An extended examination ANalysis Of VAriance ANOVA provides an inferential statistical test to

compare the means of 2 or more independent groups

on the dependent variable. Basically, we will be able to determine if any of several means is different from each other. What is ANOVA? One-way (single factor) and two-way (factorial) ANOVA allow for the comparison of the means of 2 or more groups, therefore these tests help us to avoid committing statistical sin, or the increased chance of type 1 error attributed to doing multiple t-tests. The 2 Types of ANOVA and Why

we need them... 1. Observations are independent

2. Variance on dependent variable are equal across groups

3. Dependent variable is normally distributed for each group Assumptions of the ANOVA The output consists of 6 major sections. Interpreting SPSS Test Output:

Getting Personal with your Single Factor ANOVA Data 1. Descriptive Table: provides the sample size, mean, standard deviation, minimum, maximum, standard error, and confidence interval for each level of the independent variable

2. Test of Homogeneity of Variances: the column labeled Sig. is the p value. If the p value < α level for this test, then you can reject the H0 that the variances are equal. If the p value > α level for this test, then we fail to reject H0, thus increasing our confidence that the variances are equal (the homogeneity of variance assumption has been met). 3. ANOVA table: 6 columns provide (1) unlabeled source of variance, (2) Sum of Squares, (3) Degrees of Freedom, (4) Mean Squares/ estimates of variance, (5) F ratio, and (6) Sig. of F ratio/ p value 4. The Multiple Comparisons output gives the results of the Post-Hoc tests that you requested from SPSS. We will be using the Tukey HSD and Games-Howell tests. When the F ratio is statistically significant, we need to look at the multiple comparisons output. The output includes a separate row for each level of the independent variable. 5. Summary table for Multiple Comparisons tests 6. The final part of the SPSS output is a graph showing the dependent variable on the Y axis and the independent variable on the X axis Types of error: type 1 vs type 2

Possible sources of error To err is human: possible error in ANOVA Type 1 is a false positive error -a null hypothesis is true but has been wrongly rejected.

Type II is a false negative error -a null hypothesis is false yet fails to be rejected You're all humans -Can anyone supply a possible source of error?!? Formal Features in Children’s Science Television:

Sound Effects, Visual Pace, and Topic Shifts

Boiarsky, G., Long, M., & Thayer, G. (1999) Article 1 Discussion Certain formal features reliably draw

children’s attention to the TV screen

e.g. sound-effects, women’s voices, animation, and rapid

pace. The driving concept behind the research was

that formal features, or non-content elements of

the program, influence a child’s attention to a

program Increased attention to the screen is associated

with learning of program content

The more attention children pay to the

screen, the more they learn

The presence of some formal features can

enhance learning

Certain features can also interfere with the

learning experience Education and Formal Features Rapid presentation of information seems to

degrade learning

Rapid visual or auditory change can increase

attention to the program Interference

Children’s entertainment programs presented

formal features designed to gain attention

(rapid action, music, and visual change)

Children’s education programs presented

many features designed to encourage

thoughtful processing of content (long zooms,

moderate action, and singing) Entertainment vs. Education Do educational programs still present

formal features that encourage thoughtful

processing?

HO: The use of formal features in children’s

educational programming has not changed

from 1981 to 1995.

HA: The use of formal features in children’s

educational programming has changed from

1981 to 1995. Hypotheses 4 half-hour programs were analyzed (chosen

to capture the diversity in science education

programs today) and compared against the

findings from Huston et al. (1981)

Bill Nye The Science Guy

Magic School Bus

Newton’s Apple

Beakman’s World Method 12 episodes of each program from the 1995-1996 season were analyzed

Program characteristics coded in the study

- Number of topic shifts

- Sound effects

- Visual pacing One-Way Within Subjects ANOVA was used

to analyze the findings

The independent variable was the television

program

The dependent variables were the Sound

Effects per Minute, Cuts per Minute, Fades/

Dissolves per Minute, Wipes per Minute, and

Topic Shifts per Episode ANOVA Table 1

Average Number of Formal Features per Episode

by Program In general the programs in this study were fast

paced; they used frequent sound effects,

cuts, and switched topics quite

rapidly.

Sound Effects Pacing

• On average, the programs used more than 19

sound effects per minute

• There were significant differences among the

programs (F(3,46) = 80.42, p < .05).

Visual Pacing

• While cuts were the most used visual-pacing

effect across all programs, the programs differed

significantly in the number of cuts per minute

(F(3,46) = 24.96, p < .05)

• While fades/dissolves were used sparingly in the

4 programs, averaging just under 1 fade/dissolve

per minute, their use did differ significantly by

program (F(3,46)=3.46, p<.05)

• The programs also differed significantly in the

number of wipes per minute (F(3,46)=3.05, p<.05)

Content Pacing

• The number of content shifts was significant

between programs (F(3,46)= 34.55, p<.05) Results Why did the ANOVA fit their data? Discuss: Why ANOVA? Healthcare reform information- seeking: Relationships with uncertainty, uncertainty discrepancy, and health self-efficacy

Nasim Mirkiani Thompson, Jennifer L Bevan, Lisa Sparks Article 2 Discussion The study examines information- seeking about the 2010 Patient Protection and Affordable Care Act (i.e. healthcare reform) in relation to the potential barriers of uncertainty, uncertainty discrepancy, and low health self-efficacy. Hypotheses H1: Information-seeking is positively related to degree of uncertainty about healthcare reform.

H2: Information-seeking is positively related to uncertainty discrepancy about healthcare reform.

H3: Individuals’ health self-efficacy is posi- tively related to information-seeking about healthcare reform. Participants 18 years or older completed an online survey.

Researchers then measured information-seeking, Uncertainty, uncertainty discrepancy, and health self-efficacy. Method Researchers performed a series of univariate analysis of variances then tested the categorical health insurance and healthcare reform variables in association with their variables of interest.

Take a look at Table 2! ANOVA Their goal was to determine which potential barrier accounted for increased variance in health- care reform information-seeking. Indeed, after interpreting the ANOVA results they determined that uncertainty discrepancy was the only significant predictor, and thus accounted for the most information- seeking variance. Did ANOVA lead the researchers to their desired target information? Your turn! Prepubescent children may oxidize fat more

readily than adults. Therefore, dietary fat

needs would be higher for children compared

with adults. The dietary fat recommendations

are higher for children 4 to 18 yrs (i.e., 25 to

35% of energy) compared with adults (i.e., 20

to 35% of energy).

Can we design a study that makes use of the ANOVA? 10 children and 10 adults were fed a weight

maintenance diet for three days

Metabolic rate was measured three times

before and immediately after breakfast

and for 9 hrs using a hood system (twice) or

a room calorimeter (once) State your Variables

Write Hypotheses!

Please and Thank You...

We got y'all some data. Would ANOVA have any value in our study of exercise and the workplace?

Could you give an example Brooke? Now let's apply the ANOVA to our study!

### Present Remotely

Send the link below via email or IM

CopyPresent to your audience

Start remote presentation- Invited audience members
**will follow you**as you navigate and present - People invited to a presentation
**do not need a Prezi account** - This link expires
**10 minutes**after you close the presentation - A maximum of
**30 users**can follow your presentation - Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

### Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.

You can change this under Settings & Account at any time.

# ANalysis Of VAriance

A statistical adventure guided by Laurel and Savannah

by

Tweet