Introduction Statistics A branch of mathematics dealing with the collection, analysis, interpretation, and presentation of masses of numerical data.
Statistics for the Social Sciences emphasizes
the analysis and interpretation of data to give students a feel for how data interpretation is related to the methods by which the information was obtained. Statistics (Contd…) • “Statistics are numerical statement of facts in any department of enquiry placed in relation to each other.” ----By Bowley
• “By Statistics we mean quantitative data
affected to a marked extent by multiplicity of causes.” ---By Yule and Kendall Psychological research and statistics • psychologists do not study statistics for its own sake. Statistical tests simply provide a tool for: • analyzing the results of psychological research. • The aim of psychological research is to test psychological theories about – human behavior and to make predictions about human behavior • in order to test whether the results of the research support the prediction or not. Psychological research and statistics
Once you appreciate that the point of
psychological research is to test research predictions, you will find that learning to select and use statistical tests will be reasonably straightforward. Variability in human behaviour One of the particular aspects of humans is that they vary a great deal in their characteristics and behaviour. So it is difficult for psychologists to make predictions that will apply to all human beings in exactly the same way. Even identical twins develop differently, depending on circumstances. Variability in human behaviour (Contd..) • For this reason, psychological researchers make predictions in a way that reflects the variability in human behaviour.
• The variability between humans is formulated
as variables. The aim of psychological research is to study variables in human behaviour. Ungrouped vs Grouped Ungrouped Grouped It is the data that you first It is data that has been gather. organized into groups Ungrouped data is data in known as classes. raw. Grouped data has been ‘classified’ and thus some level of analysis has taken place, which mean that data is no longer raw. It is organized in a frequency distribution. Types of Statistics Interval, nominal, ordinal, ratio Parametric Test • If the information about the population is completely known by means of its parameters then statistical test is called parametric tests.
Example: t-test, z-test, ANOVA, regression
**parameter: a numerical measurement
describing some characteristic of a population. Non-Parametric Test • If there is no knowledge about the population or parameters, but still it is required to test the hypothesis of the population. Then it is called non-parametric test.
• Example: mann-Whitney, rank sum test,
Kruskal-Wallis test, chi-square Types of Descriptive Tests Measures of Measures of Central Measures of Measures of Frequency Tendency Dispersion or Position Variation Use this when you Use this when you Use this when you Use this when you want to show how want to show how want to show how need to compare often response is an average or most “spread out” the scores to a given commonly indicated data are. normalized score response
• Count • Mean • Range: High/Low • Percentiles
• Percent • Median Points • Quartiles • Frequency • Mode • Variance & Standard Deviation (S.D): difference between observed score and mean Limitations of Statistics • Statistics is not suitable to the study of qualitative phenomenon • Statistics does not study individuals • Statistics table may be misused • Statistics is only, one of the methods studying a problem