Research quiz 10

When the relationship between two variables is perfect and inverse, what is the value of r?

-1.00

Which is the stronger level of significance, 0.01 or 0.001?

0.001 is a stronger significance level.

You had a sample with six matched pairs of participants. One participant from each pair was randomly assigned to treatment A, and the other to treatment B. The participants' scores are listed below. Show how you would compute the sign test for these data. Treatment A Treatment B 56 62 50 52 53 49 48 54 57 61 51 59

If A is greater than B, put a + If A is less than B, put a - - - + - - -

What does it mean when a researcher reports that the probability for a statistic was p > 0.05

It means that the probability of error for the statistic is greater than 5 in 100, therefore the researchers concluded that the research is not statistically significant.

What does it mean when a researcher reports that the probability for a statistic was p < 0.01?

It means that the probability of error for the statistic is less than 1 in 100, causing the results to be statistically significant.

What nonparametric statistic can be used to test the difference between two groups when you have independent samples?

Mann-Whitney U statistic

What is the difference between a simple regression and a multiple regression?

Simple regression is similar to correlation except that one variable is the independent/predictor and the other is the dependent variable Multiple regression is a study of 2 or more independent variables to determine the strongest combination of variables for predicting outcomes.

For a Pearson r of 0.50, what is the value of the coefficient of determination? What does this coefficient mean?

The coefficient of determination is 0.25 the coefficient interprets the magnitude of importance of the correlation by squaring the Pearson r.

If you read that the value of a Pearson r is 0.45, p > 0.05, should you have confidence that this correlation represents the actual situation in the population? Why or why not?

The correlation is not significant because the probability of error is greater than 0.05.

Would you say that the following is statistically significant or not statistically significant? r=0.40, df=18, p=0.26

The critical r is 0.299, therefore this correlation is significant because the Pearson r is greater than the critical r.

Interpret the parts of the following one-way ANOVA statistic: F(2,43)=6.45, p < 0.05

The probability of error in concluding that there is a difference among the groups is low There were 2 groups with 43 errors in them with an f-ratio of 6.45 the results are significant

If you read the following, t(18)=1.38, p > 0.05, what conclusion would you make?

The results of the sample are not significant at the 0.05 level.

Is an r of -0.90 stronger than an r of 0.50? Explain.

an r of -0.90 is strong because it is higher than 0.50. the negative correlations are just as strong as the positive correlations, therefore the +/- do not matter when determining the strength of the correlation

What difference is tested for significance using a t-test?

analyzing the difference between two sets of data when you have interval or ratio level measures

Explain what is means when you have a significant interaction in an ANOVA analysis.

one or more of the group differences were significant, however you do not know exactly which group differences were the significant ones

If you are conducting a t-test on two scores from the same subjects, or scores from a matched sample, what kind of t-test will you use?

paired t-test

What are two reasons that you might select a nonparametric alternative to a t-test, such as the Wilcoxon signed rank test or the Mann-Whitney U test?

1. level of measurement was ordinal rather than an interval or ratio 2. small sample sizes

Identify three factors that affect whether or not the results of a t-test will be significant.

1. magnitude of difference between the means (larger = more significant). 2. amount of variability in the data (less variable = more significant) 3. sample size (larger = more significant)

If you have two random samples with 12 subjects in each, how many degrees of freedom do you have for the t-test?

22 add the number of participants from each group and subtract two pooled variance t-test because the groups have an equal number of participants

If you make an error of rejecting the null hypothesis when it is true, what type of error have you made?

Type 1 error