Term
| A Type l error can be prevented by |
|
Definition
| setting the alpha level low enough. |
|
|
Term
| A Type l error is committed by |
|
Definition
| rejecting the null hypothesis; finding a difference when there is no difference. |
|
|
Term
| A Type ll error is committed by |
|
Definition
| accepting the null hypothesis when it should be rejected; there is a difference. |
|
|
Term
| A Type ll error can be prevented by |
|
Definition
| getting a large a size of samples as possible. |
|
|
Term
| A statistically significant difference occurs |
|
Definition
| when the calculated value from the statistical test that you have used in analyzing the differences is greater than the critical value obtained for a table of probability values from your statistical test. |
|
|
Term
|
Definition
| a number determined by the alpha the level you select and the number of degrees of freedom you have in your data |
|
|
Term
| When the calculated value is larger than the critical value you can |
|
Definition
| reject the null and accept the alternative hypothesis that the means of the two groups are not similar or equal to zero. |
|
|
Term
| When selecting a two-tailed test, you need to have |
|
Definition
| a greater difference between the two sets of data than with a one-tailed test in order to find the significant difference. |
|
|
Term
| The one tailed test will have a lower value for |
|
Definition
| critical value for the same alpha level than a two-tailed test of significance. |
|
|
Term
| Before you analyze the data, you need to set the |
|
Definition
| alpha level and develop a directional or non directional alternative hypothesis. |
|
|
Term
| If you only have two groups of data (behaviors from two types of people) you can analyze whether there are difference between the groups by using a |
|
Definition
|
|
Term
| An independent t-test is used when the two groups of data are |
|
Definition
| unrelated in some way, like men vs. women or Nebraska vs. Iowa. |
|
|
Term
| Differences between two unrelated groups of people are considered |
|
Definition
| independent and are analyzed differently than if they were related samples of data. |
|
|
Term
| A dependent t-test is used when the two groups of data are |
|
Definition
| related in some way. E.g. men 20-25 years of age compared to women 20-25 years of age. |
|
|
Term
| If two groups of data came from the same person, what kind of a statistical test would you use? |
|
Definition
|
|
Term
| What statistical test would you use for two groups of data for pre and post test measures, or before vs. after treatment? |
|
Definition
|
|
Term
| If you have more than two groups of data, you need to use a more sophisticated type of statistical analysis called |
|
Definition
| the Analysis of Variance or ANOVA. |
|
|
Term
| The ANOVA allows one to calculate |
|
Definition
| differences between and among groups. |
|
|
Term
|
Definition
| one-way or one factor, two-way or two factors, or three-way or three factors. |
|
|
Term
|
Definition
| are the main effect that is being tested in an ANOVA. |
|
|
Term
| You have 1, 2 or 3 main factors in |
|
Definition
| an ANOVA that you want to calculate to determine differences between the groups. |
|
|
Term
| Statistical test for color preference for cars, trucks and SUVs would be |
|
Definition
|
|
Term
| A statistical test for high school vs. middle school students’ ratings for three types of video games would be |
|
Definition
|
|
Term
| You determine the degree of freedom for independent samples or t-tests by |
|
Definition
| adding the number in each group and subtracting one from each group; eg if there are 20 people in each group for a total of 40 the df is 38. |
|
|
Term
| In independent samples for t-tests the number of subjects in the groups can be |
|
Definition
|
|
Term
|
Definition
|
|
Term
|
Definition
|
|
Term
| What type of t-test do you use when you have two measures from the same subjects or when subjects are matched according to some variables? |
|
Definition
|
|
Term
| In a dependent t-test, the degrees of freedom are related to |
|
Definition
| the one pair of scores that is not free to vary. |
|
|
Term
| You determine the degree of freedom for dependent samples or dependent t-tests by |
|
Definition
| one less the number of pairs of scores; eg, if there are 20 in each group there are 20 scores so the df is 19 |
|
|
Term
| In dependent samples for t-tests the number of subjects in the groups must be |
|
Definition
|
|
Term
| Examples of interval data are |
|
Definition
| attitude, ability, personality, intelligence, achievement tests, language tests, hearing thresholds |
|
|
Term
|
Definition
| frequency counts, time and distance measures, latency of responses |
|
|
Term
| In data analysis, the type of data dictate |
|
Definition
| the type of analysis that can be performed. |
|
|
Term
| Data scales are also known as levels of |
|
Definition
|
|
Term
|
Definition
| assigning a name or category to each item. |
|
|
Term
| Examples of nominal data are |
|
Definition
| =/- data, yes/no responses, normal/disordered, type of hearing loss, speech disorder, income levels, age groups, other demographic data |
|
|
Term
| Examples of ordinal data are |
|
Definition
| severity ratings, ratings or rankings by subject or others, voice quality ratings, levels of linguistic complexity |
|
|
Term
| In a two-way ANOVA there are two |
|
Definition
| independent variables (hence the name two-way). |
|
|
Term
| How many sets of hypothesis are there with the two-way ANOVA? |
|
Definition
|
|
Term
| The two independent variables in a two-way ANOVA are called |
|
Definition
| factors (denoted by A and B). The idea is that there are two variables, factors, which affect the dependent variable (Y). Each factor will have two or more levels within it, and the degrees of freedom for each factor is one less than the number of levels. |
|
|
Term
| The interaction effect is |
|
Definition
| the effect that one factor has on the other factor. The degree of freedom here is the product of the two degrees of freedom for each factor. |
|
|
Term
| There is an F-test for each of the |
|
Definition
|
|
Term
| Assumptions of parametric tests are: |
|
Definition
A. Scores are normally distributed
B. Sample size is reasonably large
C Interval or ration data are used
D. There is homogeniety of variance among groups of data
E. Subjects have been randomly sampled. |
|
|
Term
| Assumptions of Nonparametric tests are |
|
Definition
A. Distribution free meaning distribution of scores does not fit the normal distribution pattern.
B. Sample size can be quite small.
C. Nominal or ordinal data can be used.
D. Lack of homogeniety; eg., two groups of data have large differences in variance
E. Subjects are selected using convenience or quota sampling |
|
|
Term
| The alternative hypothesis is the |
|
Definition
| hypothesis that is accepted when you reject the null hypothesis. |
|
|
Term
| Use of parametric and nonparametric allow reseachers to |
|
Definition
| make inferences about the population from the sample data. |
|
|
Term
| The one-way analysis of variance (ANOVA) is used to determine whether there are any significant differences between |
|
Definition
| the means of three or more independent (unrelated) groups. |
|
|
Term
| A one-way ANOVA is an omnibus test statistic and cannot tell you which specific groups were |
|
Definition
| significantly different from each other, only that at least two groups were. To determine which specific groups differed from each other, you need to use a post-hoc test. |
|
|
Term
Why not compare groups with multiple t-tests instead of a one-way ANOVA?
Every time you conduct a t-test there is a chance that you will make a Type 1 error. |
|
Definition
| Every time you conduct a t-test there is a chance that you will make a Type 1 error. Better to miss a result than to conclude there is a meaningful difference. |
|
|
Term
| The t-test is only appropriate for situations where there are only |
|
Definition
| two levels of one independent variable. |
|
|
Term
| We use the term two-way or two-factor ANOVA,when the levels of |
|
Definition
two different explanatory variables are being assigned, and each
subject is assigned to one level of
each factor. |
|
|
Term
| The ANOVA statistic is called the |
|
Definition
| F-test, after its developer, Fisher. |
|
|
Term
| Like the t, F depends on degrees of freedom to determine probabilities and critical values, but there is a difference between t and F in terms of the degrees of freedom concept. F has |
|
Definition
| two different degrees of freedom to calculate. In contrast, t has only one formula for calculating degrees of freedom. |
|
|
Term
| F-score or F-measure is a measure of a |
|
Definition
|
|
Term
| The assumption of homogeneity of variance is that the variance |
|
Definition
within each of the populations is equal.
This is an assumption of analysis of variance (ANOVA). |
|
|
Term
| How will the alternative hypothesis chosen affect the critical values associated with t-test? |
|
Definition
| Because it raises or lowers the critical value according to whether it is nondirectional or directional. |
|
|
Term
| Which is a more serious error? Type l or Type ll? |
|
Definition
| Type l, because you used too high an alpha level. |
|
|
Term
|
Definition
independent
variable (1 factor) with 2
conditions
– conditions = levels = treatments
– e.g., for a brand of cola
factor, the levels are:
• Coke, Pepsi, RC Cola |
|
|
Term
|
Definition
independent variables (factors)
– each can have multiple conditions. |
|
|
Term
| We conduct Post-hoc Tests if |
|
Definition
the ANOVA is significant–
at least one significant difference between conditions |
|
|
