNot statistically significant.011% chance difference is not significant.9696% chance difference is not signific

25、antSteps to Hypothesis TestingHypothesis testing is used to establish whether the differences exhibited by random samples can be inferred to the populations from which the samples originated. General Assumptions Population is normally distributed Random sampling Mutually exclusive comparison samples

26、 Data characteristics match statistical technique For interval / ratio data use t-tests, Pearson correlation, ANOVA, regression For nominal / ordinal data use Difference of proportions, chi square and related measures of associationState the Hypothesis Null Hypothesis （Ho）: There is no difference be

27、tween _ and _. Alternative Hypothesis （Ha）: There is a difference between _ and _. Note: The alternative hypothesis will indicate whether a 1-tailed or a 2-tailed test is utilized to reject the null hypothesis. Ha for 1-tail tested: The _ of _ is greater （or less） than the _ of _.Set the Rejection Criteria This determines how different the parameters and/or statistics must be before the null hypothesis can be rejected. This region of rejection is based on alpha （ ） - the error associated with the confidence le