Maths Test 1 Notes Variables - Any characteristic, number or quantity that can be measured, the value may vary between populations, gender, age or race. They can be nominal (categorical), ordinal (categorical, scale or interval (numeric, continuous) Small distributions - There will be an overlap Large distributions - They will be further apart Standard Deviation - A measure of variance Difference between Standard Deviation and Standard Error - The standard deviation (SD) measures the amount of variability/dispersion, for a subject set of data from the mean, how well a set of scores represent the sample mean. It is a measure of random error variability. While the standard error of the mean (SEM) measures how far the sample mean of the data is likely to be from the population mean, how well the sample mean represents the population mean. It is a measure of sampling error. The SEM is always smaller than the SD Symbols - ? (Sum), s2 (sample variance), s (standard deviation), x (sample mean), x (sample), SE (Standard error), N (number of participants) Assumptions for a parametric test - 1) Normal distribution, 2) homogeneity of variance, independence of data points A hypothesis - Is a proposed explanation for a certain phenomenon, which is testing in an experimental test, it must predict something will change (even if it predicts nothing will change) What is hypothesis testing - Testing an assumptions based on population parameters. The method depends on the type of data and reason for analysis. To infer the result of the study/hypothesis performed on a sample to the rest of the population Theorising - how the IV has an affect on the DV, formulating a hypothesis, design an experiment based on this that manipulates these levels, controls confounds and measures the outcome KERLINGER - interrelated constructs, form a hypothesis, establish a relationship between two variables and explain the phenomena How to show cause and effect - Strong experimental design, pilot study, linear temporal relationship, controlling internal validity, avoiding selection bias Importance of controls - To avoid reducing internal or ecological validity, avoids confounding variables, extraneous variables. You need a carefully controlled environment following a specific protocol Control procedures - Counterbalancing, blind or double blind, deception, concealment A control group - Do not receive the key treatment, everything else is the same to avoid confounds Internal validity - Historical/order effects/boredom, temporal effects, regression to the mean External validity - Experimenter bias, ecological validity, population validity, demand characteristics Disadvantages of between-subjects t-test - Practicality (need more participants), individuality, difficult to match people (affects generalisability), expensive, takes more time, less sensitive to small
significant differences, matching the environment is difficult, diffusion of treatment (participants may talk to each other), resentment, compensatory equalisation of treatment, rivalry True experiment - A type of experimental design and is used to establish cause and effect relationships. Manipulating the IV and the DV, using random selection, using an experimenter group and a control group