Hypothesis Testing

Hypothesis testing is the process of testing validity of a hypothesis or a supposition in relation to a statistical parameter. Hypothesis testing is used by analysts to determine whether or not a hypothesis is reasonable. For example, hypothesis testing could be used to find whether a certain drug is effective or not in treating headache. It uses data from a sample to draw conclusions about a statistical parameter. Hypothesis testing is an important step as it validates statistical parameter which could be used in making conclusions or inference about population or large sample data.

Types of Hypothesis

In data sampling, different types of hypothesis is used to examine whether a sample is positive for test hypothesis or not.

  1. Alternative Hypothesis (H1) – This hypothesis states that there is a relationship between two variables (where one variable affects the value of other variable). The relationship that exists between the variables is not due to chance or coincidence.
  2. Null Hypothesis (H0) – This hypothesis states that there is no relationship between two variables. It states that the effect of one variable on another is entirely due to chance, with no empirical explanation.
  3. Non-Directional Hypothesis – It states that there is a relationship between two variables, but that the direction of influence is unknown.
  4. Directional Hypothesis – It states the direction of effect of the relationship between two variables.

Alternative hypothesis and null hypothesis is used to study data samples to find a possible pattern to form a statistical hypothesis that can be validated through hypothetical testing. Alternative hypothesis and Null hypothesis cannot be true at the same time as they are mutually exclusive. Similarly, Non-directional and directional hypothesis cannot be true at the same time as they are mutually exclusive.

Methods of Hypothesis Testing

  1. Frequentist Hypothesis Testing- This is the traditional approach to hypothesis testing. It involves making assumptions on current data and comparing prior knowledge about hypothesis with posterior knowledge of the hypothesis to form a conclusion on the hypothesis. One of the subtypes of this approach is Null Hypothesis Significance Testing.
  2. Bayesian Hypothesis Testing- It is one of the modern methods of hypothesis testing. In this method prior probability of hypothesis from past data and current data is used to find posterior probability of the hypothesis.

The Bayes factor, which is a key component of this approach, represents the likelihood ratio between the null and alternative hypotheses. This factor indicates the plausibility of either of the two hypotheses formed for hypothesis testing.

 

Techniques of Hypothesis Testing

There are few commonly used Tests: Z-Test, T-Test, Chi squared Test and F-Test.

  1. Z Test- A z test is performed on a population with independent data points that follows a normal distribution and has a sample size of larger than or equal to 30. When the population variance is known, it is used to determine whether the means of two populations are equal. Z test statistic is compared to the crucial value and the null hypothesis of z test is rejected if the z test statistic is statistically significant.

 

 

 

Where,

Z= Z-test

X̄ =sample average

µ=mean

s=standard deviation

  1. T Test – A t-test is an inferential statistic that is used to see if there is a significant difference in the means of two groups that are related in some way. This test is also called as Student test. It is used when variables are continuous, sample size is less than 30, and population standard deviation is not known. T statistic is used to arrive at a conclusion on whether to accept the hypothesis or reject the hypothesis.

 

 

 

Where,

t= Student’s t-test

m= mean of sample

µ= assumed mean

s= standard deviation

n= number of observations

  1. Chi squared Test – A chi-square statistic is a test that evaluates how well a model matches actual data. For using Chi squared test the data used must be random, mutually exclusive, taken from independent variables from a large sample.

 

 

where:

c=Degrees of freedom

O=Observed value(s)

E=Expected value(s)

There are two types of χ2 test – the test of independence, and goodness-of-fit test. A χ2 test for independence can show us how likely it is that random chance can explain any observed difference between the actual frequencies in the data and these theoretical expectations.

  1. F Test – Any statistical test with an F-distribution under the null hypothesis is known as an F-test. It is generally used to compare statistical models that have been fitted to a data set to find which model best fits the population from which the data were sampled. To perform an F-test, the population must have an f distribution and the samples must be random. If the f test findings are statistically significant, the null hypothesis is rejected otherwise, it is not. F statistic for large samples:

 

 

Where,

σ12  = variance of the first population

σ22  = variance of the second population

Proper Citation: A Key Norm in Academic Publishing

What to Cite?
Academic publishing is important for the career enhancement of every researcher. A long string of publications under the belt of a researcher not only performs the constructive role of filling gaps in existing research, but also enhances the chances of the researcher being cited by other researchers. The number of times your research work is cited indicates the impact of the study in your research field.
Researchers usually draft their own investigations in the light of discoveries of other researches. In the process, it is vital for these study findings to be recognized as standalone researches by maintaining a strategic distance from issues like copyright infringements and plagiarism. To walk this academic tightrope, researchers take care to refer to previous studies by presenting the thoughts of the first researcher in one’s own writing and by referring to the earlier publication. Other than recognizing the work of different researchers, the citation process also helps readers discover the source article and refer to it to acquire more data or details.
The advent of the World Wide Web and the Internet has helped the process of identifying fitting, reliable, and logical scientific information and using it in one’s research with proper citations. The researcher takes recourse to online search tools, for example Google Scholar or PubMed, to gather information about publications revolving around the proposed research area. To disentangle the mass of search results, it is important to sieve research articles that could form part of the critical reading list.
Demonstrating In-Text Citing
The purpose of referencing or in-text citation is to give credit where it is expected. There are various reference style guides and it is up to the researcher and the requirements of the target journal to choose the most suitable one. If it’s a book citation, the author needs to consider the detailed referencing guidelines specific for books. In case of a thesis, the concerned university will have a favored reference style that needs to be followed. In case of research journals, one needs to visit the author page to peruse “Instruction for Authors.” Here, the author would get a bird’s-eye view of the required referencing style along with the in-text citation style. Once the reference style has been chosen, it is critical to remain faithful to the reference style in a consistent manner throughout the manuscript.
Here are three ways to use in-text research citations.
– Name-Year format: The surname of the first author is mentioned, followed by the publication year in brackets after the text.
For e.g.:
(Smith, 2017) or “Huron et al. (2017) stated that the tumor regeneration process was…”
– Citation-Sequence and Citation-Name: Both these citation styles are widely used by many journals. These two mainstream referencing styles are fundamentally the same. In both, in-text referencing is a number that compares to the full reference in the reference list. In case of Citation-Sequence, the number relates to every article’s ordered appearance. In case of Citation-Name format, the list of sources is arranged alphabetically. For example, if the primary article referenced in the manuscript was a work of Smith (an anonymous author name), this paper would be doled out the number 1. In the numbered book reference, if Citation-Sequence style is used, Smith would be the primary reference in the reference list. If Citation-Name style is used, the reference list would be arranged alphabetically, and the in-text number assigned to Smith would relate to whatever position Smith has in the reference list.
Hence, it is vital for a researcher or author to follow the reference style guide in an organized manner. Notably, footnotes are by and large not utilized as a part of logically written scientific work. Besides, there are style guides that demand abbreviating the journal names. For e.g.: International Journal of Civil Engineering can be abbreviated as ‎Int. J. Civ. Eng.
Fortunately, there are currently many reference management tools accessible to researchers and scientists. These tools assist academic research in maintaining consistency in reference citations with an assortment of style guides. Few examples are Mendeley, Zotero, EndNote, and Papers. These are additional reference directories, which are purchasable. However, all these reference managers also offer scholarly or understudy discounts.
Academic Publishing, Academic Research, Authors, Researchers

Sci-Hub – A New Napster for Academic Publishers

Sci-Hub or Scientific Hub is an open access online search engine that has gained popularity in the academic publishing industry in recent years. It is a repository of scholarly works with more than 58,000,000 published researches that are available for free and can be directly downloaded by the scholars.

How does it work?

Users can look up publications based on three search criteria: URL of the article, digital object identifier (DOI), and text search. The platform searches for the particular article in its library called Library Genesis (LibGen). If the platform is not able to locate the publication in LibGen, it tries to do so by using various institutional access systems. This can also enable access to articles published in the subscription mode by bypassing the paywall. These articles are usually donated by scholars or publishers.

Benefits of using Sci-Hub

This is a hub for not only research articles but other forms of research publications like monographs, books, book chapters, and so on. It offers free access to most of these researches and saves both money and time of the users. Sci-Hub shares similar goals as open access journals, making many scholarly publications available to anyone who searches for them. The site seeks to remove barriers to science through clear hints of piracy for those who cannot afford to pay the high subscription charges levied by journals or publication houses.

Sci-Hub has accomplished certain important breakthroughs. Its ambit covers many publications by scientists or researchers who have opted to publish in open access journals that can be accessed by anyone. In addition, it has brought academic publishing to the mainstream. As scientific credibility mostly depends on scientific publications, most of the chargeable journals own the copyright for their published articles. In this scenario, Sci-Hub helps researchers access these articles without any hidden cost.

Trump releases his 100 days plan- What for Science?

trump

 

 

 

 

 

 

 

Electing Donald Trump as the 45th American President will bring about scads of policy reforms, even faster than the people realize. Starting from freezing the employee recruitments to the scrapping of Obamacare initiatives are all on the list! In addition, the breakneck statements and views of Donald Trump on various scientific facts have also sparked strong reactions among academics. However, the term “Science” has turned out to be a jargon for the Republicans and has found no special mention in the 100 days plan. However, we will have a bird’s eye view on the Trump’s blueprint that he would gift the Americans and the world community this New Year, and figure out if the science facts have been addressed to.

Trump – Throwing on off Policy fetters
Trump’s hard-line positions on immigration — including his commitment towards barring Muslims or terror-prone nationals from entering the US, a plan for wall building across the Mexico borders, imbibing visa restrictions, prioritizing American workers, and the termination of job programs for foreign youths, have surely perturbed the research advocates. Such decisions could sidetrack many talented international students or researchers from studying or working at US institutions. The future of foreign research scholars in the USA could be jeopardized due to such visa restrictions.

Science Facts vs. Trump’s Contradiction- Will it affect R&D funding?
The US has been a major investor of federal dollars in the field of R&D. “The entire business of the US academic biomedical research enterprise is based on federal dollars. Without that, it would collapse,” says Ethan Weiss, an associate professor, University of California. Trump’s shockingly ignorant views on vaccination for children with autism, and calling climate change a hoax and data to be unrealistic, pulling out US (the second most carbon generator) from the Paris climate change submit), curtailing the funds to UN for supporting climate change initiatives, and calling NASA as a logistics agency, have surely put him under the scanner of the intellectuals.
As per the statement released in September, by Donald Trump, he says that “there are increasing demands to curtail spending and to balance the federal budget; we must make the commitment to invest in science, engineering, healthcare and other areas that will make the lives of Americans better, safer and more prosperous.” In an interview by sciencedebate.org, Trump added that “scientific advances do require long-term investment.” In spite of such speculations, the fate of R&D industry is too early to predict. However, before the commencement of 2017, the present US Congress Govt. could approve spending bills before Christmas. These bills will raise the National Institute of Health funding as well as the NSF budget. During the first year of Trump’s presidency, the public funding will be secured.

Uncertain change in the climate
Trump’s election could factor into climate negotiations and be a setback for the upcoming climate change meets. When the world is thinking of implementing Paris agreement, the exit of the US from the Paris summit can be an unfortunate development and the pledge of 800 million USD as the annual contribution to the United Nations Framework Convention on Climate Change may cease. However, legally Trump would not be able to sign off the Summit within his four years tenure.

Donald trump on Healthcare reforms
The Affordable Care Act, an initiative by Obama, which is in its current incarnation, won’t survive if Trump makes good on his campaign promises. By this logic, the funds linked to birth control programs would fade away, though not immediately. Trump may defund Obamacare and associated programs like state grant for medical care. A Trumpian shift to insurance premium deductions and insurance plans sales and the opening of tax-free Health Savings Accounts may not remedy the ultimate problem of high-cost health care services in the US.

Tech Boost and Trump
The Silicon Valley may be benefitted by the manufacturing revival initiative by Trump’s govt. “There are several things that a Trump administration could do that would be beneficial to tech,” says Rob Atkinson, president of the Information Technology and Innovation Foundation. The export industry will flourish over the import, which will be part and parcel of the shifting away from the traditional start-up model and the adjusted tax and trade policy.

We know very little
The research policies and development across a wide spectrum in the US political scenario are still up in the air and have kept the scientific community optimistic (though cautiously). The outcomes of Trump’s immigration policies are also not clear. This is considered as the central pillar of his campaign, which might or might not affect research. Leighton Ku, a professor at George Washington University, said that “it’s likely that the kinds of highly-skilled scientists who immigrate to the US for school or work would still be welcome. But will they want to come?” This is a billion dollar question that still remains unanswered.

Choosing a journal: Open access or traditional publication?

journal selection : Open access or traditional publication

What is open access publishing?

Open access (OA) publishing provides researchers and readers free access to research articles online. In case of OA journals, an article processing fee is levied on the authors after acceptance of the paper. This charge is payable by the researcher, author or the institution the author is affiliated to. However, certain OA journals do not charge any fee and support their operations through sponsorship or subscriptions of the journals.

What is traditional publishing?

Traditional publishing refers to a type of contract between the author and the publisher. In this type of publishing, the author receives a portion of the revenue generated from sales of the journals. This is also known as the “royalty payment model.”

Which route to adopt?

Various factors play a determining role for authors adopting either the open access or the traditional route for publication.

Many researchers consider the open access model as economically unsustainable because it imposes an additional financial burden on them as well as on the institute they are affiliated to. But again, it comes with a basket-full of advantages, such as a much quicker publication process compared to the traditional mode and enhanced visibility of the research to a broader audience. On the other hand, traditional publications have incorporated many reforms in their business models. They ensure manuscript quality and a brand value.

Many publishing houses place the onus on the author. They give authors the choice of either disseminating the research to a wide research community through an OA publication, or opting for the traditional mode of publication.

With the advent of the Internet, we are habituated to rapid changes in business models of the publication industry. However, the journal publication business has been relatively more resistant to change. That is a function of the prevailing academic culture, where the importance of a publication is recognized through the brand value of journals and their ability to promote the publication and win research grants.

Preparing tables for research papers

How to effectively prepare tables for research papers

Tables and illustrations are important tools for efficiently communicating information and data contained in your research paper to the readers. They present complex results in a comprehensible and organized manner.

However, it is advisable to use tables and illustrations wisely so as to maximize the impact of your research.They should be organized in an easy-to-understand format to convey the information and findings collected in your research. The tabular information helps the reader identify the theme of the study more readily. Although data tables should be complete,they should not be too complex. Instead of including a large volume of data in a single unwieldy table, it is prudent to use small tables to help readers identify the important information easily.

Here are some points you should consider before drafting the tables in your research paper:

  • Finalize the results that are required to be presented in tabular form.
  • Include the data or results that are relevant to the main aim of the study without being choosy and including only those results that support your hypothesis.
  • Create each table in a lucid manner and style without cluttering it with in-table citations.
  • Number the tables in a sequence according to their occurrence in the text.
  • Don’t mix tables with figures. Maintain separate numbering systems for tables and figures.
  • Create tables in a storytelling manner. Remember that your tables communicate a story to the reader that runs parallel to the text.
  • If you are using or reproducing tables from other published articles, obtain permission from the copyright holder (usually the publisher) or/andacknowledge the source.
  • Do not repeat the tabular contents in the text again; that will create confusion among readers.
  • Use clear and informative text for each table title.
  • Take extra care while extending the data in your tables. If you have too many tables, consider using them as appendices or supplementary materials.
  • Create tables with sufficient spacing in the layout so that they do not look messy, crowded, or cluttered.
  • Do not forget to spell out abbreviations used in the tables, ideally in the footnotes.

For the reader, a research paper that is dense and text-heavy can be tiresome. Conversely, tables not only encapsulate your data lucidly, but also welcome a visual relief for the reader. They add value to the layout of your paper. Besides, and more importantly, reviewers often glance at your tabulated data and illustrations first before delving into the text. Therefore, tables can be the initial draw for a reviewer and deliver a positive impact about your research paper. If you can achieve an optimum balance among your text, tables, and illustrations, it can go a long way toward being published.

Preparing your figures for research papers

How to prepare your figures for research papers

Often a research paper is embedded with loads of data and complex results and it might not be viable to include all them in the space-constrained paper. Hence, this calls for effective presentation of the information in the form of figures or diagrams. In fact, figures are the most powerful tools that leave a strong visual impact for both reviewers and readers.

Here are few tips on how you can improve the presentation of figures in your research paper.

  • Ensure that the components of the figures are clearly visible including the lines and text.
  • Always use a standard font style and size for the figure text.
  • Every figure needs to have a legend. The legend should support your figure entirely. The reader should be able to understand your figure, paired with its legend, without going to the results or method sections.
  • All abbreviations in the figure legends need to be consolidated and spelt out.
  • All parts of the figure need to be labelled. The symbols, lines, colors, abbreviations, error bars, scale bars, and other components need to be defined and described properly.
  • If you are using photographs of your human subjects, don’t forget to obtain an informed signed consent for the same.
  • Do not be afraid to use lengthy figure and table captions—better that than confusing or incomplete ones.
  • Do not forget to cite the figure that has been taken from another source and supports your present study. Use the same citation style throughout the paper.
  • All journals have their specific requirements for formatting figures, such as file format, font size, font style, image resolution, style of numbering, etc. Adhere to these guidelines before submission. You can learn more about fonts and styles if you are not familiar with them.
  • Cite figures in the main text at the appropriate place where the text is supported by a particular figure.

The figures in your research paper communicate a parallel story to the reader. In fact, the reader can derive a fairly good idea of your paper by just scanning the figures in the paper. Remember that figures are not just tools to beautify your text; they are the heart of your research and an intrinsic part of your research paper. This highlights the importance of organizing the figures well so that they are able to perform as an excellent prop for your text.

Research problem: A statement of intent

Research problem: A statement of intent
How do I devise my research problem?

A research problem is a statement based on the area of research, which is the first step in a research process. Devising an appropriate research problem depends on the in-depth knowledge, skills, and expertise of a researcher in their particular subject field. Therefore, a researcher needs to devote considerable time to select a suitable research problem.

Steps to formulate a research problem

There are two essential steps to follow while selection:

  • Identification of a research problem
  • Selection of a broad research topic and narrowing it down to a precise statement.

Sources to derive a research problem

Several factors, both extraneous and intrinsic to the research per se, help the researcher in identifying a research problem. They include the following:

  • Field conditions: The rich experiences in the field provide relevant ideas for developing an apt research problem.
  • Personal experience: This might help generate new ideas for formulating the research problem.
  • Previous related researches and theories, and critical review of the available literature: Relevant questions might crop up in our mind when we evaluate the articles, reports and reviews related to the subject area.
  • Expert advice: Subject matter experts are vastly experienced in the field of study. Hence, they may help the researcher find the current problem related to the research, and even devise a research problem.

What should be the nature of the research problem?

There are several guidelines that need to be followed while selecting a research problem. Your research problem needs to be:

  • An original and unique one.
  • An encapsulation of the nature of research.
  • Feasible vis-a-vis time required for its completion.
  • A realistic statement that can be achieved with the available financial resources.
  • Backed by support from your affiliated institution and peers.
  • Formulated in accordance with ethical considerations.
  • Based on recent or current problems persistent in the field of study.

Types of research problems

Research problems can vary according to the field of study and the scope of the research. Basically, there are three types of research problems:

  • Descriptive
  • Relative
  • Casual

A well-framed and appropriate research problem presents the researcher’s view in a clear and lucid manner, and helps readers understand the purpose of the research better.

Authorship Disputes: Tips to avoid conflicts

‘Tips to avoid Authorship DisputesAuthorship’ denotes the practice of providing truthful credits for intellectual contributions and innovative concepts. It not only helps authors acquire the credit for the work, but also ensures that they assume responsibility for the research conducted and presented. Moreover, it is perceived as a tool for personal satisfaction, prestige, and especially, a stepping stone in a writer’s academic career. Though the term sounds interesting, it involves high risks and problems in practice.

The Committee on Publication Ethics (COPE) often receives disputes regarding authorship. These cases usually involve disputes like the omission of a deserving junior researcher’s name from the authors’ list or a proposal by a sponsor for including the name of a non-contributing author. However, it also received a shocking complaint from a female author, who said that her name was replaced with that of her boss in the final version when she was away on maternity leave.

Apart from having a direct impact on the publication in question, authorship disputes can also have repercussions on a writer’s fair credit, collegial relationships, future collaborations, and reputations.

Following the adage that prevention is better than cure, the following are some guiding principles to avoid conflicting situations like authorship disputes.

  • Adhere to the authorship criteria of the publication

Each publisher follows specific authorship guidelines enunciated by organizations such as the International Committee of Medical Journal Editors (ICMJE), World Association of Medical Editors (WAME), Council of Science Editors (CSE), Committee on Publication Ethics (COPE), and Good Publication Practice (GPP2). Non-compliance with the concerned guidelines—i.e., unequal application of authorship criteria, granting authorship to undeserving individuals, and/or omitting authorship to deserving individuals—is considered to be a serious offense in the academic world and can be construed as  research misconduct.

  • Hold prior discussions with co-authors

All the authors of a paper should discuss and finalize the authorship order and contributions along with respective responsibilities before beginning to prepare a manuscript and, if possible, even before starting a study.

  • Stick to the plan of action

In few cases, it has been observed that even if the authors have agreed to the sequence of authorship and contributions, fraudulent authors make last-minute changes in the manuscript or research paper just before submission. This leads to conflicts in publishing the paper, and some even end with retraction of the paper. To avoid such anomalies and unpleasant situations, it is advisable to comply with the agreement made between the author and co-authors.

However, even the best plans sometimes fail. So it is better to track and revisit the issues and monitor any changes or modifications in authorship or contributions. If one discovers any changes before publication, it can be revised after discussions with the co-authors. Conversely, if the detection is made post-publication, one can contact the journal along with the written agreements and evidence of contributions, and request for a correction or a retraction of the paper.

Thalidomide: Is it the next-gen cancer drug?

History of the wonder drug “Thalidomide”

In 1957, thalidomide was first marketed under the trade name Contergan in Germany. It is one of the most widely used immunotherapeutic agents to treat immune responses that involve suppression or induction of the immune system. It was prescribed as a sedative in cases of hypertension, sleeplessness or insomnia, and anxiety attacks.

Thalidomide was subsequently administered to pregnant women to reduce the symptoms of morning sickness and nausea. However, the drug was found to cause deformities in the neonates. The deformity, called phocomelia, mainly affected the limbs. It was concluded that thalidomide causes two major health complications: Embryo-Fetal Toxicity and Venous Thromboembolism. Besides, risks increase significantly when the drug is used in combination with other potent chemotherapeutics, such as dexamethasone.

Potential of thalidomide

Despite its dark past, thalidomide has many beneficial attributes that are continuously being explored by researchers and scientists. In fact, thalidomide is now being considered as an effective drug for treating cancer, especially blood cancer known as myeloma.

The drug is found to inhibit the COX-2 gene activity that plays a vital role in the upregulation of cancer. Another wider class protein called NF-κB is an active regulator of anti-apoptotic factors.  This protein is also inhibited by thalidomide. Thalidomide elevates the levels of immune cells, such as T-cells and natural killer cells.

Although researches on thalidomide as a potential cancer therapy drug are yet to reach a conclusion, they have shown the efficacy of the drug in shrinking and attenuating malignant tumors.

There are other drugs available in the market with similar cancer treating properties as thalidomide, but they are not cost-effective and have many side effects. Conversely, thalidomide is cheaper and off-patent, which makes it more conducive for exploring its potency in cancer treatment.