Using APA intext citations, and based on the information below, How does a researcher determine what type of statistical analysis is appropriate to analyze their data?

Knowing what factors determine what statistical analysis you should use is important because it will allow you to select and use appropriate methods for evaluating outcomes and practice effectiveness (Competency 9, Evaluate Practice With Individuals, Families, Groups, Organizations, and Communities), and assess how social welfare and economic policies impact the delivery of and access to social services (Competency 5, Engage in Policy Practice). Besides knowing what types of statistical analysis to conduct based on the level of measurement of the independent and dependent variables, the purpose of the research question, and the number of independent and dependent variables, social workers need to be able to interpret the results from these analyses. For all the statistical procedures discussed in this chapter, you will find information on how to interpret the results.

At the outset, we must state that we will not discuss all the statistical procedures researchers use to analyze their data. For those of you who are interested in learning more about other statistical procedures not discussed in this book, there are lots of books available that provide a comprehensive overview of these procedures. In this chapter, you will be introduced to two types of statisticsdescriptive and inferential. Univariate descriptive statistics allow researchers to describe or summarize their data. A researcher would use descriptive statistics to answer the following research question: "What percentage of individuals participated in a particular program?" Descriptive statistics would not be appropriate to answer a research question where a researcher is interested in determining if parenting practices are associated with less substance use. The descriptive statistics you will learn about in this chapter are frequency distributions and measures of central tendency, and measures of variability (dispersion). Diagram 13.1 presents information about when these descriptive statistics should be used based on the level of measurement of the independent and dependent variables. Researchers use inferential statistics to estimate a parameter and to determine whether the results of statistical tests based on the sample drawn from a population can be generalized to that population. One type of inferential statistic that is used to estimate a parameter is a confidence interval (CI). CI is a statistic used to estimate a parameter based on the data from the sample to say something about a population parameter that is unknown. The CI gives you an interval (a range of values that likely includes the unknown population parameters) and an associated confidence, which quantifies the level of confidence a researcher can have that the parameter lies in the interval. The 95% confidence level is the most commonly used. A CI is normally formatted as follows: (98.000, 98.37), 95% confidence interval. In this chapter, you will be introduced to inferential statistics that are used to test the statistical significance of hypotheses. There are two categories of inferential statistics used to test the statistical significance of hypotheses. One type of inferential statistic is categorized as statistics used to assess the degree of relationship among variables (i.e., Pearson's correlation, chi-square test of independence, and multiple regression analysis). Diagram 13.2 presents information about when these statistics are to be used to assess the degree of relationship among variables based on the level of measurement of the independent and dependent variables. The other type of inferential statistics is categorized as statistics used to assess significance of group differences (i.e., independent and dependent t-tests, analysis of variance [ANOVA], and multivariate analysis of variance [MANOVA]). Diagram 13.3 presents information about when to use the independent t-test, dependent t-test (paired t-test), and ANOVA to assess significance of group differences based on the level of measurement of the independent and dependent variables.