REPLY

1. What are some non-parametric tests? Please illustrate when one of them would be utilized. Make sure that your example is specific and unique.

2. For each parametric test, there is a nonparametric test "equivalent." With that in mind, which one is preferred (if you can use either)? Why?

A minimum of 75 words each question and References (IF NEEDED)(Response #1 – 7) KEEP RESPONSE WITH ANSWER

Make sure the Responses includes the Following: (a) an understanding of the weekly content as supported by a scholarly resource, (b) the provision of a probing question. (c) stay on topic

1. A parametric test is a hypothesis test that is used to test hypotheses about parameters in a population in which the data is normally distributed and measured on an interval or ratio scale of measurement (Privitera, 2017). Parametric test assume that the observations are independent except when paired. These test are more sensitive to sample size while nonparametric test are not.

 Nonparametric test are hypotheses test that are used to test hypotheses that do not make inference about parameters in a population, and to test hypotheses about data that can have type of distribution, and to analyze data on a nominal or ordinal scale of measurement (Privitera, 2017). Nonparametric test assume that the observations are independent and randomly drawn from the population. Nonparametric test do not require that the population of values are normally distributed. Nonparametric test are typically used when data isn’t normal.

 The parametric test’s measure of central tendency is mean while nonparametric test is median. Pearson’s coefficient of correlation is used in the parametric test to measure the degree of association and the spearmen’s rank correlation is used for nonparametric test.

2. “Parametric tests are hypothesis tests that are used to test hypotheses about parameters in a population in which the data are normally distributed and measured on an interval or ratio scale of measurement.” (Privitera, n.d.) This includes paired and unpaired t-test, linear regression, Pearson rank correlation, and ANOVA. ANOVA can be one way non repeated, and two way or three way repeated.

Nonparametric tests are hypothesis tests that are used 1, to test hypotheses that do not make inferences about parameters in a population, 2, to test hypotheses about data that can have any type of distribution, and 3, to analyze data on a nominal or ordinal scale of measurement.” (Privitera, n.d.) This includes the Mann-Whitney U, Wilcoxon Signed Rank, The Kruskal-Wallis, Chi-squared (x2).

The difference between these two test types is that parametric tests are performed to test whether a hypothesis is correct about a population where the data is normally distributed. While a nonparametric test data that is nominal or ordinal scale of measurement, where there is no inference about the population, and the data can have any type of distribution, it does not have to be normally distributed.

3. A parametric test is a hypothesis test which measures an interval or ratio scale, examples of a parametric test is the one sample t-test, the two-sample t-test, z test are a parametric test (Privitera, 2018). An example would be to measure the average age that depression is diagnosed in a sample of male and female clients. As you can see the sample is normally distributed. In nonparametric this same research would be proportioned.

Nonparametric are characterized by these 3 factors it does not need to test the parameters of a population, the population does not need to be normally distributed, this type of data can have any types of distribution (Privitera,2018). Nonparametric can be used to analyze data on a nominal or ordinal scale. This can be used in skewed distribution and categorical data. Examples of non-parametric are Wilcoxon rank- sum test, two sampled sign test

4. According th the readings, the difference between observed frequency and expected frequency is as follows:

Observed frequency is the amount of times an event actually occurred after a probability experiment or trial has been repeated a given number of times. Observed Frequencies are counts made from experimental data.

The expected frequency is a probability count. This appears in contingency table calculations including the chi-square test. Expected frequencies calculate standardized residuals, where the expected count is subtracted from the observed count in the numerator.

 Application of the chi-square test requires the computation of an expected frequency for each cell of a contingency table under assumption that there is no relationship between the two variables in the population.

If there is no difference between the expected and observed frequencies, then the value of the chi-square should be equal to 0, but the farther the chi-square value is from zero, the more likely there is a relationship present.

5. Observed frequencies are counts made from experimental data. You would actually observe the data that is occurring and take measurements. For example, if you roll a dice ten times and count how many times each number is rolled. So you are counting after the experiment is completed.

 Expected frequencies are counts calculated using the probability theory. Such as when you are going to roll a six-sided dice, you calculate the probability of any number rolled as 1/6.

 Chi square test are calculated by evaluating the cell frequencies that include the expected frequencies in cases when there is no association between variables. The test will then determine the similarities between the expected frequency and the observed frequency

6. Upon reading the textbook, it was stated that parametric tests consist of z-tests, ANOVA, correlation, and analysis of regression. These tests have parameters on the population. A non-parametric test can be used on data that does not have parameters on inferences on the population, test hypothesis of data that have any type of distribution, and can analyze data on an ordinal or nominal scale (Privitera., G.J., 2018).

7. Hi Professor Krywaruczenko nd class, from what I have read the parametric test are used to test the hypotheses within the parameters of a population and a non parametric test are used to test hypotheses that do not make assumptions in a population but sticks with one area to test." A parametric test includes the Student T test and the Anove because of normal distibution and the nonparametric test includes the chi-square and Fisher exact test and the Mann-Whitney." (Statistics How To, 2019).

"Parametric tests are hypothesis tests that are used to test hypotheses about parameters in a population in which the data are normally distributed and measured on an interval or ratio scale of measurement. Nonparametric tests are hypothesis tests that are used (1) to test hypotheses that do not make inferences about parameters in a population, (2) to test hypotheses about data that can have any type of distribution, and (3) to analyze data on a nominal or ordinal scale of measurement." (Privitera, 2017).