** ALL FIGURES TO 2 DECIMAL PLACES EXCEPT FOR P VALUE ** PROBABILITY = P VALUE p < . 050 = significant, p > .050 = not significant, p = . 000 report as p<0.001 ** DO NOT REPORT NEGATIVE FOR T VALUE ** PROPORTION = frequency MEAN X = total of all values total number total number MEAN DIFFERENCE = xd STANDARD DEVIATION = Sd INDEPENDENT VARIABLE CAUSES A CHANGE IN DEPENDENT VARIABLE. It is not possible that DV could cause a change in IV ** If unclear usually the IV is mentioned first, then the DV ** OBSERVATIONAL = Uncontrolled/uninfluenced observation EXPERIMENTAL = Manipulating IV to observe effect on DV BIAS - Source = sample selection or bad measurement/wording BIVARIATE - Used to obtain correlation coefficients, a measure of linear relationship between 2 variables. It computes Pearson's correlation coefficient CONFIDENCE INTERVAL - The range of values above and below the sample mean within which you are 95% certain the true population mean lies. In normal distributions, 95% of values fall within 2 standard deviations of the mean. 2.5% either side are unusual results CONFOUNDING FACTOR - Factors other than IV which may affect result NUISANCE VARIABLES - affect the dependent variable. Experiments design must minimise or evenly distribute NV effects. NV act as confounding factors CONTROLLING NUISANCE VARIABLES Independent Groups Design - Random allocation of separate groups to undertake tests under different conditions. Group 1 driving with BAC of .00 and group 2 driving with BAC .05. Doesn't minimise NV but distributes. Matched Pairs - Match participants with those very similar, separate into groups to undertake tests under different conditions. Time consuming & difficult to identify NV. Repeated Measures - Same participants undergo tests under different conditions several times. Introduces practice effects which sway results. T SCORE - When there is a low probability that the results of an experiment occurred by chance alone- results are significant if the probability of their occurance by chance is equal to or less than 0.05. When standard deviation is unknown T VALUE - Calculated difference in units. The closer to 0, the less likely there isn't a significant difference Z SCORE - Standardised value, the number of standard deviations away from the mean Z = x- u Data value - mean of pop 6 standard deviation Below mean = negative score, above mean = positive score PEARSON'S CORRELATION COEFFICIENT .50 or more - a strong linear relationship .30 to .49 - a moderate strength linear relationship .10 to .29 - a weak linear relationship Less than .10 - an extremely weak linear relationship ** MUST INCLUDE NEGATIVE SIGN FOR REPORTS AND CALCULATIONS ** P value to test hypothesis REGRESSION y = a + b x X x = I variable | y = D variable | a = vert. intercept (average start size eg. Newborn guinea pig weighs 50g, a = 50). b = SLOPE / REGRESSION COEFFICIENT (average change per period eg. guinea pig weighs 70g more per month of