BF[1]
Design Principals
Visualization & Miscellanea
Formal ANOVA
Fisher Assumptions
100

These are the two universal factors in the BF[1] design?

What are the benchmark and residuals?

100

This technique converts potentially systematic variability to chance like variability by distributing differences in experimental material across conditions.

What is randomization?

100

This plot depicts all observations as points and maps the levels of the treatment factor along with x axis.

What is a parallel dot graph?

100

This is a table with a design's universal and structural factors in listed in the rows and the SS, df, MS, and F-ratio quantities in the columns.

What is an ANOVA table?

100

These are the letters in the acronym CA-SINZ that correspond to assumptions about model residuals. 

What are SINZ?

200

This is the degrees of freedom for the treatment factor if the design has 5 levels.

What is 4? 

200

When every level of factor A is present with every level of factor B to create treatment combinations.

What is factorial crossing?

200

This popular visualization is an alternative to the parallel dot graph that does not show individual observations. 

What are side-by-side boxplots?

200

If I had all of the SS's and the df's, how could I fill in the MS's in the ANOVA table?

What is, by dividing the SS by the df?

200

If the standard deviation of the largest treatment group is >3 times as large as the standard deviation of the smallest treatment group, we should consider doing this. 

What is transform the response variable?

300

A factor diagram for the BF[1] whose structural factor has 3 levels. 

What is this: [picture on board]?

300

One way of blocking is by creating similar groups of experimental materials, this is another way.

What is by reusing experimental material?

300

These two Fisher assumptions are both checkable with side-by-side boxplots. 

What are the S and N assumptions?

300
The most likely F-ratio value when the null hypothesis is true. 

What is 1?

300

This Fisher assumption holds that observations within the same treatment condition are measurements of the same true value.

What is (C) constant treatment effects?

400

The formula for calculating the residual degrees of freedom in the BF[1] design. 

What is N - a, where a is the number of treatment levels?

400

This is a design with blocking present, but only a within blocks treatment factor and no between blocks treatment factor.

What is complete block, or CB[1], design?

400

A numeric measurement scale, with no true zero point, where we assume that distances between pairs of adjacent points are measuring the same amount of the construct. 

What is the interval level of measurement?

400

In the SP/RM[1,1] design, this is the denominator for the F-ratio that tests for variability in effects due to the between blocks treatment factor. 

What is the MS for the blocking factor?

400

What proportion of residuals should be within one standard deviation of zero in order for the N assumption to hold?

What is about 2/3rds?

500

If experimental materials were reused such that each unit was measured once for each level of the treatment factor (creating time slots), the BF[1] design becomes this design. 

What is the complete block, CB[1], design?

500

These design principals are present in the split plot/repeated measures design where the between block factor is experimental.

What are randomization, blocking, and factorial crossing?

500

When the effect of one factor is different across levels of another factor.

What is an interaction effect?

500

This is the second parameter that gives the F-distribution its shape under the null hypothesis. 

What is the denominator degrees of freedom? (or error df)

500

This data visualization will help me check for independence in my residuals if I have a within block treatment factor that has two levels.

What is a scatterplot?