PCC GROUP RESEARCHES

PCC GROUP RESEARCHES  

PCC group ask me to show some statistical formula to their research and some of them are theoretical so I opted to have some research review on some of their formula and the formula are as follows mean, percentage, and the one way anova or one way classification of anova .  I learned from the group of students of PCC they are a critical thinker, which is great, or maybe they are anxious and worried about their oral defense and they needed to be precise and accurate because the panels are from the elite.

First is the percentage n/N x 100 where n is the sample and N is the total number of sample for example 

	Frequency		Percent
	Male	52	35.6
	Female	94	64.4
	Total	146	100.0

For male n = 52 N= 146 so percentage is (52/146) * 100= 35.6

Now for the mean of grouped data: Ug =  however, the data used in the study of the PCC students is ungrouped mean, which the formula is as follows:

For example

Factors	Sum	Mean
Overpopulation	295.00/n	2.0205
Low Demand	486.00/n	3.3288
Termination	487.00/n	3.3356
Low Salary	507.00/n	3.4726
Unable to Pass	559.00/n	3.8288
Heath Hazard	721.00/n	4.9384

Example let fi= 4 or you have 4 total sample

Moreover, their perception tabled as follows

	overpopulation	Low demand	termination	Low salary	Unable to pass	Health hazard
Student 1	1	2	3	5	4	6
Student 2	2	6	5	1	3	2
Student 3	6	5	4	3	2	1
Student 4	1	2	3	4	5	6
sum	10	15	15	13	14	15
mean	10/4	15/4	15/4	13/4	14/4	15/4

                       The analysis of variance is an extension or generalization of the difference of means test. The technique is used several means, however the test itself involve directly with the variance rather than means and standard errors.

                       The one-way anova classification, two component of variation are estimated for example the data PCC nursing students in identifying if those living or not living with their family have significant difference in terms of the indicators of eating habit. The data is as follows:

Indicator	Living in the Family	WT Mean	F.	P
1. Plans daily activity	Yes No	3.3 3.28	.013	.908 ns
2. Finds time to cook nutritious food	Yes No	3.44 3.21	1.568	.212 ns
3. Allocates Time to buy Food	Yes No	3.39 3.33	.070	.792 ns
4. Share Household Chores with house mates	Yes No	3.60 3.51	0.201	.654 ns
5. Acquiring skills in Preparing and Cooking	Yes No	3.50 3.51	.005	.941 ns

                       The variations are the indicator of the students and the other variation is if the student is living or living away with his or her family. Then the ratio of these estimates computed. If the null hypothesis is correct then this ratio approaches unity but is the difference is entirely different, and then the ratio tends to be large. The ratio of the two variances denotes F knows a test statistics as the F-test.

The estimation of sum of squares is as follows

a.)                             Correction factor (CF) CF= (1/n)(x..)²

b.)                            Total sum of Squares (TSS) TSS= ƸƸXij² – CF

c.)                             Treatment Sum of Squares (TRSS) TRSS= Ƹ(Xi² /ni) – CF or Between Group Sum of Squares

d.)                             Within group sum of squares ESS = TSS – TRSS or Within Group Some of Squares

e.)                             F = Mean Square Between group/Mean Square Within Group from the output or

F  =  ( TRSS/(t-1)) / ( ESS/ (n-t)

                                               ANOVA output

 

 

		Sum of Squares	df	Mean Square	F	Sig.
Plans daily activity	Between Groups	.016	1	.016	.013	.908
	Within Groups	192.591	156	1.235
	Total	192.608	157

So let us take the test if there is a significance of those living and living away with their family The TSS or Total sum of squares is 192.61

TRSS or Between Group Sum of Squares = .016

ESS or Within Group Some of Squares = 192.591

For for computation of the F value is

a.)                             F = Mean Square Between group/Mean Square Within Group from the output or

F = (TRSS/ (t-1)) / (ESS/ (n-t) = .016/1.235 = .013

Take note in your study we set the value of critical region is .05  and the program automatically compute the significant value or the P value thus any value within or lower than .05 is a significant one and any value higher than .05 is a not significant.

The Pvalue or calculated probability is the estimated probability of rejecting the null hypothesis (H0) of a study question when that hypothesis is true.

As a rule in the ideal world, we would be able to define a "perfectly" random sample, the most appropriate test and one definitive conclusion. We simply cannot. What we can do is try to optimize all stages of our research to minimize sources of uncertainty. When presenting P values some groups find it helpful to use the asterisk rating system as well as quoting the P value:

P < 0.05 *
P < 0.01 **
P < 0.001

Most authors refer to statistically significant as P < 0.05 and statistically highly significant as P < 0.001 (less than one in a thousand chance of being wrong). So in your research we do same.

The asterisk system avoids the woolly term "significant". Please note, however, that many statisticians do not like the asterisk rating system when it used without showing P values. As a rule of thumb, if you can quote an exact P value then do. You might also want to refer to a quoted exact P value as an asterisk in text narrative or tables of contrasts elsewhere in a report.

Mind you computing the F test manually would take no less than 3 session of regular lecture so the computation are being deducted and the results are being obtained automatically. The data are being done from statistical software, which is design to compute the needed test.

For the other group who have significant difference per region and region 3 is the significant one and the post hoc test used is Fisher LSD.  The Fisher LSD test stands for the Least Significant Difference test (rather than what you might have guessed).   The LSD test is simply the rationale that if an omnibus test is conducted and is significant, the null hypothesis is incorrect. (If the omnibus test is non significant, no post hoc tests are conducted.) The reasoning is based on the assumption that if the null hypothesis is incorrect, as indicated by a significant omnibus F-test, Type I errors are not really possible (or less likely), because they only occur when the null is true. So, by conducting an omnibus test first, one is screening out group differences that exist due to sampling error, and thus reducing the likelihood that a Type I error is present among the means.  Fishers LSD test has been criticized for not sufficiently controlling for Type I error.