Research methods

what is the name for the variable that is manipulated or changed by the researcher?

independent variable

what is the name for the variable which is measured?

dependent variable

a design where each ppt takes part in all conditions is known as a ….

within-subject design

advantage of within-subject design

it accounts for individual differences - each ppt acts as their own control

disadvantage of within-subject design

order effects, fatigue effects and demand characteristics

a design where different ppts are assigned to each condition is known as a …

between-subject design

disadvantage of between-subject design

variation due to individual differences

in analysis, matched pairs is treated like what other design

within subject design

a variable that is not controlled in an experiment and could potentially affect the dependent variable

extraneous variable

a variable that varies systematically with the IV

confounding variable

data consisting of categories

nominal

data that consists of categories in a hierarchical order

ordinal

continuous data on a scale with equidistant intervals and no meaningful zero

interval data

continuous data on a scale with equidistant intervals and an absolute zero

ratio data

which measure of central tendency is the middle point of an ordered list of data?

the median

formula for calculating standard error

SE = SD/ square root of N (sample size)

what is the purpose of a Z score?

used for comparing scores between ppts or across different conditions

name of the test used to check is data is normally distributed

shapiro-wilk test

within how many standard deviations from the mean does 95% of the data fall in a normal distribution

95% of the data falls within 1.96 SDs of the mean

what is the formula for calculating a 95% confidence interval

CI = mean± (1.96 x SE)

which skewed distribution makes the mean and median are lower than the mode

negative

which skewed distribution makes the mean and median higher than the mode

positive

if data is skewed, which measure of central tendency better represents the average

the median

stat tests that work on the mean, assuming normal distribution, are…

parametric tests

what are non-parametric tests

alternative tests that use the median for non-normally distributed data

what is a sampling error

difference between the sample mean and population mean

what is a type 1 error

true null hypothesis is incorrectly rejected - false positive

what is a type 2 error

false negative - concluding there is no significant effect when one actually exists

is the p valye is less than 0.05, what decision is made regarding the null hypothesis

its rejected

if the p value is 0.05 or more, is it significant or not?

non-significant

for shapiro wilk, do the results have to be significant or not to demonstrate normality?

non-significant - more than 0.05

purpose of a one sample t-test

compares the mean of a single sample to a known single number

non-parametric alternative to the one-sample t-test

one-sample Wilcoxon signed-rank test

purpose of an independent sample t-test

compares the means of two independent groups in a between-subject design

what is homogeneity of variance

the assumption that the variance in each condition is similar

which stat test checks for homogeneity of variance

levene’s test

for homogeneity of variance to be met, does levene’s test have to be significant or not?

non-significant - 0.05 or more

non-parametric alternative to the independent samples t-test

mann-whitney U test

purpose of a paired sample t-test

compare the means of two related conditions in a within-subject or matched-pairs design

what assumption must be met for a paired sample t-test concerning normality

differences between the two conditions must be normally distributed

non-parametric alternative to the paired sample t-test

wilcoxon signed-rank test for related samples

which stat tests compares the observed proportion of a single dichotomous variable to an expected proportion (chance)?

a binomial test

which test is used to determine if there is an association between two nominal variables in a sample

chi-square test of independence

two key sample size assumptions for a chi-square test of independence

sample size of at least 40 and each cell must have an expected frequency of 5 or more

non-parametric alternative for chi-square test of independence

fishers exact test

another name for a directional hypothesis

one-tailed hypothesis

which test is similar to a binomial test but can be used when a single nominal variable has more than two options

chi-square goodness-of-fit test

name of the stat used to measure the strength and direction of a linear relationship between two continuous variables

Pearson’s Product Moment Correlation Coefficient (Pearson’s R)

range of possible values of a correlation coefficient

range is from -1 to +1

pearson’s correlation coefficient is only appropriate for measuring…

linear relationships

non-parametric alternative to pearson’s correlation

spearman’s correlation coefficient (spearman’s rho)

which non-parametric correlation test works well with small data sets that have lots of tied ranks

kendall’s tau