Stats/Research Flashcards
If a researcher has found heteroscedasticity in a scattergram, they have found that:
the variability (range) of scores on the criterion varies for different scores on the predictor; Heteroscedasticity means unequal variability. Heteroscedasticity occurs when the variability of scores on the criterion differs for different scores on the predictor (e.g., when there is a narrow range of criterion scores for low and high predictor scores but a wide range of criterion scores for moderate predictor scores)
Protocol analysis
Protocol analysis (also known as the “think aloud” technique) is used to identify the mental processes that occur during the solution of problems or the performance of tasks. Of the techniques listed, protocol analysis is the only one researchers use to study cognitive processes.
Event sampling
Event sampling is a behavioral observation and data collection technique that is useful when the behavior of interest occurs infrequently.
Situation sampling
Situation sampling is a behavioral observation and data collection technique that involves observing a behavior in a variety of situations.
A functional analysis is used…
A functional analysis is used to identify the functions of a behavior (i.e., the antecedents and consequences that maintain the behavior).
Mann-Whitney U test is used…
The Mann-Whitney U test is used when the analysis involves comparing rank-ordered data obtained from two independent samples.
When the relationship between the predictor (the X variable) and the criterion (the Y variable) is curvilinear and both variables are measured on an interval or ratio scale, the appropriate correlation coefficient is:
eta; Eta is used to measure the relationship between two continuous (interval or ratio) variables when their relationship is nonlinear. The choice of a correlation coefficient is based on several factors including the scale of measurement of the variables and the shape of the relationship between them (linear vs. non-linear).
The phi coefficient is appropriate when…
The phi coefficient is appropriate when both variables are true (natural) dichotomies.
Kendall’s tau is appropriate when
Kendall’s tau is appropriate when both variables are measured on an ordinal scale.
Rho (also known as the Spearman rank-order correlation coefficient) is used when…
Rho (also known as the Spearman rank-order correlation coefficient) is used when both variables are measured as ranks.
The standard error of the mean equation:
Knowing the formula for the standard error of the mean will help you identify the correct answer to this question. The standard error of the mean is equal to the population standard deviation divided by the square root of the sample size. As the population standard deviation increases and/or the sample size decreases, the standard error increases in magnitude.
What is autocorrelation and when is it a problem?
Autocorrelation refers to the correlation between measurements of the dependent variable when it is repeatedly administered to the same participants. Autocorrelation is a problem in repeated measures designs because it can artificially inflate the value of the inferential statistic, which will increase the probability of making a Type I error. Of the research designs listed in the answers, repeated measurement of the dependent variable is only characteristic of the time series design, which is a type of repeated measures (within subjects) design.
multicollinearity
The term “multicollinearity” is used to describe high correlations between predictors (X variables, independent variables).
The Spearman-Brown formula is used…
The Spearman-Brown formula is used to estimate the effects of increasing or decreasing the length of a test on its reliability coefficient
eigenvalues
associate with principal components analysis
