The trouble with statistics is that even when you think you have the right one the data doesn't want to play ball! Correlation was productive but has not revealed anything too startling. There are some average correlations but nothing particularly strong that could not be anticipated. So the last couple of weeks have been investigating other techniques.
The one I am now looking at using is cluster analysis. This is because what I really want to know is how different variables gravitate towards each other. With this I can look at the individual students to get a better and more grounded picture. The problem has been that the data has to be in the right format to use cluster analysis in SPSS so I have have to amend the data to get it to work. Unfortunately the online help from SPSS is only partially helpful so thank goodness for the internet where others who have passed this way have posted their procedures.
It is all very frustrating at times as I don't really want to get deeply involved with advanced stats methods but that is the price I have to pay for not designing a simple investigation using basic techniques! Hopefully in a week or so I will have some facts to work with. I'd better as I have to present initial findings at a workshop in two weeks time with some of our tutors!
No rest for the wicked.
Monday, 25 August 2008
Thursday, 7 August 2008
The Right Statistic
Another two weeks on and progress has been made but frustratingly so. The latest questionnaire went out to the 41 tracking sample of students on 21st July with the request for them to be completed by 1 August. The date came and only 24 had responded, however, an email reminder to those who had not completed has now yielded 37 responses with a further one likely when the student returns from holiday.
That is the progress so what is the frustration. Needless to say that is the statistics. My intention of using ANOVA was scuppered once I started to look more closely at the detail. Originally I had a mix of free and categorised data. When I looked again at the frequencies I realised that the free data had a very wide range with some extreme outliers. As most of the data is already presented in categories (ie 1, 2, 3 etc) I took the decision to convert all the data into this form. This is now done but again valuable time has been used.
Now that I only have data in categories the next frustration was realising that simple ANOVA is not suited to this as there are no figures to provide means. So which statistic to use? Rather than follow trial and error I have spent over a week re-reading the statistics books to refresh the bonce! What I am interested in is the relationship between variables to see where further investigation is needed. Correlation will provide this, but thereby results another frustration - there are different methods of determining this in SPSS! The method most suited to my categorised data is Spearman's rho correlation. I have now started to put the data through this but the SPSS output is immense. Consequently I am taking it into Excel so that I can both process and sort it but also to condense it for printing out! It may be that I will convert some data back to values at some point but at the moment I have plenty to do.
That is the progress so what is the frustration. Needless to say that is the statistics. My intention of using ANOVA was scuppered once I started to look more closely at the detail. Originally I had a mix of free and categorised data. When I looked again at the frequencies I realised that the free data had a very wide range with some extreme outliers. As most of the data is already presented in categories (ie 1, 2, 3 etc) I took the decision to convert all the data into this form. This is now done but again valuable time has been used.
Now that I only have data in categories the next frustration was realising that simple ANOVA is not suited to this as there are no figures to provide means. So which statistic to use? Rather than follow trial and error I have spent over a week re-reading the statistics books to refresh the bonce! What I am interested in is the relationship between variables to see where further investigation is needed. Correlation will provide this, but thereby results another frustration - there are different methods of determining this in SPSS! The method most suited to my categorised data is Spearman's rho correlation. I have now started to put the data through this but the SPSS output is immense. Consequently I am taking it into Excel so that I can both process and sort it but also to condense it for printing out! It may be that I will convert some data back to values at some point but at the moment I have plenty to do.
Monday, 21 July 2008
A Moment for Optimism
Apologies if it appears that all I have to write about is getting the data into SPSS but it has taken nearly all my spare time! Two weeks ago I attended my son's graduation at the Bridgewater Hall in Manchester. It was a very proud occassion that I thoroughly enjoyed - but of course interrupted my time for working on the thesis.
Last week I attended the Pan Commonwealth Forum which was held at IOE. Apart from hearing a lot of interesting talks and presentations worthy of the international education taught module, and catching up with a number of friends and acquaintances, it also gave me an opportunity to check my data and to see my supervisor. All seems well on all fronts so I progress!
I said 'nearly all my time' as I have also created the latest questionnaire for the longitudinal time study. In this one I am repeating some questions but have reframed others to ask about the effect of work, domestic, personal problems on the time available. I am also interested to find out whether students have settled into a pattern of weekly study that enables them to 'protect' time ie hours when they are definately studying and which are ring fenced against interuption or interference. I have sent this to the 41 students who answered my previous questionnaire and already 6 have responded. I anticipate that the number completing will drop off with each new questionnaire so hope that I started with enough to see the study through!
Last Thursday we had about 200 students come to a face to face workshop in Reading which gave me the chance to talk to some in the breaks. They are interested in the outcomes and I have been able to use some of their comments to frame the latest set of questions. Of course another questionnaire means yet more data but as the saying goes 'you can never have too much data'!!
This week my aim is to start the analysis of the data in earnest. My plan is to use one-way ANOVA to identify where there is significant variance in the data and then to use this to review the printed profiles. Currently I have 323 variables (not all of which I intend using!) and will pick off the main areas likely to impact on time in clusters. Hopefully my next posts will start to summarise findings.
All in all I'm feeling pretty optimistic about the research - long may that continue.
Last week I attended the Pan Commonwealth Forum which was held at IOE. Apart from hearing a lot of interesting talks and presentations worthy of the international education taught module, and catching up with a number of friends and acquaintances, it also gave me an opportunity to check my data and to see my supervisor. All seems well on all fronts so I progress!
I said 'nearly all my time' as I have also created the latest questionnaire for the longitudinal time study. In this one I am repeating some questions but have reframed others to ask about the effect of work, domestic, personal problems on the time available. I am also interested to find out whether students have settled into a pattern of weekly study that enables them to 'protect' time ie hours when they are definately studying and which are ring fenced against interuption or interference. I have sent this to the 41 students who answered my previous questionnaire and already 6 have responded. I anticipate that the number completing will drop off with each new questionnaire so hope that I started with enough to see the study through!
Last Thursday we had about 200 students come to a face to face workshop in Reading which gave me the chance to talk to some in the breaks. They are interested in the outcomes and I have been able to use some of their comments to frame the latest set of questions. Of course another questionnaire means yet more data but as the saying goes 'you can never have too much data'!!
This week my aim is to start the analysis of the data in earnest. My plan is to use one-way ANOVA to identify where there is significant variance in the data and then to use this to review the printed profiles. Currently I have 323 variables (not all of which I intend using!) and will pick off the main areas likely to impact on time in clusters. Hopefully my next posts will start to summarise findings.
All in all I'm feeling pretty optimistic about the research - long may that continue.
Saturday, 5 July 2008
Where does time go?
So two weeks on from my last post and not a lot to report. Mainly this is because family matters are absorbing the precious weekend time. The last two weekends my son and his girlfriend have been staying with us. He has just completed his Event Management degree at Manchester so is now looking for work (if anyone knows of openings anywhere in the world let me know!!). This morning was the ceremony for my students who have completed their course, and tomorrow I go to Manchester to attend his graduation ceremony. It will be wonderful to see him receive his degree but it does mean I have less time!
Mostly I am still sorting out SPSS data. I had forgotten how long it takes to set up variables and with 323 so far it has been a lengthy process. I have also had to resort to IOE for assistance in getting clear how to deal with missing data. With Charlie Owen's help I think I have the solution now so hopefully can get on with the analysis.
One thing I will need to do in the next week or so is to create the next tracking questionnaire as my sample of students are about to finish their latest module. No rest for the wicked!!
Mostly I am still sorting out SPSS data. I had forgotten how long it takes to set up variables and with 323 so far it has been a lengthy process. I have also had to resort to IOE for assistance in getting clear how to deal with missing data. With Charlie Owen's help I think I have the solution now so hopefully can get on with the analysis.
One thing I will need to do in the next week or so is to create the next tracking questionnaire as my sample of students are about to finish their latest module. No rest for the wicked!!
Thursday, 19 June 2008
Time to Reflect
Over a month has passed since my last post, however, the lengthy delay is due to my rewarding myself with a holiday in Portugal! Actually this was an opportunity to combine a break with attendance at the European Distance and E-Learning Network conference in Lisbon. I presented a paper titled Time and Borderless Distance Education that introduced the main issues surrounding this research. I am pleased to say it was well received and attracted a few questions afterwards.
Holiday is always a good time for reading. I did allow myself a couple of novels but additionally managed to finish reading Ron Barnett's book A Will to Learn. I found his perspectives on student 'being', motivation etc very interesting albeit that he was focusing mainly on full time students. If I get a chance I must talk with him about distance learners.
Taking a holiday provides good opportunity for reflection. I feel pretty happy that the data collected so far is representative and that apart from the follow up surveys to track my sample of students I can definately draw a line under the data collection. Incidentally 46 resonses have been made to the first of these follow up questionnaires which I have yet to analyse.
I had my annual review with my supervisor at the Institute yesterday- we both agree that things are on track and that the next stage is to analyse the data collected in clusters to identify any significant relationships. These can then be examined in more details from the collected data. I am still remaining optimistic about completion and aim to have the first draft written by the end of this year.
Better get to work!!
Holiday is always a good time for reading. I did allow myself a couple of novels but additionally managed to finish reading Ron Barnett's book A Will to Learn. I found his perspectives on student 'being', motivation etc very interesting albeit that he was focusing mainly on full time students. If I get a chance I must talk with him about distance learners.
Taking a holiday provides good opportunity for reflection. I feel pretty happy that the data collected so far is representative and that apart from the follow up surveys to track my sample of students I can definately draw a line under the data collection. Incidentally 46 resonses have been made to the first of these follow up questionnaires which I have yet to analyse.
I had my annual review with my supervisor at the Institute yesterday- we both agree that things are on track and that the next stage is to analyse the data collected in clusters to identify any significant relationships. These can then be examined in more details from the collected data. I am still remaining optimistic about completion and aim to have the first draft written by the end of this year.
Better get to work!!
Sunday, 18 May 2008
Stage 4 Preparation
The last two weeks have been slower due mainly to the mini heatwave that we experienced for the first 10 days of May. Last weekend was too hot (30 degrees) to do a lot on the computer so time was spent in the garden with a cooling hose or in the shade!!
Not that the EdD was overlooked entirely. As mentioned in my last posting, this research not only aims to understand what happens with student time during the period of study for a module but also aims to track a sample of students through a sequence of modules. Therefore the last couple of weeks have been spent looking through the initial output data to identify which students will be asked to participate in the follow up surveys.
The decision has been helped by the question asked at the end of the post-module questionnaire. Only those students who positively agreed to participate further were considered - a total of 184 students out of 310 (64%) that completed the questionnaire.
Of these, deciding which students to include has not been too difficult, and has either been based on a process of elimination or on a need to include basis. Having the detailed analysis of the IMC forums, and the Blackboard access statistics, has proved useful in determining those students who appear to have provided accurate data in their diaries about their study. In the believe that an 'honest' student will continue to offer truthful answers these students were included in the pot.
On the 'need to include' side, this stage aims to track students longitudinally over the course of their Part 1 studies. Consequently only those students who are taking the full course without retake or exemption were included. Additionally, due to the nature of the EdD those students located overseas were automatically included - not least as they are a relatively small number in comparison with UK ones. As family circumstances are a (critical) focus for the research all students indicating that they have a family aged below 16 were also included.
This provided a pool of 122 students who either invited themselves into the follow up stage or did not exclude themselves. This was considered to be too large a sample and the final step was to look through the data again to decide who to leave out. This was not done entirely scientifically but did aim to generate a representative sample by gender, age, location and study route (ie property or construction). The aim was to end up with a sample of 50 students. In the end 62 students have been identified which represents about 20% of the main group of 295 students. The larger number allows for casualties along the way.
The tracking sample will be emailed later this week and invited to complete a follow up 'tracking' questionnaire. This aims to collect changes in time use and life circumstances from the students and will be repeated after the next two modules as well. It contains several questions identical to those in the post IMC questionnaire allowing comparison to be made. It also includes questions that drill deeper than the previous one in areas related to time and the course, study, personal circumstances and employment issues. Lastly it feeds back the summary weekly time commitment from the student's own diary and asks them to update on how their use of time has changed.
I'm not sure that I want, or even need, more data, however, my objectives will not be met unless I can see how students use of time changes as they come up against different life events.
Onward and upward!!
Not that the EdD was overlooked entirely. As mentioned in my last posting, this research not only aims to understand what happens with student time during the period of study for a module but also aims to track a sample of students through a sequence of modules. Therefore the last couple of weeks have been spent looking through the initial output data to identify which students will be asked to participate in the follow up surveys.
The decision has been helped by the question asked at the end of the post-module questionnaire. Only those students who positively agreed to participate further were considered - a total of 184 students out of 310 (64%) that completed the questionnaire.
Of these, deciding which students to include has not been too difficult, and has either been based on a process of elimination or on a need to include basis. Having the detailed analysis of the IMC forums, and the Blackboard access statistics, has proved useful in determining those students who appear to have provided accurate data in their diaries about their study. In the believe that an 'honest' student will continue to offer truthful answers these students were included in the pot.
On the 'need to include' side, this stage aims to track students longitudinally over the course of their Part 1 studies. Consequently only those students who are taking the full course without retake or exemption were included. Additionally, due to the nature of the EdD those students located overseas were automatically included - not least as they are a relatively small number in comparison with UK ones. As family circumstances are a (critical) focus for the research all students indicating that they have a family aged below 16 were also included.
This provided a pool of 122 students who either invited themselves into the follow up stage or did not exclude themselves. This was considered to be too large a sample and the final step was to look through the data again to decide who to leave out. This was not done entirely scientifically but did aim to generate a representative sample by gender, age, location and study route (ie property or construction). The aim was to end up with a sample of 50 students. In the end 62 students have been identified which represents about 20% of the main group of 295 students. The larger number allows for casualties along the way.
The tracking sample will be emailed later this week and invited to complete a follow up 'tracking' questionnaire. This aims to collect changes in time use and life circumstances from the students and will be repeated after the next two modules as well. It contains several questions identical to those in the post IMC questionnaire allowing comparison to be made. It also includes questions that drill deeper than the previous one in areas related to time and the course, study, personal circumstances and employment issues. Lastly it feeds back the summary weekly time commitment from the student's own diary and asks them to update on how their use of time has changed.
I'm not sure that I want, or even need, more data, however, my objectives will not be met unless I can see how students use of time changes as they come up against different life events.
Onward and upward!!
Monday, 5 May 2008
SPSS and all that!
Since my last post I have looked again at the diary data and find that there are a further 74 sets of data which are complete except for the post-module questionnaire. Therefore I have added them to the collection making 295 sets of partial or complete data. Each set has been printed out on 6 sides of A4 consuming reams of paper and several printer cartidges. The whole collection now fills six 2 inch (5 cm) ring binders!
Apart from printing and filing, my last couple of weekends have been taken up with re-acquainting myself with SPSS. I haven't really used it since the taught module on methods of enquiry (about 2004) so am somewhat rusty- also of course it is now in a new version. Thank goodness for up-to-date textbooks! SPSS 15 Made Simple by Paul Kinnear and Colin Gray is particularly helpful.
Having spent many hours checking through the Excel data relating to students and the Pre-Course questionnaire to ensure that the variables are complete and the data in the right form to import I have hit a problem today with licencing. Basically the student version that I bought tells me that the licence has expired which, as it is not yet the end of the academic year, it should not.
So rather than go further I have passed the query back to the help desk and will spend the afternoon in the garden. I'm not unhappy about this as the sun has finally come out, but it is a bit of an irritant as I had planned on getting the data into SPSS by the end of this holiday weekend.
On another front, in the next week or so I have to decide on the group of students that I will track over the coming months. Not only do I need to identify the significant profiles but I also need to prepare the questionaire for their feedback.
Hey Ho - never a dull moment in research!!
Apart from printing and filing, my last couple of weekends have been taken up with re-acquainting myself with SPSS. I haven't really used it since the taught module on methods of enquiry (about 2004) so am somewhat rusty- also of course it is now in a new version. Thank goodness for up-to-date textbooks! SPSS 15 Made Simple by Paul Kinnear and Colin Gray is particularly helpful.
Having spent many hours checking through the Excel data relating to students and the Pre-Course questionnaire to ensure that the variables are complete and the data in the right form to import I have hit a problem today with licencing. Basically the student version that I bought tells me that the licence has expired which, as it is not yet the end of the academic year, it should not.
So rather than go further I have passed the query back to the help desk and will spend the afternoon in the garden. I'm not unhappy about this as the sun has finally come out, but it is a bit of an irritant as I had planned on getting the data into SPSS by the end of this holiday weekend.
On another front, in the next week or so I have to decide on the group of students that I will track over the coming months. Not only do I need to identify the significant profiles but I also need to prepare the questionaire for their feedback.
Hey Ho - never a dull moment in research!!
Subscribe to:
Posts (Atom)
