In: Statistics and Probability
Restate the question that the researcher is investigating?
What type of test is appropriate for this question?
Write out the model statements in words (make sure you include null model too)
What are the hypotheses (all of them)
Run the appropriate statistical test in Minitab (for this example you do not need to check for normality, variance, outliers etc, just run the test). Paste the output here. Paste it so it is easy to read.
Run a post-hoc test if appropriate. Paste results here as appropriate.
Summarize what the results are telling you. What is the take home message that you want to tell your audience. (I am not requiring a final graph for this assignment)
Salary course Subject
1700 Humanities
1900 Humanities
1800 Humanities
2100 Humanities
2500 Humanities
2700 Humanities
2900 Humanities
2500 Humanities
2600 Humanities
2800 Humanities
2700 Humanities
2900 Humanities
2500 Social Sciences
2300 Social Sciences
2600 Social Sciences
2400 Social Sciences
2700 Social Sciences
2400 Social Sciences
2600 Social Sciences
2400 Social Sciences
2500 Social Sciences
3500 Social Sciences
3300 Social Sciences
3600 Social Sciences
3400 Social Sciences
2700 Engineering
2800 Engineering
2900 Engineering
3000 Engineering
2800 Engineering
2700 Engineering
3700 Engineering
3600 Engineering
3700 Engineering
3800 Engineering
3900 Engineering
2500 Managament
2600 Managament
2300 Managament
2800 Managament
3300 Managament
3400 Managament
3300 Managament
3500 Managament
3600 Managament
Restate the question that the researcher is investigating ?
Answer : researcher wants to test or to find there is mean difference between treatments, it is significant or not
that is treatments are significant or not here treatments are subject.
## Q ) What type of test is appropriate for this question ?
we can use ANOVA test : and find out treatments are significant or not here treatetmes are subject .
also find out which treatment is different .
## Q ) Write out the model statement in words : Yij = u + α i+ error
Ho : all treatments mean are same (null hypothesis ) vs H1 : at least one mean is differ for treatment.
Yij = u + α i+ error ( model )
where u is overall mean , alpha is treatments .
## Q) what are the hypothesis :
Ho : null hypothesis : all treatments means are equal vs
H1 : alternative hypothesis : at least one mean is differ
## Q ) Run the appropriate statistical test in Minitab Paste the output here. Paste it so it is easy to read.
Answer : paste here output of the minitab:
One-way ANOVA: salary cource versus Subject
Method
Null hypothesis All means are equal
Alternative hypothesis At least one mean is different
Significance level α = 0.05
Equal variances were assumed for the analysis.
Factor Information
Factor Levels Values
Subject 4 Engineering, Humanities, Managament, Social Sciences
Analysis of Variance
Source DF Adj SS Adj MS F-Value P-Value
Subject 3 4167567 1389189 6.23 0.001
Error 41 9144878 223046
Total 44 13312444
### from anova p value is less than alpha value hence we reject Ho ( using p value appraoch)
we can say that there is enough or sufficient evidence to conclude that there is atleast one treatment is differ .
that is atleast one subject mean is differ
Model Summary
S R-sq R-sq(adj) R-sq(pred)
472.277 31.31% 26.28% 17.15%
Means
Subject N Mean StDev 95% CI
Engineering 11 3236 495 (2949, 3524)
Humanities 12 2425 435 (2150, 2700)
Managament 9 3033 485 (2715, 3351)
Social Sciences 13 2785 478 (2520, 3049)
Pooled StDev = 472.277
## Q ) Run a post hoc test if appropriate . Paste results here as approapriate
answer : post hoc test is valid only if we have reject Ho : by using it we can find which treatment mean is differ .
here post hoc test is valid because we reject Ho .
Tukey Pairwise Comparisons
Grouping Information Using the Tukey Method and 95% Confidence
Subject N Mean Grouping
Engineering 11 3236 A
Managament 9 3033 A
Social Sciences 13 2785 A B
Humanities 12 2425 B
Means that do not share a letter are significantly different.
Tukey Simultaneous Tests for Differences of
Means
Difference SE of Adjusted
Difference of Levels of Means Difference 95% CI T-Value
P-Value
Humanities - Engineering -811 197 (-1340, -283) -4.12 0.001
Managament - Engineering -203 212 ( -772, 366) -0.96
0.775
Social Scien - Engineering -452 193 ( -970, 67) -2.33 0.107
Managament - Humanities 608 208 ( 50, 1166) 2.92 0.028
Social Scien - Humanities 360 189 ( -147, 866) 1.90
0.243
Social Scien - Managament -249 205 ( -798, 300) -1.21
0.621
Individual confidence level = 98.94%
using p value appraoch result is not significant if p value is less than alpha value here
using p value approach . Humanities - Engineering ,and Managament - Humanities mean pair is significant out of all .
## Q ) Summarize what the results are telling you . What is the take home mesasge that you want to tell your audience .
Answer : first from anova reuslt is significant and there is at least one treatment mean is differ .
use post hoc test ( Tukeys comparison test and find which one is differ )
overall we can say that subjects ( tramtments ) have different with salary course .and
Humanities - Engineering ,and Managament - Humanities mean pair is significant out of all .