Week 9: Final Project

Week 9: Final Project

Hypotheses

Statistical hypothesis is any supposition regarding the distribution of the population - a function or parameter value decomposition. It is the process of checking the veracity of the assumptions on the basis of a random sample of the verification of statistical hypotheses.

Formulation of a Null and Alternate Hypothesis

The null hypothesis (H0) is a hypothesis subject to verification procedure, in which we assume that the difference between the analyzed parameters or distributions is zero i.e. there is no statistical difference between the two variables and in our case the variables are bipolar disorder and schizophrenia patients.

We then build a t - statistic, which is a function of the results of the random sample and we determine its distribution, assuming that the null hypothesis that is there is no in the physical activities of bipolar disorder and schizophrenia patients and simultaneously there is no difference in the magnitude of disorder among the bipolar disorder and schizophrenia patients is true. The function is called the test statistic or test function(Box et el, 2005). Following are the formulated hypothesis:

H1: There is a significant difference in the physical activities of bipolar disorder and schizophrenia patients.

H2: There is a significant difference in the magnitude of disorder among the bipolar disorder and schizophrenia patients.

At this stage of the verification procedure we take the maximum allowable probability of committing a type I error, which is to reject the null hypothesis when it is true. This probability is indicated by a and called the significance level. In general, we assume the probability close to zero, because we want to minimize the risk of errors being made. Most assume significance level a = 0.05, the time shall be such as a = 0.01, a = 0.1.

Statistical Procedure

There are two different groups used in the studies: bipolar and schizophrenia patients. To determine differences between their levels, initially to support hypothesis 1, independent samples t - test could be used to determine differences between the groups(Clement et al, 2003). The Wilcoxon-Mann-Whitney test is based on the positions of the values ??obtained by combining the two samples. This is done by ordering up these values, from smallest to largest, regardless of the fact that each population value comes from. In case we have a random variable qualitative ordinal numbers commonly associate the various categories (or classes, or attributes), according to which the variable is classified. In this case and in other situations it is preferable to work stations than with arbitrary values ??associated with the qualitative variable.

Similarly, for hypothesis 2, differences in the disease levels were observed which can be determined through paired samples t - test. In paired samples t - test, there are two samples each observation in the first sample is paired with an observation of the second sample(Creswell, 2008). In our research design the study of measurements made before and after the treatment provided to bipolar and schizophrenia patients.

Independent samples test the null hypothesis from two means from two ...