Principles of Description and Inference
9 videos • 98 views • by Fourth Z This is Playlist 2 in the Nonparametric Statistics for the Behavioral, Social and Medical Sciences series. The methods available for analyzing and making inferences about dichotomous variables are among the simplest in the world of statistics. In my opinion, this simplicity provides an ideal starting point for learning how to use description and inference in statistical analysis. Most introductory courses in applied statistics begin with the normal distribution, adding both a layer of complexity and the need to believe in a state of affairs that may well differ from reality. Even if you have learned the principles of description and inference in such a course, it may make more sense once seen from a nonparametric statistics perspective. My hope is that by presenting these concepts in the simplest possible framework that you will be best able to fully understand and apply the concepts. One side effect of deep understanding is that we will save time later as you generalize the concepts to other research settings with different numbers of conditions and types of variables. Here we go! The anticipated learning outcomes for this playlist are these: 1. You can describe dichotomous data and a Bernoulli event. 2. You can define joint events and calculate the number of such events as well as the probability of a single joint event. 3. You can count the number of permutations of a specified number of objects, including when not all objects are distinct. 4. You can define and calculate the binomial coefficient. 5. You can calculate densities and cumulative probabilities using the binomial distribution. 6. You can provide the proportion of success in a sample of observations. 7. You can use a sample of observations to estimate the proportion of success in a larger population. 8. You can assess the conditions for valid inference of the proportion parameter for exact inference. 9. You can test a hypothesis about a proportion using exact methods. 10. You can construct a confidence interval for a population proportion using exact methods. 11. You can explain the relationship of hypothesis tests to confidence intervals. 12. You can calculate power for the exact test of a proportion and can explain what this means.