This is an excellent collection of articles illustrating the use of statistics in various
fields. Paulos, John A. A Mathematician reads the newspaper. Anchor Books ...
GEMP40010 - Introduction to Quantitative Research Methods Credits : 10 Module Co-ordinators : Dr Patrick Murphy & Caroline O’Kelly Module Description : This module is worth 10 credits and is aimed at first year PhD students in the Colleges of Human Sciences and Business and Law. The module will provide students with an introduction to Quantitative Research Methods. There will be two aspects to the course, one will concentrate on how to design and conduct surveys and experiments for data collection. The second will consider some basic statistical tools for analyising data. The module is a 10 credit module with 5 credits based on work in weeks 1 to 6 where the course will focus on the fundamental principles of research methods and statistics including data collection. Weeks 7-12 will be more applied in nature and will provide students with the skills required to complete basic statistical analyses. Topics covered will include: design of sample surveys, observational studies and experiments, descriptive statistics, hypothesis testing and confidence intervals, simple linear regression and analysis of variance. Learning Outcomes : Students will be able to critically assess studies in the literature and will be able to compute basic descriptive statistics and conduct basic hypothesis tests. They will also be required to conduct a study of their own in the first 6 weeks of the course. In weeks 7-12 they will gain familiarity with entering and analysisng data using SPSS. This will enable them to analyse the data that they have collected in weeks 1-6. Finally they will gain experience in writing a research report.
Introduction to Quantitative Methods – Part 1 Dr. Patrick Murphy Course Description: This course is a gentle introduction to statistics and its simple applications. The only prerequisite is secondary school algebra and a lot of common sense. In most cases the latter requires some interest in scientific methods and "truth" finding. By the completion of the course students are expected to be able to recognise the statistical nature of scientific information, and to perform and interpret simple statistical computational tasks. Course Outline: Introduction: why statistics? Reading the news Measurement, sampling and opinion polls Experiments and observational studies Summarising data Normal distribution Relationship between variables Simple Linear Regression with applications in Business and Social Sciences How to interpret Hypothesis Tests and Confidence Intervals
Required Text: Utts, J. M. (1999). Seeing through statistics. London: Duxbury Press.
Further Reading: Hinkle, D. E., Wiersma, W. and Jurs, S. G. (1994). Applied statistics for the behavioural sciences (3rd ed.). Boston, MA: Houghton Mifflin. Pagano, R. R. (1993). Understanding statistics in the behavioural sciences (4th ed.). St. Paul, MN: West. Tanur, J. M., et a1. (1989). Statistics, a guide to the unknown. Pacific Grove, CA: Wadsworth and Brooks Cole. This is an excellent collection of articles illustrating the use of statistics in various fields. Paulos, John A. A Mathematician reads the newspaper. Anchor Books
Learning Objectives for Introduction to Quantitative Methods – Part 1 Dr. Patrick Murphy
Topic1 What is statistics? Learning Objectives: Appreciate that statistics are frequently misused. Understand the difference between Descriptive Statistics and Inferential Statistics.
Topic 2 To Believe or not to Believe Learning Objectives: Become critical users of reports presented by others. In particular the student should be familiar with the Seven Critical Components and should be able to identify when a study fails any of these components. Students could be presented with new studies and asked to identify what are the problems with the study.
Topic 3. Asking Questions
Learning Objectives: Students should appreciate that the way a question is phrased in a survey can dramatically influence the responses received. Seven problems associated with questions on surveys are presented the students should be familiar with these and should be able to identify if a question on a survey suffers from any of these problems. Students should appreciate the difference between Open and Closed questions and they should understand the problems associated with each. Under the heading “Defining what is being measured” they should understand how sometimes reports use statistics in the wrong context. “The statistics don’t measure what they are claiming they measure” The differences between categorical and numerical variables should be understood. Concepts such as reliability and validity should be understood.
Topic 4 How to get the data Learning Objectives Students should understand the differences between Sample Surveys, Observational Studies and Experimental Studies. They should understand various different methods used in each of these ( for instance in Sample surveys they should understand the ideas of Stratified Sampling, Cluster Sampling etc.) They should also appreciate the pitfalls that can occur with each of these three data collection methods. If given details of a study the students should be able to identify the methodology used and to critique the study to determine if it was performed appropriately. Topic 5 What to do when you have the data Learning Objectives Be familiar with basic descriptive statistics ( Stem and Leaf diagrams, Histograms, Means, Medians, Modes, Standard Deviations). In particular students should be able to draw each of the graphs themselves and should understand how to use the statistics mode on their calculators to compute the above quantities. Understand the idea of Skew-ness in data sets, variability and the empirical rule and percentiles and Z-Scores. Understand how to read Standard Normal tables as provided in the exam to compute probabilities for a given Normal Random Variable. (Note special tables are used not Cambridge Tables) Topic 6 Relationships between Variables Learning Objectives Become familiar with scatter plots. Understand how to interpret a correlation coefficient but do not need to be able to compute this. Understand the difference between correlation and causation. Relate this to the concept of confounding variables discussed earlier. Topic 7 How to interpret Hypothesis Tests and Confidence Intervals In this section we will consider some the meaning and relevance of Type I and Type II errors. We will discuss the relationship between Significance Levels and Power for hypothesis tests. We will then consider the meaning of Confidence Intervals and their use in estimating population characteristics. We finish with a discussion regarding the relative merits of P-Values and Confidence Intervals and we consider the newer approach involving Effect Sizes. Learning Objectives Understand the principles of making population inferences based on sample statistics Become familiar with Type I and II errors in Hypothesis tests Be able to interpret P-Values and understand the limitations of these Be aware of the literature regarding the merits of Confidence Intervals and P-values with emphasis of effect sizes.
Topic 8 Simple Linear Regression with applications in Business and Social Sciences Learning Objectives Understand the purpose of Linear Regression Gain an awareness of the types of data where Linear Regression may be applied Understand how to interpret the output from a Regression analysis.
