10 May ARE YOUR RESULTS REPRESENTATIVE OF THE WHOLE POPULATION THAT YOU ARE TRYING TO STUDY?
Charts and Tables: do’s and don’ts?
It is best to use charts and tables when you have a number of different variables.
..These are best for questions that have several choices:
How much do you agree with the following statement: ‘I am a heavy drinker’.
Strongly agree agree disagree strongly disagree
Don’t create a table and a chart for the same question. Choose one or the other.
Always discuss any chart or table that you use.
?Stage 3- Inferential Statistics? ?
The use of Inferential Statistics is a little more complex.
Accepting the Null Hyp or Hyp???
They attempt to establish whether a relationship between variables is significant or just by chance.
Are your results representative of the whole population that you are trying to study? Be critical!!
Inferential tests- measure the statistical significance of your result.
Very important for your analysis!!
?‘statistically significant difference’?
“A statistically significant difference” simply means there is statistical evidence that the independent variable affects the dependent variable, and that any difference seen is not purely by chance.
Apply to your results!
There are two different levels of test: Parametric and non-parametric.
Parametric tests are stronger and more accurate than non-parametric tests.
You need to know which type of test is appropriate for your data?
?Parametric and non parametric Tests?
Parametric tests -calculation involves an estimate of population parameters made on the basis of sample statistics.
Larger the sample, more accurate the estimate will be!
Opportunity to be critical of your size of sample- limitations?
Was your sample collected in a statistically random way???
IF NOT… Yours is…
Non parametric data need not be from a normally distributed population. Because you are using a convenience sample, yours will be non parametric!
?Stage 3 continued: Inferential tests? :
This is about measuring whether there is a significant difference between data and also how strong any association (correlation) is between variables.
Show understanding in this stage- 4 or 5 different combinations of your variables
Remember- keep your focus on hypothesis!
How do you do Inferential stats? There are THREE simple stages to your inferential stats!
?Stage 1 -Create a Crosstabulation?
Can only be used with data that is in categories (Nominal/Ordinal).
To help you uncover patterns in the data
Ask can you see a visual difference between variables?
?This plots gender against the question whether people think CCTV cameras have clear images.
?Stage 1 Create a Crosstabulation?
Can you see a visual difference between variables?
(The expected count is done for the benefit of the chi-square test to make sure that the expected counts are over 5, so that it is valid to use the chi-square measure. In this case it is.)
There is a visual difference although the sample size is a little uneven…
But is this visual difference statistically significant?
?Stage 2: Is the visual difference statistically significant? chi-square test?
In statistics, a result is called significant if it is unlikely to have occurred by chance.
If the significance value (p) of Chi-square p is more than 0.05, the null hypothesis is accepted and the result is therefore not significant.
If the significance value (p) of Chi-square p is less than or equal to 0.05 but greater than 0.01 than the null hypothesis is rejected and the result is significant beyond the 5% level.
?Here is the Chi-Square test for the previous data?
For the chi-square value of 6.766, there is a statistically significant difference between males and females in answering the question, as p=0.034.
The difference is therefore significant beyond the 5% level (p=0,05). The significance level is actually 3.4%.
The statement under the table also tells us that the criteria for the expected counts is okay. Expected counts relate to sample size.
?Stage 3: How strong is any association we see?Phi and Cramer’s V?
Phi and Cramer’s V are statistics which measure the strength of the association between variables.
Phi and Cramer’s V are called ‘correlation coefficients’.
Phi is usually used when the crosstab is a 2 x 2 configuration. Cramer’s V is used for any larger configuration.
These are measured in values from 0 (weak) to 1 (strong). Any value of approx 0.5 or above is seen as relatively strong.
?Tips on what to include in your results?
Focus on key findings of your results.- Decide INDIVIDUALLY not as a group!
Remember to address your hypothesis… do the findings support your hypothesis or your null hypothesis?
If your hypothesis is about gender differences do not spend the whole project talking about age differences!
Be creative- apply secondary literature and use terminology.
?The report must include? :
All three stages:
Define your data- mean/ median/ mode.
Descriptives- Frequency tables discuss and commented on.
Inferential- Crosstabs with chi square and phi/cramers V calculations: discussed and commented on.
Appropriate bar or pie charts: discussed and commented on.
?What to include…FAQ?
Do I include all the charts?
No- your choice- make sure most appropriate!
How many inferential stats?
Approx 5 Crosstabs with chi square and phi/Cramers V calculations.
Cut and paste these into your Results write up and describe and discuss them.
Important – Consider the limitations of these results: What might they be? Are there implications from the small sample size?
Problems/trouble shooting- be critical of your findings but do not be overly critical if you have no significant results. This is a perfectly valid finding which you need to discuss and not a failing in your part!!!!
?Final thoughts!?
Projects should compare their findings with other relevant secondary sources, both in introduction, methods and results!
Include your research design, questionnaires both pilot and final (amended) copy in the appendices.
Reflect on why you may have got the results you collected?
BE ANALYTICAL AND REFLECT ON FINDINGS!
Also here one lecture just follow the structure
?(Doing your research project? )
Why write reports????
Core study skills-follow the criteria, guidance, work from feedback-ask tutor!
“Creativity does not exist in a vacuum”(Sliverman 2014: 388) Techniques to writing reports and skills needed.
Good research “the identification of a worthwhile topic and the selection and competent use of an appropriate method” (Gilbert 2003: 1)
Concepts and the application of concepts -central aspects of conducting research.
?Why quantitative methods??
Develop your research methods skills & levels of confidence!
Quantitative methods involve numerical approach to both the collection and analysis of data.
Remember deduction…embedding concepts within your hypothesis and measuring this!
“The researcher must skilfully deduce a hypothesis and then translate it into operational terms” (2016:21)
Argue/justify- most appropriate approach- to fit the method that best fits your research objectives.
?Doig and Littlewood 1992 (cited Gilbert p33) “Mixed methods research strategies are particularly effective in policy orientated research..”
Needs to have a clear structure -Use sub-headings, be concise.
Finding the balance between description and remaining analytical and challenging.
Hart (1998: 172) – based on existing knowledge, developing that knowledge using reasoned argument, sound evidence and a critical and reflexive stance.
?Abstract? :
Starting your structure for the report- follow criteria on Blackboard!
Brief general summary of what you did/how you did it and what you found out.
Gilbert 2003 -abstract has a double function, serving as an overview and also as a self standing summary.
Self explanatory! Your reflection!
Not looking at secondary literature but on YOUR work!
Should outline the topic focus, methods, key findings. Only a paragraph!
Look in journals for examples!!!
?MPs’ Attitudes to Welfare: A New Consensus?HUGH BOCHEL and ANDREW DEFTY?
The post-war ‘consensus’ on welfare was based largely in the perceived agreement of leading politicians of Conservative and Labour parties on the role of the mixed economy and the welfare state. (explanation of the topic/ background) However, from the late 1970s economic and demographic pressures and ideological challenges, particularly from the New Right, led to cuts in spending on welfare, increased private involvement and an emphasis on more individualistic and selectivist approaches to provision.( Why interesting to research!) Recently some scholars have begun to discuss the emergence of a ‘new liberal consensus’ around welfare provision.(Not identifying academics but outlining a noticed trend!) Drawing upon interviews with 10 per cent of the House of Commons, this article examines the extent to which a new political consensus upon welfare can be identified. (Methodological approach) In addition to analysing responses to questions on welfare issues, it considers the extent to which MPs themselves believe there to be some degree of consensus in approaches to welfare.(more depth to why chose that method) It also considers whether any consensus exists merely in the political language used in relation to welfare issues, or whether there is a more substantive convergence.(findings!)
(Published Online December 21 2006)
?Hypothesis and Null Hypothesis? :
Refer back to the research design!
Look at feedback- did it need amendment?
Workable??? represents the condition to be tested and should be paired with a ‘Null Hypothesis’:
Follow and act on feedback on your research plan- opposite of each other?
Eg: Hyp: It is expected that female university students at Lincoln will be more fearful of crime than male Lincoln university students.
Null Hyp: There will be no difference in the fear of crime between male and female Lincoln university students
?Core to your research analysis.
“A hypothesis is a reasoned but provisional supposition about the relationship between two or more social phenomena, states in terms that can be empirically tested and which forms the focus for the research, particularly in quantitative studies” Payne and Payne (2004; 112)
Tentative statement (a ‘working hypothesis’) -leads to research and directs the focus of the research.
A ‘Relational hypothesis’ -refers to the possible relationship between two or more variables.
?Identifying variables? :
A variable is ‘something which is free to vary’.
Our website has a team of professional writers who can help you write any of your homework. They will write your papers from scratch. We also have a team of editors just to make sure all papers are of HIGH QUALITY & PLAGIARISM FREE. To make an Order you only need to click Ask A Question and we will direct you to our Order Page at WriteDemy. Then fill Our Order Form with all your assignment instructions. Select your deadline and pay for your paper. You will get it few hours before your set deadline.
Fill in all the assignment paper details that are required in the order form with the standard information being the page count, deadline, academic level and type of paper. It is advisable to have this information at hand so that you can quickly fill in the necessary information needed in the form for the essay writer to be immediately assigned to your writing project. Make payment for the custom essay order to enable us to assign a suitable writer to your order. Payments are made through Paypal on a secured billing page. Finally, sit back and relax.
About Writedemy
We are a professional paper writing website. If you have searched a question and bumped into our website just know you are in the right place to get help in your coursework. We offer HIGH QUALITY & PLAGIARISM FREE Papers.
How It Works
To make an Order you only need to click on “Order Now” and we will direct you to our Order Page. Fill Our Order Form with all your assignment instructions. Select your deadline and pay for your paper. You will get it few hours before your set deadline.
Are there Discounts?
All new clients are eligible for 20% off in their first Order. Our payment method is safe and secure.