University of Galway

Course Module Information

Course Modules

Semester 1 | Credits: 5

This module demonstrates classical and modern approaches for statistical inference in Business, Finance, Marketing and Economics. Students should already be familiar with methods in descriptive statistics and basic probability theory, including the normal probability distribution before taking this module. This module is a first course in statistical inference covering sampling distributions, construction of confidence intervals, hypothesis testing, and communication of results of analysis in application.

Learning Outcomes
  1. define basic terms: experimental unit, quantitative and qualitative variables, population, sample, parameter, statistic, descriptive statistics and inferential statistics, standard error, sampling distribution, and identify these in application.
  2. calculate the standard error and determine the sampling distribution for a statistic, in common applications, including stating and applying the Central Limit Theorem in the context of the sampling distribution for large and small samples. Discuss and check any assumptions that apply in those cases.
  3. construct and interpret a confidence interval for a population parameter, and discuss factors that will result in a more precise interval estimate.
  4. carry out a hypothesis test for a population parameter, in doing so, define type I and type II error, the significance level, the test statistic, the power of the test and the p-value and interpret each of these terms in application. Complete the hypothesis test by either determining a rejection region for the test statistic, a rejection region for the sample estimate of the parameter, or a p-value. Identify and complete one and two tailed testing procedures.
  5. interpret results from inferential techniques in variety of applications including estimation of a single population mean (large and small samples), a population proportion of successes in a binary variable, population proportions in a multinomial experiment, i.e. the chi-square goodness of fit test, comparing means of two populations (large and small samples, independent samples and paired samples), comparing means of more than two populations using ANOVA, comparing proportions of successes between two populations (large and small samples), inference for model parameters in simple linear regression.
  6. use statistical computing software to produce output which reports confidence interval estimates and results of hypothesis testing in a variety of applications, and incorporate this output in statistical report writing.
Assessments
  • Written Assessment (70%)
  • Continuous Assessment (30%)
Teachers
The above information outlines module ST2120: "Data Science for Business Analytics II" and is valid from 2023 onwards.
Note: Module offerings and details may be subject to change.