Tag Archives: Statistics paper

Need help-Statistics Assignment:Geochemistry 1


Need help-Statistics Assignment:Geochemistry 1

Field and Laboratory Techniques in Geochemistry 1

Statistics Assignment

 

Question 1)  10%

The data for a digestion of Bolivian tailings are provided. The elements are grouped as majors, traces and rare earth elements. Produce, using the descriptive statistics command in Excel (or any other suitable programme), summary data for each of these three groupings (Mean, Standard Error, Median, Mode, Standard Deviation, Sample Variance, Kurtosis, Skewness, Range, Minimum, Maximum, Sum and Count).

The data should be presented in tabulated form.

 

Question 2)  10%

Explain, using a maximum of three sentences for each, what you understand by the terms: Mean, Standard Error, Median, Mode, Standard Deviation, Sample Variance, Kurtosis, Skewness, Range, Minimum, Maximum, Sum and Count.

 

Question 3)  10%

Calculate the precision for each element analysed. (Hint the copy and paste tool is very useful for formulae).

 

Question 4)   10%

The data for a digestion of Bolivian uncontaminated soil are provided. The elements are grouped as majors, traces and rare earth elements. Calculate the mean, standard deviation, standard error and median of the samples for each of these three categories. Comment on any elements which show a large median/mean difference (hint Bi might be worth comparing in this context; for example against a major element). Your answer should incorporate the word ‘outlier’.

 

Question 5)   10%

BCR-1 and JB-3 are soil CRM materials. They were digested at the same time and using exactly the same methodology as the samples themselves. Calculate the accuracy of the digestion by comparing the results with the given elemental concentrations of the reference materials (BCR-1 rv and JB-3 rv). Comment on the accuracy of the analysis.

 

Question 6)  25%

The data for chloride concentrations of Regent’s canal and Pennine stream water, as determined by Ion Chromatography (IC), are presented. The data to be analysed are those collected from the Regent’s canal (RC in the spreadsheet itself). To the right of the spreadsheet these data has been extracted to help you answer the following questions.

Question 6a) the samples were analysed at two dilutions: a hundred fold (*100) and neat (*1). Why do you think that such a difference was reported in concentration? Which of these ‘dilutions’ do you trust?

Question 6b) construct a calibration curve (hint, scatter graph). The calibration standards employed were made up to 10, 20, 40 and 60 mg L-1. Plot a suitable regression line and display the R2 value on the graph, from this calculate the Pearson correlation coefficient (hint this is a one-step transformation)

Question 6c) do you think that drift correction might be necessary? Plot a suitable scatter graph to illustrate your answer. Note there is not a definitive yes or no answer to this question. You will be awarded marks on the strength of your reasoning.

Question 6d), using the blank data determine the LOD and LOQ for the complete analytical run. Describe, in a maximum of four sentences, what is meant by the terms LOD and LOQ.

Question 6e) Determine the precision* and accuracy (hint, consider the CRM dilution factor) of the Regent’s canal data. The concentration of chloride in the Battle reference standard is as follows:

 

*Note there are two duplicate pairs: 1 and 1a together with 2 and 2a. Calculate the individual precisions and the combined overall precision by any appropriate method.

 

 

Question 7)  25%

The data provided are from a column experiment which investigated the evolution of pore water concentrations over a modelled twenty year period. The column was packed with uncontaminated Bolivian soil together with sulphide mine tailings.

Question 7a) Produce a correlation matrix encompassing all of the elements (hint spreadsheet 30 gives a suitable method and also remember to remove all non-numerical data).

Question 7b) Produce three scatter graphs from the data. The first should show a strong positive correlation, the second a negative correlation and the third show minimal correlation. For each of these graphs plot a regression line, produce a linear equation and a R2 value. From the latter obtain the value of r (Pearson’s correlation).

7c) Calculate a Spearman correlation coefficient for the Zn and Cd concentrations (hint, follow the ranking formulae given in spreadsheet 11).

When comparing the Pearson and Spearman correlation coefficient, which of the two is more sensitive to outliers? Looking at the formulae can you suggest a reason for your conclusion?

Pearson

Spearman

 

7d) Give an example, not necessarily from the scientific literature, of correlation not implying causation (hint, Wikipedia has a good page addressing this specific question).

 

Need help-Statistics Assignment:Geochemistry 1

Advertisements

Describe the elements of Power analysis and discuss how to conduct a power analysis.


Describe the elements of Power analysis and discuss how to conduct a power analysis.

Quantitative Methods Assignment


Quantitative Methods Assignment

(Please do NOT take this project unless you’re 100% sure that you’ll get at least B)

Quantitative Methods Assignment

The student is required to demonstrate the creativity to formulate a problem, the ability to collect information, to enter and edit it, to analyse it; and to write an effective and clear report. Ask yourself a question. The question must be relevant to the Quantitative Methods course. Collect all the relevant information, perform any relevant analysis, and then write a report on what you have done. I expect the report to contain between 2500 and 3000 words, although it is the quality rather than the length of the report that matters most. You may collect the data yourself. Alternatively, if appropriate, you may use official statistics. What you may not use is a standard data set from a textbook. Such an approach will not be well received. If you find it necessary to use a computer package such as SPSS, then I expect you to fully use it. Computing simple statistics by hand will not attract many marks. Above everything else, it is the originality and insight provided by the task that I will value: It is better to use simple statistics ef

The student is required to demonstrate the creativity to formulate a problem, the ability to collect information, to enter and edit it, to analyse it; and to write an effective and clear report. Ask yourself a question. The question must be relevant to the Quantitative Methods course. Collect all the relevant information, perform any relevant analysis, and then write a report on what you have done. I expect the report to contain between 2500 and 3000 words, although it is the quality rather than the length of the report that matters most. You may collect the data yourself. Alternatively, if appropriate, you may use official statistics. What you may not use is a standard data set from a textbook. Such an approach will not be well received. If you find it necessary to use a computer package such as SPSS, then I expect you to fully use it. Computing simple statistics by hand will not attract many marks. Above everything else, it is the originality and insight provided by the task that I will value: It is better to use simple statistics ef ectively than to reproduce some complex and standard material, which I could find in a textbook or a journal article. Plagiarism is taken very seriously. Submitting a piece of coursework you have already submitted for another course, perhaps at another university, is not acceptable. Some students decide to obtain some data, apply a particular formula, and report that the answer is 42 or some other meaningless number. Without a context, this is not a valuable exercise. Such studies invariably get bad marks. I value initiative and a demonstration of an inquisitive mind even more than technical ability. Assignment page 1 Examples of Statistical Problems Studied in Previous Years The following is a list of chosen amongst the most interesting from the collection of previous studies: 1.­ Are women safer drivers? Data was obtained from an insurance company on claims by age and sex group. It was found that the answer is ‘Yes’. There are interesting effects in a particular age group when teenager children use mum’s car. 2.­ Death is interesting. An analysis of mortality rates by age and sex in Hampshire compared with the national average. People, particularly women, live longer in Hampshire, but this may indicate that elderly ladies retire here. 3.­ Auto Trader: The weekend football matches were found to affect the effectiveness of tele­canvassers. 4.­ Does the rain in Germany affect the movements in the stock market? It would if people were in a bad mood because of the rain. The data does not support this view. 5.­ Drinking coffee in Thames River. A student had a boat and enjoyed sailing around while drinking coffee. This is difficult if the wind reaches certain strength. The student would not go out to sea if the wind were above a certain limit. Data from the Met Office was used to assess the probability of the wind changing strength while the student was at sea. 13.­ Did it make any difference if a particular player was or was not in the team? A Bristol City fan was very fond of a particular player and argued that when he was not in the team, the match was more likely to be lost. The data did not support the conjecture. 14.­ Do soldiers with larger families receive more letters than soldiers with smaller families? It appears to be the case that the reverse is true. 15.­ The Oxford­Cambridge boat race: The probability of winning was found to increase with the weight of the crew. 16.­ Child abuse in Canada. Is there a relationship between age at register and severity of abuse? 17.­ Simulation of photocopying in the library. What would be the impact on queue lengths of introducing an upper limit on the number of photocopies a student is allowed to make? 18.­ Are music bands with shorter names more successful than music bands with longer names? 6.­ Foreign aid in Sudan. Foreign aid is meant to help a country overcome economic problems and improve its national product. It turns out that the more aid a country receives, the worst off it is in subsequent years. The student invented a rational for this observation. 7.­ Women in Africa. Is the participation of women in the labour force related to the degree of development of the country? 8.­ Cornflakes: Is Kelloggs worth the price? Branded (Kelloggs) cornflakes packets were compared with unbranded own­labels (Safeway, Tesco and Asda). The group laid out criteria for ‘a whole cornflake’. They then counted the number of whole cornflakes in samples of the different brands! They found that Kelloggs had the better quality. 9.­ Payment methods for salesmen. A company used salesmen who were paid according to a series of categories. The amount they received for a sale depended on how the sale had been Assignment page 2 classified. The student proposed a system of commissions. Salesmen were expected to win the same amount of money under the old and the new system. Then the system was modified to encourage large sales. 10.­ Association between results in university degrees and in professional examinations. Are people with relevant degrees at an advantage when taking professional exams? 1 l.­ Does the method of paying for dental care influence the number of interventions that the dentist inflicts on the patient? It used data from before and after a change in funding. 12.­ How many lorries should my father have in his business? The lorries could be leased or rented. The student examined probability distributions and did a kind of simulation to explore the consequences of various policies. 19.­ Analysis of French electoral results. How representative is the Government? 20.­ Bus lateness: Was Orléans Express assertion that buses will be on time, most of the time supported by the data? 21.­ Down syndrome and age of mothers. Is it true that older mothers are more likely to produce children with Down syndrome? This was too ambitious, and the student found it too difficult to cope with the issues. 22.­ Do shoe sales respond to changes in the weather? The intention was to develop an ordering and stock holding policy for a shoe shop. 23.­ How good are forward rates at anticipating changes in the spot rate? Exceptions It will be advisable if you do not choose any of the following problems: 1. Economic analyses, especially those involving econometric data such as gross domestic product. The reason is that such analyses often require more advanced models than we are able to cover in this unit. 2. Olympics: There have been many studies about the Olympics, especially those to do with total medals per country. Inevitably, they all lead to the same conclusion: Big countries get more medals! Assignment page 3 The marking criteria to be used in assessing these assignments is given below: Note: The total marks for each category are as indicated in brackets Report Quality (20%) Style, Presentation, Clarity and Organisation Methodology (20%) Choice and Statement of Research Question; Sampling Data Collection and Manipulation Process: Validity and Quality of Data Quality of Quantitative Model(s) Used (30%) Appropriateness, Correctness and Sophistication Results and Conclusions (20%) Interpretation; Discussion of Limitations, Relevance and Usage Evidence of Further Reading (10%) Assignment page 4

Quantitative Methods Assignment


Subject: Statistics
Topic: Quantitative Methods Assignment

Paper details

Quantitative Methods Assignment

The student is required to demonstrate the creativity to formulate a problem, the ability to collect information, to enter and edit it, to analyse it; and to write an effective and clear report. Ask yourself a question. The question must be relevant to the Quantitative Methods course. Collect all the relevant information, perform any relevant analysis, and then write a report on what you have done. I expect the report to contain between 2500 and 3000 words, although it is the quality rather than the length of the report that matters most. You may collect the data yourself. Alternatively, if appropriate, you may use official statistics. What you may not use is a standard data set from a textbook. Such an approach will not be well received. If you find it necessary to use a computer package such as SPSS, then I expect you to fully use it. Computing simple statistics by hand will not attract many marks. Above everything else, it is the originality and insight provided by the task that I will value: It is better to use simple statistics effectively than to reproduce some complex and standard material, which I could find in a textbook or a journal article. Plagiarism is taken very seriously. Submitting a piece of coursework you have already submitted for another course, perhaps at another university, is not acceptable. Some students decide to obtain some data, apply a particular formula, and report that the answer is 42 or some other meaningless number. Without a context, this is not a valuable exercise. Such studies invariably get bad marks. I value initiative and a demonstration of an inquisitive mind even more than technical ability.

Custom Essay writers


ABOUT US

Where are we Based?

We are an academic assistance agency based in the US and open to the Global market.

How long have we been in the Market?

Our agency is a high quality writing service provider, whose establishment dates back to 2012. Our team is committed to providing all-time customized papers with exceptional authenticity to our customers from across the USA, Canada, Australia, UK and all other parts of the World.

  • USA
  • UK
  • AUSTRALIA
  • CANADA
  • OTHERS

 Our Support Team

Our teams who work in the Support department are highly-trained to answer to inquiries professionally and in a friendly way. The team is available 24/7.

Quote for Order

Simply fill your order details at Order Now  and notify us through our email writersestate@gmail.com. Make Payment through either Paypal or Skrill /Moneybookers (writersestate@gmail.com). Within the first 15 minutes, you will receive a notification through email, confirming we received the order and the payment. The most suitable writer who has done your discipline will be assigned to complete the order. We offer premium services to all our clients upon request.

As well you can make free inquiries on ‘How much to pay for your Order’ through our email; writersestate@gmail.com.  Our Support will guide you accordingly.

WHY CHOOSE US?

Best Quality

  • Highly trained content writers and editors
  • Highest Quality control
  • 6 Six years writing experience

Convenience

  • Consistent communication
  • Customer Support is 24/7
  • Simple process of placing your Order

Affordable Services

  • Prices start at $8 per page
  • Average prices
  • Discount plan for Returning Customers

Zero Plagiarism

Our services are exceptional, free of plagiarism.

Our Values

Confidentiality

We guarantee all our clients confidential deals. We do not share your details either by disclosing private details to any institution, person or reusing any custom essay papers in the online platforms.

Authenticity

Order for ready custom sample papers, research papers, essays, term papers, dissertations, theses, Research projects book/movie reviews, reports, speeches, technical papers and other assignments.

Our Services

Essay draft: We create sample paper useful as reference.

Editing: Polishing a written paper through necessary amendments.

Research: We assist our customers to find reliable sources to your subject.

Formatting: We format your paper using citation styles such as APA, MLA, Harvard, Chicago and/orTurabian.

Articles: We write articles of different subjects.

Blogs: Appealing blogs and social media pages are necessary for your online sites. We write such blogs.

Web Content: We create website content of any audience.

Email Campaigns: We offer assistance in email marketing campaigns.

Landing Pages: Our writers are able to write texts for the landing pages; able to attract visitors.

Creation of Newsletters and News: We create newsletters to our clients depending on requirements provided.

Press Releases: We also write enticing news articles, corporate brochures and Presentations.

Proofreading and Editing: We offer proofreading and editing services on Books and ebooks of all genres, Academic papers (Research papers and Dissertations) at cheaper prices.

 

 

Cell Phones Apps Communication


 Cell Phones Apps Communication

Results and discussion write-up (75 points):

After data collection takes place, students will be required to analyze the data and describe what the results are. Students will also be required to interpret the findings and figure out what the results mean for the topic studied. There is no required page limit, but the paper should be around 4-6 pages. The basic outline should be:

  1. Results
    1. Descriptive statistics:
      1. How many subjects were included?
      2. What are the mean, standard deviation, variance, and standard error of the mean for each variable?
    2. Inferential statistics:
      1. What statistical tests were used? Why (i.e., what does the test do that makes it appropriate)?
      2. What are the calculated value of the statistic (i.e., the t-value, r-value, chi-square value), the degrees of freedom, and the calculated p-value? (If more than one statistical test is performed, these should these should be reported for each test.)
  • Is the finding statistically significant? What does this mean?
  1. Discussion
    1. What do the results mean? What do the results tell us about the topic being studied?
    2. How do the results help us to understand communication?
    3. What explanations for the results can you think of? Do they fit with what other authors found, based on the literature that was discussed in class?
    4. What are some limitations or weaknesses of the study?
    5. What would a good next step be for continuing to study this topic?

 

Results and discussion write-up grading guidelines:

  • Results (35 points):
    • All descriptive statistics listed in the outline are provided (2 points each, 10 points total)
    • An explanation of the inferential statistics used is included, and the explanation for why is consistent with the explanation of those tests given in class (10 points)
    • The calculated value, degrees of freedom, and p-value are reported for all tests (10 points)
    • Whether or not the test is significant is correctly reported for each test (5 points)
  • Discussion (35 points):
    • All five questions in the outline above are answered thoroughly (7 points each)
  • Grammar and spelling (5 points)

 

 

NURS2906 S15 Major Lab Assignment – Brain Size vs IQ


NURS2906 S15 Major Lab Assignment – Brain Size vs IQ

Due July 31th, 11:00pm Does a bigger brain make you smarter? It was postulated that Albert Einstein’s genius came from marked differences in his brain, so maybe it is just pure size? In 1991, Doctor L.Due July 31th, 11:00pm Does a bigger brain make you smarter? It was postulated that Albert Einstein’s genius came from marked differences in his brain, so maybe it is just pure size? In 1991, Doctor L.

Due July 31th, 11:00pm Does a bigger brain make you smarter? It was postulated that Albert Einstein’s genius came from marked differences in his brain, so maybe it is just pure size? In 1991, Doctor L.

Due July 31th, 11:00pm Does a bigger brain make you smarter? It was postulated that Albert Einstein’s genius came from marked differences in his brain, so maybe it is just pure size? In 1991, Doctor L. Willerman, R. Shultz, J. N. Rutledge, and E. Bigler used Magnetic Resonance Imaging or MRI to determine brain sizes of 40 right handed students. They then used this data along with weight, height and gender data along with scores on two different IQ tests to determine if there was a relationship. Our goal is to verify and reproduce their study with the concepts learned in this course and see for ourselves, ”does a bigger brain make you smarter?” The dataset is available on Blackboard. The background of this story can be found at http://lib.stat.cmu.edu/DASL/Stories/BrainSizeandIntelligence.html For this report we will focus on the PIQ, Performance IQ scores; MRI Count which gives an idea of brain size; and Gender. Please include a title page and submit the file through the assignment drop box on Blackboard as a PDF File. Use SPSS 22 for all statistical analysis and include tables and graphs where necessary. Any numbers or information used in the report write up must reference SPSS output which appears either in the report or the appendix, and visa versa. If you include a table or graph explain it. Use some method (i.e. footnotes, italics, etc) to show where questions are answered, multiple locations are acceptable but the footnote must note this. Extra information or clarification may be added to the assignment before the due date, watch Blackboard and in class notes. If your assignment is handed in before the new information it will be exempt from the changes. 1 The purpose of this report is to explore this dataset and create a story about the relationship between IQ, gender and brain size. Do your best to connect each section and create a narrative and convincing argument. There are other variables, use them if they help. 1 Introduction Find information online and elsewhere and write a brief summary of the study and what the variables and data are about, so as to give context to your report. 2 Analysis 2.1 Graphical Methods Use graph styles presented in class and labs to produce graphs and look at the distribution of PIQ and MRI Count before and after splitting genders. Can you see any connection with and without gender as a factor? Are there any trends or patterns? Can you see anything worth questioning or studying about the data? 2.2 Summary Statistic Summarize the basic statistics in terms of location and dispersion, and distribution of PIQ and MRI Count and also compare the differences between males and females in both. 2 2.3 Linear Perform a linear regression to predict PIQ scores based on the MRI Count (brain size). Is there a significant relationship? Is there a significant relationship within each gender? Is brain size a good predictor of IQ in general and/or within each gender? 2.4 Hypothesis Testing According to the Flynn effect IQ should rise over time. Since this study was in 1991 we would expect the mean IQ to be above the baseline 100. At the 5% level are the PIQ scores significantly above the 100 point baseline. Include all steps of the hypothesis testing process. 2.5 Population Estimation Estimate an interval for the mean PIQ at the 95% confidence level, for each gender. Since the study was conducted in 1991 the IQ should be at 118.3, since according to the Flynn effect the IQ should rise 3 points per decade. Does this interval help to confirm this? Include the intervals with proper interpretations as well. 3 Conclusion Write a short report to summarize all of your findings and conclusively answer whether there is difference in IQ between males and females, and whether you can predict IQ my knowing the size of someones brain. 3

Data

nGender FSIQ VIQ PIQ Weight Height MRI_Count
Female 133 132 124 118 64.5 816932
Male 140 150 124 72.5 1001121
Male 139 123 150 143 73.3 1038437
Male 133 129 128 172 68.8 965353
Female 137 132 134 147 65 951545
Female 99 90 110 146 69 928799
Female 138 136 131 138 64.5 991305
Female 92 90 98 175 66 854258
Male 89 93 84 134 66.3 904858
Male 133 114 147 172 68.8 955466
Female 132 129 124 118 64.5 833868
Male 141 150 128 151 70 1079549
Male 135 129 124 155 69 924059
Female 140 120 147 155 70.5 856472
Female 96 100 90 146 66 878897
Female 83 71 96 135 68 865363
Female 132 132 120 127 68.5 852244
Male 100 96 102 178 73.5 945088
Female 101 112 84 136 66.3 808020
Male 80 77 86 180 70 889083
Male 83 83 86 892420
Male 97 107 84 186 76.5 905940
Female 135 129 134 122 62 790619
Male 139 145 128 132 68 955003
Female 91 86 102 114 63 831772
Male 141 145 131 171 72 935494
Female 85 90 84 140 68 798612
Male 103 96 110 187 77 1062462
Female 77 83 72 106 63 793549
Female 130 126 124 159 66.5 866662
Female 133 126 132 127 62.5 857782
Male 144 145 137 191 67 949589
Male 103 96 110 192 75.5 997925
Male 90 96 86 181 69 879987
Female 83 90 81 143 66.5 834344
Female 133 129 128 153 66.5 948066
Male 140 150 124 144 70.5 949395
Female 88 86 94 139 64.5 893983
Male 81 90 74 148 74 930016
Male 89 91 89 179 75.5 935863

Dissertation chapter – Discussion Scientific Thinking


Dissertation chapter – Discussion

Scientific Thinking

Reference this week’s lecture to develop a research question and a hypothesis for a hypothetical business problem of your choice. Explain the management dilemma or the business problem that the research would attempt to solve. Your research question must relate to the business reason for the research. For example, “Why have sales of used cars been declining at a rate of 5% per month since July 2012 at Smith Motors?” is a valid research question because you can investigate it with research.

A hypothesis must state an educated guess about why you think something is happening; think about cause and effect. For example, “Sales are declining at Smith Motors due to road construction around our dealership” is a hypothesis because it offers a possible cause for the problem. “Sales are declining at Smith Motors” is not a hypothesis because it does not offer a possible cause for the problem.

Evaluation and Criticize a Quantitative Research Paper


Work type: Critical thinking
Academic level: Master’s
Subject or discipline: Statistics
Title: Evaluation and Criticize a Quantitative Research Paper
Number of sources: 0
Provide digital sources used: No
Paper format: MLA
# of pages: 2
Spacing: Single spaced
# of words: 1100
# of slides: ppt icon 0
# of charts: 0
Paper details:

This a Quantitative Medical Research Paper need to be answered according to Quantitative Research methods. The answers will be according to specific Question will be provided in additional material. please Note the following:
1- These Question of previous use so some of the question may not applicable to this paper and some of the question has to be modified according to this paper to be answered. Therefore, please try your best to address the question.
2- There is no word limit for answer.
3- please make it Clear and Brief as much as you can.
4- No Resources and References needed.
5- concentrate on interpretation of data.
6- answering according to these Questions.

  • About introduction:

 In your own words, discuss the rationale for the study? [6 marks]

    • [HINT: You should include the background of the condition, rationale for the choice of interventions as well as the strengths and weakness of case the case made for the need for this study]

 Is the objective of the study clear? Does it follow from the rationale? [2 marks]

 About design:

3-  What would the disadvantages of an observational study be to answer the study’s objectives?                                                                                         [2 marks]

4-   A colleague suggests that the authors did not need to use such a complicated approach to allocating patients to treatment arms but could simply have done it sequentially so that the first participant was allocated surgery, the second rehabilitation, the third surgery, etc.  

  • Explain the disadvantages of this allocation technique and the advantages of the method used by the authors. [3 marks]

Hint: question about randomisation and concealment.

 

 

  • Discuss the inclusion /exclusion criteria given below, and their appropriateness. Additionally, discuss the appropriateness of participant recruitment. [7 marks]

Hint: Make sure you can understand if the population is appropriate to answer questions. (Or comment on lack of justification) 

  • About Sample Size:

7- Is all the information provided for it to be repeatable?                            [2 marks]

                8-  Why were the values of the mean difference and the standard deviation used?

                                                                                                                                                         [4 marks]

                9- Would the sample size increase or decrease if the authors decreased the level of     mean difference from 10 to 5 points?                                                                             [2 marks]

                10- What is meant by the term ‘power’?                                                              [3 marks]

                11) Would the sample size increase or decrease if the authors wanted to have 90% power?                                                                                                                       [2 marks]

               12- Discuss, with specific examples from appropriate tables in the paper, the balance of                                the two treatment groups at baseline.

Hint: Question is about baseline comparability and  discuss the consequences of it.

 

13- ‘Blinding’ is an important method used to avoid bias in RCTs. Discuss any blinding in this trial and the potential consequences in terms of bias.                                 [5 marks]

 

  • 14- The primary outcome measure was the Oswestry disability index (ODI) at 2 years
  • a) Given that this a patient-reported questionnaire which types of validity should have been established to justify its use? Describe each type of validity and why it is relevant here.                                                                                      [6 marks]
  • b) What type of reliability is important when using the Oswestry disability index? Explain why.                                                                                                 [2 marks]

Hint: Need to know reliability and validity well.

 

  • 15- The authors have used a t-test to compare the difference from baseline in Oswestry disability index ODI between the two treatment groups.                                                     
  • a) What null hypothesis is this testing?                                                [2 marks]
  • b) What assumptions are needed about the distribution of ODI for this test to be valid?                                                                                                              [2 marks]
  • c) Discuss how the assumptions might be checked.         [2 marks]
  • d) Interpret the 2 year results which give a treatment effect of -8.4 (-13.2 to -3.6) with a p-         value of 0.001.                                    [5 marks]

 

  • 16- In the ‘planned analyses’ section the authors plan to use ‘intention to treat’. Explain what is meant by this term and discuss the advantages of this approach? [4 marks]

 

  • 17- Table 5 presents the results for other outcome measures. Interpret the results for
  • a) SF-36 at 2 years                                                                            [5 marks]
  • b) Number (%) satisfied with outcome at 2 years             [4 marks]

 

Question 1:

  1. Summarize the background of the study.
  2. Comment on the appropriateness and clarity of the rationale/aims of the study, given the background provided.

Question 2:

 This is a randomised controlled trial. What are the benefits of randomised allocation over other forms of treatment allocation?

  1. What is meant by the term “blocked randomisation”
  2. Was the allocation concealed from the researchers? What are the advantages of doing this?

Question 3:

 The authors have identified primary and secondary outcome measures. Why is it important that the authors categorise outcome measures in this way?

  1. What is the primary outcome measure for this trial? Discuss the appropriateness of this outcome measure for this trial.
  2. What are the disadvantages of measuring and analysing the primary outcome measure at 12 and 24 months?
  3. What type of outcome measure is the primary outcome and what descriptive statistics would be appropriate?

Question 4:

With reference to Table 1 and other tables, discuss the balance between treatment arms.

  1. Why is it important to consider the balance of treatment groups at baseline?

Question 5:

The sample size calculation uses 90% power, explain what is meant by “power” here.

  1. The sample size calculation uses a two sided 5% significance level. Explain what is meant by “significance level” here.
  2. What mean difference is the sample size calculation based on? Have the authors justified this choice?
  3. Discuss if the first sentence of the sample size section reports all the necessary components for a sample size calculation.

 

Question 6:

 The primary outcome measure is SF-36, in Table 3, the “unadjusted difference” row gives the results for the t-test at both 12 months and 24 months.

  1. What distributional assumptions are required for these tests to be valid? How might these be assessed?
  2. State the null hypothesis that is being tested here in terms of the parameters of the assumed distribution at 12 months and 24 months. What does the p-value of 0.031 mean for the hypothesis at 24 months? What does the p-value 0.11 mean for the hypothesis at 12 months
  3. Interpret the entries “5.7 (-1.4 to 12.8)” and “8.2 (0.8 to 15.7)”
  4. How does the results compare with the hypothesized difference in the power calculation?

Question 7:

 The authors state they are going to do the analysis on an “intention to treat” basis. Explain what is meant by “intention to treat”.

  1. With reference to Figure 1, discuss patient flow through the study highlighting areas of potential concern.

 

Question 8:

The study states that “…this was an open trial, neither participants nor researchers were blind to treatment assignment” discuss the potential biases this might pose.

Question 9:

 

What are the potential limitations for the generalisability of this study?

[HINT: please consider the inclusion/exclusion criteria, patient flow and potential biases]

 

 

Question 10:

 

The conclusion drawn by the authors is summarised as “Weak evidence was found of an effect of acupuncture on persistent non-specific low back pain at 12 months, but stronger evidence of a small benefit at 24 months. Referral to a qualified traditional acupuncturist for a short course of treatment seems safe and acceptable top patients with low back pain”. Either provide support for this statement from the results of the paper or explain why they are incorrect.

 

Question 11:

 

Discuss, with reference to the study aims, if the choice of control group was appropriate.

 

Question 12:

 

For the primary outcome measure (in this case the bodily pain domain of SF-12 which is patient-reported) which types of test validity and reliability are relevant and why?

 

Question 13:

 

  1. a) In terms of RCTs, what is meant by the term blinding?
  2. b) In terms of the primary outcome in this study explain who was blind? What are the potential consequences of this?

 

 

Question 14:

 

  1. What percentage of people randomised had outcomes at 12 months?
  2. Discuss how this compares with what was expected by the authors?
  3. In what way could the people who didn’t have outcome reported at 12 months bias the comparison of the primary outcome between treatment groups?

 

 

Question 15:

 

  1. Are all the outcomes discussed in the ‘Outcome measures’ section reported in the results section?
  2. Discuss any possible reporting bias in terms of the outcome measures.

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Statistics; Predicting Response at BookBinders: Logistic Regression


 Statistics; Predicting Response at BookBinders:  Logistic Regression

Simply Click ORDER NOW and your paper details. Our support team will review the assignment(s) and assign the right expert whose specialization is same to yours to complete it within your deadline. Our Editor(s) will then review the completed paper (to ensure that it is answered accordingly) before we email you a complete paper 

Email Us for help in writing this paper for you at: support@customwritings-us.com

As a direct marketer of specialty books, the BookBinders Book Club has achieved steady growth in their customer base.  Yet while sales have grown steadily, profits began falling when the database got larger and when the company diversified its book selection and increased the number of offers sent to customers. The falling profits have led Dave Lawton, BookBinders’ marketing director, to experiment with different database marketing approaches in order improve BookBinder’s mailing yields and profits.

 

Dave began a series of live market tests, each involving a random sample of customers from the database.  An offer for the current book selection is sent to the sample and then the sample customers’ responses, either purchase or no purchase, are recorded and used to calibrate a response model for the current offering. The response model’s results are then used to “score” the remaining customers in the database and select customers from the full customer database for the ‘rollout’ mailing campaign.

 

Dave’s first market tests relied on RFM (recency – frequency – monetary) analysis.  Direct marketers have used this approach to predict customer behavior for more than 50 years.  The approach is intuitive, easy to implement, and produced significant improvements in response rates and profits compared with mass mailings to BookBinder’s full database.  Despite this initial success, Dave is eager to evaluate the effectiveness of alternate approaches.  BookBinders offers books in different categories including cooking, art and childrens’ books – and the number of previous book purchases in each category is recorded in each customer’s record in the database.  RFM analysis does not use this or other customer information such as gender, and Dave suspects that a more sophisticated modeling approach could yield superior results to the RFM approach.

 

Logistic Regression offers a powerful method for modeling response.  Logistic regression is similar to linear regression – the key difference is that the dependent variable is binary (for example, purchase or no purchase) rather than continuous.  For each customer, logistic regression predicts a probability, between 0 and 1, of purchase or response, which can be used for targeting and prediction decisions.  Like linear regression, it can accommodate both continuous and categorical predictors, including interaction terms.  Its use in database marketing has grown as software becomes more readily available and as familiarity with the approach grows.

 

Dave has just received a dataset containing the responses of a random sample of 50,000 customers to a new offering from BookBinders titled “The Art History of Florence.”   Dave is eager to assess the potential value of logistic regression as a method for predicting customer response and has asked you to complete the following analyses.

 
  1. Logistic Regression
    Estimate a logistic regression model using BUYER as the dependent variable and the following as predictor variables: (Use ‘Analyze/Regression/Binary Logistic” in SPSS. Save the predicted probabilities by clicking on the ‘Save’ button and then on ‘Probabilities’ under ‘Predicted Values’).
    LAST  
    TOTAL$
    GENDER
    CHILD

    YOUTH
    COOK
    DO_IT
    REFERNCE
    ART
    GEOG
Technical Note:

PURCH is excluded from the set of predictor variables – including it will lead to perfect collinearity since PURCH (the number of books purchased) is equal to the sum of the number of books purchased in the 7 categories. By including the number of purchases in each category, there is no need to include the total number of purchases.

  1. Summarize and interpret the results (so that a marketing manager can understand them). Which variables are significant?  Which seem to be ‘important’?  Interpret the coefficients for each of the predictors.

 

  1. Decile Analysis of Logistic Regression Results
    1. Assign each customer to a decile based on his or her predicted probability of purchase. (Hint: use “largest values” to create deciles)
    2. Create a bar chart plotting response rate summarized by decile. (Hint: Use deciles as the “Category Axis” and mean “Bought” on the vertical axis)
    3. Generate a report showing number of customers, the number of buyers of “Art History of Florence’ and the response rate to the offer by decile. (Hint: use “Case Summaries,” be sure to uncheck “Display Cases”)
    4. Generate a report showing the mean values of the following variables by probability of purchase decile:
      Total $ spent
      Months since last purchase, and
      Number of books purchased for the seven categories (i.e., children, youth, cookbooks, do-it-yourself, reference, art and geography). (Hint: use “Case Summaries,” be sure to uncheck “Display Cases”)
    5. Summarize and interpret the decile analysis results.

 

 

 

  1. Lift and Cumulative Lift
    1. Use the information from the report in 2c) above to create a chart showing the lift and cumulative lift for each decile. Recall that the lift for a decile is the response rate for that decile divided by the overall response rate.  Similarly, cumulative lift is the cumulative response rate (summing up to and including that decile) divided by the overall response rate.  You may want to use Excel for these calculations.
    2. Create a graph showing the cumulative lift by decile.
  2. Gains, Cumulative Gains and ‘Banana’ Charts
    1. Use the information from the report in 2c) above to create a chart showing the gains and cumulative gains for each decile. Recall that the gains for a decile are the proportion of responders who are in that decile.  Similarly, cumulative gains are the sum of gains up through that decile.  You may want to use Excel for these calculations.
    2. Create a ‘banana’ chart showing the cumulative gains by decile along with a reference line corresponding to ‘no model’. Interpret the Banana chart.
  3. Profitability Analysis

Use the following cost information to assess the profitability of using logistic regression to determine which customers will receive a specific offer:

 

Cost to mail offer to customer:                          $.50
Selling price (shipping included):                    $18.00

Wholesale price paid by BookBinders:             $9.00

Shipping costs:                                                  $3.00

  1. Create a new variable (call it MAIL) with a value of 1 if the customer’s predicted probability is .083 or greater, and 0 otherwise. Since the breakeven response rate is 8.3%, this variable will be used to determine who gets mailed the offer and who doesn’t.
  2. Generate a report summarizing the number of customers, the number of buyers of “Art History of Florence’ and the response rate to the offer by the MAIL variable.
  3. What would the gross profit (in dollars, and also as a percentage of gross sales) and the return on marketing expenditures have been if BookBinders had mailed the offer to buy “The Art History of Florence” only to customers with a predicted probability of buying of 8.3% or greater?

 

 

  1. What are the key learning points from this assignment? What are the managerial implications of your findings?

Simply Click ORDER NOW and your paper details. Our support team will review the assignment(s) and assign the right expert whose specialization is same to yours to complete it within your deadline. Our Editor(s) will then review the completed paper (to ensure that it is answered accordingly) before we email you a complete paper 

Email Us for help in writing this paper for you at: support@customwritings-us.com

 

 

%d bloggers like this: