Exploring Inferential Statistics and Their Discontents

Solution Preview

Part 1
2.
Degrees of freedom are the number of values in the final calculation of a statistic that are free to vary. This is the number of values involved in a calculation have the freedom to vary. To calculate the degrees of freedom we minus one from the number of values in a data set. Df = N-1 where N is the number of values in the sample size. This applies to 1-sample t test.
3.
Inferential statistics allow me to infer conclusions that extend beyond the immediate data. Inferential statistics is used to infer from the sample data what the population might be. Inferential statistics allow me to infer information about the whole population even though I have access only to limited number of data (1). Inferential statistics enable me to make inferences about the population. These statistics are required because it is not possible or convenient to measure information about the entire population.

4.
The general linear model is a statistical linear model. From a narrow perspective the general linear model is an ANOVA procedure in which the calculations are done using a least squares regression approach to show the statistical relationship between one or more predictors and a continuous response variable. The general linear model is a generalization of multiple linear regression model to the case of more than one dependent variable It matters because it underlies most statistical analyses that are used in social research. It provides the foundation for Analysis of variance, t-test, analysis of covariance, and regression analysis (2). In addition it also provides the foundation for multivariate statistical analysis methods such as factors analysis, cluster analysis, multidimensional scaling, discriminant analysis, and canonical correlation.
5.
A parametric statistic is one obtained from a test in which specific assumptions are made about the population parameter. A nonparametric statistic is one obtained from a test in which non-metric independent variables are used. The basis of parametric statistic is a distribution. In case of nonparametric statistic the basis is arbitrary. In case of parametric statistic, the measurement level is interval or ratio, whereas in case of nonparametric statistic the measurement level is nominal or ordinal. In case of parametric statistics, the measure of central tendency is mean, whereas in case of nonparametric statistics, the measure of central tendency is the median. For parametric statistic, the information about the population is completely known, however, in case of nonparametric statistic, the information about the population is unavailable. The correlation test for parametric statistics is Pearson's test, whereas the correlation test for nonparametric statistics is Spearman's test. The parametric statistic and ...