Forearm & Foot length?

1) Variables in our study were first defined, as shown below.

The 4 important readings that will be then used in our data analysis will be:

- average_1 (average of left forearm length)

- average_2 (average of right forearm length)

- average_3 (average of left foot length)

- average_4 (average of right foot length)

2) The data was then keyed in accordingly.

As can be seen, no data is missing, as most of the measurements were taken on the same day right after our common lecture (Refer to Details of Data Collection). However, for a smaller group of participants who had to attend other lessons, their measurements were taken by our group on another day.

We took 2 measurements each for the left and right forearms, as well as the left and right feet. The average of the two measurements are then calculated and later used for the data analysis.

Rationale:

'If we calculate the difference between each pair of measurements and find that the average different is 0, then we can infer that there is no systemic difference between the pairs of result i.e. on average, the duplicate readings agrees. If 1 set of reading represents the true values, as is likely in a method comparsion study, this means that there is no bias.'

3) We then proceeded on to choose a statistical test for the data analysis.

Statistical test chosen: Pearson's r

Rationale:

Our research question aims to find out if there is any association/relationship between 2 scale data

Scatter plots were then drawn to determine linearity of data

4)Scatter plot for left forearm and foot lengths:

5) Scatter plot for right forearm and foot lengths:

As seen above, both scattered plots generally showed a linear relationship between the variables.

6) Pearson's r (i.e. correlation coefficient) was generated via the SPSS.

Our findings for the left forearm and foot:

From the above, r=0.667, p<0.05,n=50

Therefore, the null hypothesis is rejected.

A Pearson's r of 0.667 indicates that there is a strong relationship between the left forearm length and left foot length.

Our findings for the right forearm and foot

From the above, r=0.720, p<0.05,n=50
Therefore, the null hypothesis is rejected.
A Pearson's r of 0.720 indicates that there is a strong relationship between the right forearm length and right foot length.

WE LOVE STATS.

Hello... testing 1 2 3

Null hypothesis
There is no relationship between length of foot and length of forearm (among the year 2 Occupational therapy students 2010).

Research hypothesis
There is a positive relationship between length of foot and length of forearm (among the year 2 Occupational therapy students 2010).

Conceptualization
Length of forearm is defined as the the distance between the elbow articular line (determined by the medial and lateral epicondyles of humerus), and the wrist articular line (determined by the styloid processes of radius and ulna)

Length of foot length is defined as the distance between the calcaneus and the tip of the big toe. (Unless subject has a longer second toe as compared to the big toes, length would be measured from the calcaneus to the second toe)

Operationalization
Length of both forearm and foot length is measured by measuring tape and a ruler to prevent parallax errors.

Dependent Variable
Scale Date - Length of foot (cm)

‘Foot length: maximum distance between the back of the heel to the tip of the longest toe'

Independent Variable
Scale Data – Length of forearm (cm)

‘forearm length: the elbow articular line (determined by the medial and lateral epicondyles of humerus), and the wrist articular line (determined by the styloid processes of radius and ulna) were taken as reference.’

Extraneous Variables
- Time of day
- Temperature
- Gender
- Age
- Race
- Religion
- Place
- Medical conditions (Edema, Pes planus)
- Medications, if any

Why did we ask for additional information?
With the additional data, it helps us in assess and having more confidence in the data. Furthermore, the conditions of participants may affect the data collected and affect the data reliability and accuracy. For example, a participant may have foot injuries that caused a discrepancy. Thus, it would help facilitate any data rejection that may occur in the process.

With the information, we can also check for trends across genders, courses and countries in the future if a more detailed study is conducted. This further enhances the importance of having a quality data.

Proportional stratified random sampling was used for our selection of subjects.
Select units in proportion to size of stratum
Cohort= 70 = 58f + 12 m
Therefore, f=82.8%, m=17.2%
With N=50,
F= 82.8% x 50 = 41
M= 17.2% x 50 = 9
Number of subjects needed: 50 (41 females and 9 males) out of 70 students in the entire cohort(58 females and 12 males)

Details of Data Collection
Date: 09/06/2010 (Wednesday)
Time: 1000 hours
Venue: School of Health Sciences (Block H, Level 5, Room H519 )
Our samples: 50 subjects - 41 girls and 9 guys randomly selected via the random number generator

Steps:
1.A namelist of the entire cohort was used as sampling frame.
2.This was then split into two groups according to their genders. (not shown here due to confidentiality)
3.Each person in the groups was then assigned a number in the lists respectively. E.g. 1 to 58 for the female list and 1 to 12 for the male list
4.An online application ‘random number generator’ was used to generate the required random numbers.
Website: http://www.psychicscience.org/random.aspx
5.Participants corresponding to the numbers generated were then chosen to make up our sample.
For the female list:

For the male list:

Note: The 'Unique Value' was selected when using the programme to prevent numbers from repeating (subjects cannot be repeated)

How was the collection done?
1.Before we began our data collection, each of us had a list of names that we needed to measure.
2.We spilt our subgroup into 3 groups. Each group was equipped with measuring tapes and rulers. Participants were then asked to approach any group for their measurements to be taken.
3.For each participant, measurements were taken twice for each forearm and foot. ( there was in a total of 8 measurements recorded for an individual)
4.After obtaining the measurements from all the participants, we collated the data into SPSS. In the event that some subjects had other lessons and could not be measure at that timing, they were measured when their lessons ended.

Based on our findings, we will reject the null hypothesis and conclude that there is a relationship between the forearm length and foot length in the Year 2 Occupational Therapy students (in 2010).

Reflections
Chalene
Through this project, I was able to learn more about the applications of SPSS which will definitely deem helpful for the ICA and future purposes. I was also being exposed to new experiences like collection of data from scratch which required each one of us to go around measuring the feet and forearm of others. The usage of blog to present our findings rather than through traditional presentation is also something new and fun. Finding appropriate literature was the toughest part of this project. In addition, it was hard to find time to meet due to other pressing datelines to be met. In a nutshell, it was really fun doing project with this group and I enjoyed the process of doing this project.

Meizhen
The most interesting part of the project is to collect data from our subjects, we had interactions with our subjects and it was fun. It was very intriguing to look at the raw data and wonder what will be analyzed out. The tedious part was to key in the data collected and other relevant data into SPSS. Other than that, there was a difficulty in finding literature to support our hypothesis, as we could not find any pilot study for the research topic we chose. Overall, this statistics project is a good experience in preparing for future research studies.

Shu Ling
This is my very first time actually collecting data from the start and keying them into a system (i.e. SPSS). It greatly differed from the sort of ‘studies’ that I have been exposed to in the past. Data collection took time, but it was nice to see the group work and dynamics in the process (especially when keying in the data). The process of statistical analysis really warmed me up to using SPSS as well. The use of the blog was fun (when trying to figure out the htmls and such) especially since I have never ever used blogger before. I do think this is a very useful and creative way for us to learn Statistics in a nonconventional (i.e. not boring hahahha!) manner.

Trevor
As I carried out this project, I realized that the most crucial part was gathering everyone to take the measurements in one place. Luckily, we had a free timeslot after lecture to carry it out, which was how we got everything done. The measurement process was a fun yet 'dirty' one as we had to measure people's feet. You cannot imagine the smell of some people's feet after they off their shoes. However, even with that setback, we were able to complete our job. The next part that I enjoyed, was keying in the data into SPSS. Although it was tedious, I felt a sense of achievement when everything was keyed in and the graph was produced. The time when I felt most inadequate was during the blog creation. I had no idea about how to write my own blog, so I was not able to contribute much to the group's blog. I'd be sure to learn some basics about it in the future!

Yanling
It was very interesting collecting raw data and wonder what the results will show. There was a lot of team work as we all worked towards a common goal. I also liked displaying the results through a blog as it is very different from other modules. It was exciting to design the blog and to know that it is real supported information that we are posting up on the internet where everyone from all over the world can assess to it.

Group reflection
Overall, we have all learnt from this project and module and we are glad to have been a part of this project. It was fun, allowed us to put the SPSS to use, problem-solve and work as a group. Of course, we would like to thank Ms. Chia for everything as well, because Statistics was truly made less boring in this module and style of teaching :D

ALVES, N.; CÂNDIDO P. L. & FRAZÃO, R. (2004) Innervation of the Pronator quadratus muscle. Last retrieved on 29 June 2010 from http://www.scielo.cl/pdf/ijmorphol/v22n4/art02.pdf

Bridger, R.S. (2003). Introduction to ergonomics. (2nd ed). p.62. London: McGraw-Hill, Inc.

Kon, H.B., Madnick, H.B. and Wong. R.Y. (1992) Data Quality Requirement Analysis and Modelling. Vienna, Austria: Ninth international conference of Data engineering

Maltais, R., (2007). Data collection and statistics provide important information. Last retrieved on 29 June 2010 from http://worldvillage.com/data-collection-and-statistics-provide-important-information

Moses. A., (2004) Accurate demographic data needed. Last retrieved on 29 June 2010 from http://www.equip123.net/docs/e2-DemoData_PolicyBrief.pdf

Petrie, A. & Sabin, C. (2009). Medical Statistic at a Glance. (3rd Ed). p.119. Oxford: Blackwell Publishing

Layout by : Tainted kisses. Background from : Fivepointsapart Basecodes from : hasta_mañana Graphics from : TouchtheVelvetsky Mini Icons : Famfamfam / Inspired by Cia