Upload
euri
View
235
Download
4
Embed Size (px)
DESCRIPTION
Lecture
Citation preview
Research in Psychology and Basic Concepts in Statistics
Bryan Q. EngayApplied Psychology Program
University of the Philippines Extension Program in Pampanga
Basic Concepts
• Population – entire collection of events/observations we are interested in studying.
• Parameter – measurement taken from the population.
• Statistic – measurements collected from the sample drawn from the population.
Basic Concepts
• Population – denoted by the Greek letter (mu) µ.
• *we must always clearly define the population we are interested in.
Basic Concepts
• Samples – observations drawn from the population and used to infer something about the characteristics of the population.
• Sampling frame – term used to refer to the population where samples are drawn from.
• Variable/s – things/observations/constructs that can be measured, controlled, or manipulated in research and can take on different values.
Basic Concepts
• Independent variable – variables that could have an effect on other variables and the one usually controlled in research.
• Dependent variable – variable affected by the variations in the independent variable.
• Independent variables may be either quantitative or qualitative and discrete or continuous.
Basic Concepts
• Dependent variables are generally, but not always, quantitative and continuous.
• Confounding variables – variables that can affect the outcome of the study, but which are not strictly part of the study. (have to be controlled in experiments)
• Discrete variables – variables that can take on only a limited number of values. (e.g., gender, high school class)
Basic Concepts
• Continuous variables – variables which can assume, at least in theory, any value between the lowest and highest points on the scale. (e.g., age and self esteem score)
• Quantitative data/Measurement Data – data which are results of any sort of measurement.
• Categorical data – (frequency data or qualitative data)
Basic Concepts
Levels of Measurement of Variables/Scales
1. Nominal – variables that allow for only categorization into named sets. Individual items belong to some distinctively different categories, but there is no quantifying or ranking of items.
Examples: male or female, Republican, Democrat, or Independent.
Basic Concepts
2. Ordinal – variables which are ranked in order in terms of which has less and which has more of the quality represented by the variable, but not how much more.
Examples: socioeconomic status, military ranks, Holmes and Rahe (1967) Scale of Life Stress.
3. Interval – not only give rank but also quantify and compare the size differences (interval) between.
Basic Concepts
Examples: temperature, Fahrenheit and Celsius
4. Ratio – variables that have an identifiable absolute ottrue zero point.
Examples: length, volume, time
Basic Concepts
• Descriptive statistics – statistics primarily aimed at describing or summarizing data into meaningful framework.
• Examples: measures of central tendency (mean, median, mode), measures of dispersion (standard deviation, variance), graphical representations of data or distribution (histograms, graphs, scatter plot etc.)
Basic Concepts
• Exploratory Data Analysis (EDA) or Exploratory Statistics – (developed by John Tukey) necessity of paying close attention to data and examining them in detail before invoking more technically involved procedures.
• Inferential statistics – inferring hypotheses or educated guesses from the sample to the population with the use of statistical procedures.
Basic Concepts
Cornerstones of Research
• Validity – measures what is supposed to be measured in research.
• Reliability – replicability of findings in research.
• External validity – refers to whether or not experimental or research results can be generalized to a real-world situation.
Basic Concepts
• Internal validity – manipulation of variables in research has led to an observed/desired difference.
• Hypothesis – a formal way of expressing a question as a prediction that can be tested.
• Null hypothesis – hypothesis that states that there will be no effect of the independent variable on the dependent variable.