Hypothesis testing

Hypothesis testing

1. Using the T-TEST we controlled one specific variable and measures the result, in linguistics, we are commonly faced with no experimental data.

2. F-test; t-test is a factual strategy that looks at the method for two groups or two arrangements of scores while considering their variance. The F-test depends on dividing the bigger variance by the smaller variance. and looking into basic qualities. The F-test is just a way to an end

3. The chi-square test has the purpose of deciding whether the acceptance of the hypothesis is possible when a given a sample comes from a certain population that has a specific probability distribution within the null hypothesis. If the null hypothesis is rejected, if there is a significant difference between the observed frequencies and the expected frequencies. using this kind of test, the measurement level must be higher or nominal. The Chi*-square can take values between zero and infinity. if the sample increases the value also increases.

4. ANOVA

   • Two or more populations are equal are tested analysis of variance, (ANOVA) comparing the response variable of various levels of the factors to determine the value of more or one factor.
     • (ANOVA) it consists of a set of mathematical models and procedures in which the variance is partitioned into different components due to various explanatory variables. ANOVA (Analysis of Variance in English)

5. Techniques for analysis of variance

   • in statistics model for estimating the dependency relationship between a dependent variable Y (anxiety) and independent variables X (different treatments), and a random phrase.
   • ANOVA is used to see whether different therapies (Psychiatric treatments), ANOVA is used to test theories regarding differences, and ANOVA entails the study or decomposition of total variability, which is primarily due to two sources of variation: Intergroup variability, Intergroup variability or error, and Types of ANOVA.
     • Types of analysis of variance (ANOVA)
       • ANOVA I: there is only one condition for clasification (independent variable), It can be both intergroup (there are many experimental groups), and intragroup (there are just a few)
       • ANOVA II, there are several classifications criteria
   • Characteristics and assumptions
     • Consistency: this implies that the scores of the dependent variables (anxiety) must have a normal distribution The so-called goodness-of-fit tests are used to verify this assumption
     • Self-reliance: there is no autocorrelation between the scores, the scores are independent of one another.
     • Homoscendacity: the variance is a measure of score variability and dispersion, and it rises as the score variability or dispersion rises.
     • the definition of sphericity: means that the various sources of error are related to one another.
     • Complementary: there is no subject X treatment interaction, if the assumption is not met, the error variance will rise.