Statistical Testing
In order to understand all of the different types of hypothesis we must first define what each one means or what they stand for, in order for us to truly understand why we need to use them.
The term hypothesis is used to make an assumption, in order for us to make logic of the data. When we receive this data it is up to hypothesis to decide if we are going to accept or reject the information. This type of testing is done on the null hypothesis; the opposite of alternative hypothesis, H1. The null hypothesis is the hypothesis that will disprove, reject or nullify the data.
H1, one example would be that snack foods have a higher risk of clogging your arteritis when eaten with cheese.
HO, snack foods do not have a higher risk of clogging your arteritis when eaten with cheese.
If the null is rejected, with no alternative, the experiment may be invalid. This is the reason why science uses a battery of deductive and inductive processes to ensure that there are no flaws in the hypotheses (NULL HYPOTHESIS, 2008-2011).
Nonparametric tests are called distribution free statistics, because they don’t require any form of data that fits into a normal distribution. Nonparametric testing has less restrictive assumptions when they are reading data, the probability of rejecting the null hypothesis would be lower.
Chi Square Test compares observed frequencies that are within groups to their expected frequencies, example would be that HO = the observed frequencies that are not different from expected frequencies, research hypothesis relates to that they are different.
A few examples of what a Chi Square Statistic would look like would be the following, that FO = the observed frequency and that FE = the expected frequency, this is one way that they would use to view data. Other way in which they read the data is categories, meaning that in example degree of freedom = k-1, where k is the number of categories. Another way would be to compare value to Table of X2.
As this is still challenging to read if we calculated value of chi square is less than the table value, accept or retain HO, but if we calculate chi square as greater than the value, we then have to reject HO.
By using the ANOVA factor we would then be able to teat what the average sales would be for Company W’s regions, if we have 125 people using the software we would be able to compare the data and find out who is using the software and which regions were not using the software.
In order to market our products we must have the statistical testing done, to reach different groups, these formulas are very important so that we can better evaluate our companies data, by using the many different formulas it will enable our company to grow and expand our products to different regions, thus giving us a better view on how they will be choosing our product over someone else’s.
References
NULL HYPOTHESIS. (2008-2011). Retrieved June 5, 2011, from Experiment Resources: http://www.experiment-resources.com/null-hypothesis.html
3.2.3.1. (n/d). Retrieved June 5, 2011, from Engineering Statistics Handbook: http://www.itl.nist.gov/div898/handbook/ppc/section2/ppc231.htm
was using the software and who was not using the software per regions.