Statistical Analysis - Create questions and analyis

© Open Polytechnic 1

Here’s an example of what your report might look like. A covering memo and a Terms of

Reference are not required, but a Title page is. Including an Executive Summary or Abstract

is optional. You may prefer to use alternative terms (for example Procedure instead of

Methodology) in line with reports you have written for other subjects. Further help on

writing reports is found here:

http://www.openpolytechnic.ac.nz/study-with-us/study-resources-for-

students/assignments/types-of-assignments/reports/how-to-write-a-report/

Title Page (This will include your full name, student number and the title of your report.)

Table of Contents (This lists the sections below.)

1. Introduction to topic and aims (Give a general discussion about your topic, discuss why the questions you are asking are important and include two or more

clearly stated aims.)

(Title page, Table of Contents, Introduction: 20 marks)

2. Data

2.1 Data description (Give a general description of the data, its source, how it was collected and name and describe the variables you will be using.) 2.2 Method of sampling (Say how your sampling was done and state the sample size.) (Data description, method of sampling: 10 marks)

3. Data analysis 3.1 Methodology (Give a brief description of the analysis which will follow.) 3.2 Analysis (Show your analysis here – an example is shown on page 3 of this document)

(Methodology, data analysis: 40 marks)

4. Conclusions (Summarise your findings in the context of your topic/aims and discuss the implications).

5. Recommendations (Not all reports will have recommendations.) (Conclusion, recommendations: 20 marks)

6. List of references (Data and any publications used should be referenced in correct APA format. You do not need to reference information obtained from the

set text.)

72160 Statistical Analysis

Assignment 4 formatting instructions

72160 Statistical Analysis Assignment 4 formatting instructions

© Open Polytechnic 2

7. Appendices (Include a sample of your data and manual workings or computer output.)

(Presentation, referencing: 10 marks)

Headings: Use bold headings, with larger font for main headings. Imagine this is a

business report and you are preparing it for publication.

Tables: Tables should be labelled Table 1, Table 2 in the order they occur. This should go

above the table and on the following line there should be a title in italics.

For example:

Table 1

Means and standard deviations of cooking times

Mean (mins) Standard deviation (mins)

Men 42 23

Women 39 6

The table must be clear and easily ready. Data and headings should be centred. If you are

copying summary statistic tables from Excel or other software, delete any unnecessary

values, round to an appropriate number of decimal places and put in the units of

measurement.

Graphs. Graphs should be labelled Figure 1, Figure 2 etc below the graph, with a title. For

example

Figure 1: Normal quantile plot of density of the earth.

72160 Statistical Analysis Assignment 4 formatting instructions

© Open Polytechnic 3

It is optional whether you put a title on the graph as well as below it.

Appendices. This should start on a new page and be labelled Appendix. If there are more

than one, start each on a new page and label as Appendix A, Appendix B etc.

Page breaks. As we will be marking online, you need to use page breaks to keep the

correct pagination. Use the keyboard shortcut: Ctrl + Enter in all versions of Word. Put a

page break after your title page, after your Table of Contents and between appendices.

Keep all tables on one page, rather than splitting them in the middle.

Footer. Insert a footer and include your full name, student number, 72160 Assignment 4

and page numbers in this footer. On Word 2010 and 2007 this is on the Insert ribbon. On

Word 2003 use View, Header and Footer and hover over the icons to see the one which

switches between header and footer.

APA referencing style. If you refer to any publications, you must cite and reference these

correctly. You can find help with referencing on the main Online Campus page under Find

Support.

Here’s an example of what the analysis section might look like.

3. Data Analysis

3.1 Methodology

(Give a brief description of the analysis which will follow)

3.2 Analysis

3.2.1 Comparison of mean cooking times taken by men and women

To compare the mean times taken by men and women to complete the task of cooking

dinner, the following side-by-side boxplots were prepared.

(Insert your graph here)

As can be seen, there appears to be little difference in median times, which are around

40 minutes. However, the men have one observation at 240 minutes, which appears

to be an outlier. Use of the 1.5IQR rule confirms this (see Appendix D). This

observation was checked for authenticity, found to be a legitimate value and retained

for further analysis. The minimum times are similar for both men and women at

around 20 minutes.

The means and standard deviations for cooking time are given in the following table.

(Insert your table here)

Although the means are similar, the men’s times have more variation.

A two-sample t test confirms that there is no statistically significant difference in mean

times taken. Using a one-sided alternative hypothesis that men take longer than

women, on average, to cook dinner, the hypotheses for this were:

0 :

w m H  

72160 Statistical Analysis Assignment 4 formatting instructions

© Open Polytechnic 4

: a w m

H  

The test is valid as the sum of the sample sizes exceeds 40.

Results show t(80) = 1.01, P = 0.17 (see software output in Appendix E). This large P-

value means that there is no evidence to reject 0

H and I can conclude that ... .

3.2.2 Comparison of average number of dishes used by men and women

…..

72160 Statistical Analysis Assignment 4 formatting instructions

© Open Polytechnic 5

Reporting results of descriptive and inferential statistics in APA format

Important note: APA presentation of statistical results is outlined as follows, but you

will not be penalised for not using this style. You will notice that some symbols are not

consistent with what has been used in our course (e.g. APA style uses M for sample

mean, rather than for median) and some formats are not what we have taught as

good practice (e.g. APA style has no leading zeros in decimal numbers less than 1). To

maintain consistency with our course textbook, we recommend you use the

conventions you have used during the trimester and follow the examples above.

In reporting the results of statistical tests, report the descriptive statistics (means and

standard deviations), the test statistic, degrees of freedom, obtained value of the test, and

the p-value. Test statistics and p-values should be rounded to two decimal places. All

statistical symbols that are not Greek letters should be italicised (M, SD, n, t, p, etc.)

Tables are useful if you find that a paragraph has almost as many numbers as words. If you

do use a table, do not also report the same information in the text. It's either one or the

other.

Use a zero before the decimal point with numbers that are less than 1 when the statistic can

exceed 1 (e.g. 0.75 cm). Do not use a zero before a decimal fraction when the statistic

cannot be greater than 1 (e.g. correlation, proportion and levels of statistical significance).

Mean and Standard Deviation are most clearly presented in parentheses:

In the sample of 100 Statistical Analysis students the average Assignment 1 mark was

relatively high (M = 72.5%, SD = 9.4%).

In the Statistical Analysis course the average Assignment 1 mark for the sample of

100 students was 72.5% (SD = 9.4%).

Percentages are also most clearly displayed in parentheses with no decimal places:

Nearly half (49%) of participants in the sample were working full time.

Correlation:

The two variables were strongly correlated, R = .91.

Regression results are often best presented in a table. APA doesn't say much about how to

report regression results in the text. You may use the following format:

Consumption = 225.75 + 0.86 Income, R = .89, R 2 = 79%

Confidence interval should be presented in squared parentheses with confidence level:

Mean: M = $300.5, 95% CI [$255.75, $344.25]

72160 Statistical Analysis Assignment 4 formatting instructions

© Open Polytechnic 6

Proportion: p = .55, 95% CI [.45, .65]

p-values

p = value (no leading zeros); e.g. p = .07

p < .01 (if the value is less than .01)

t-test should be include test statistic, degrees of freedom, value of the test and p-value,

i.e. t(df) = value, p-value:

one sample t-test: One sample t-test showed that the difference in quiz scores between

the current sample (n = 6, M = 3.45, SD = 2.11) and the

hypothesized value (µ = 3.00) was not statistically significant, t(5) =

1.25, p = .26, 95% CI [1.24, 5.66].

two sample t-test: Two sample t-test showed that the difference in Assignment 1 marks

between Statistical Analysis students in Trimester 1 and Trimester 2

was marginally significant, t(5) = 1.25, p = .08.

match pairs t-test: The 25 participants had an average difference from pre-test anxiety

scores of -4.8 (SD = 5.5), indicating the anxiety treatment resulted in

significant decrease in anxiety levels, t(24) = -4.36, p < .01 (one-

tailed).

Chi-square statistics are reported with degrees of freedom and sample size in

parentheses, and p-value:

As can be seen by the counts in the two-way table in Table xx, there is a significant

relationship between marital status and depression, χ 2 (3, n = 126) = 24.7, p < .01.

The relationship between these variables was not significant, χ 2 (1, n = 100) = 1.96, p

= .15. Whether the students posting their coursework activities or not did not differ by

gender.

Based on:

American Psychological Association. (2010). Publication manual of the American

Psychological Association (6 th ed.). Washington, DC: Author.