deletions | additions       diff --git a/textbf_Background_A_meta_analysis__.tex b/textbf_Background_A_meta_analysis__.tex  index 4804e23..5b3c00d 100644  --- a/textbf_Background_A_meta_analysis__.tex  +++ b/textbf_Background_A_meta_analysis__.tex 
...
\textbf{Background}  A meta-analysis is an array statistical techniques that aggregates a procedure for aggregating  data from multiple studiesin a systematic review  to a higher take advantage of increased  statistical power instead of relying on a single study which may have results which are biased. due to the larger sample size achieved from combining individual studies.  These meta-analyses studies  contrast and combine studies to help identify patterns, disagreements, and possible sources of bias (Greenland 2008). When multiple studies are combined in a systematic review it is only natural that there will be differences between the studies (location of testing, drug doses, dosing schedules, follow-up, ethnicity of participants, etc.). These variables, which can be classified as clinical diversity (varying participants, interventions, and outcomes studied) and methodological diversity (varying study design and risk of bias), are known as heterogeneity and is present in all systematic reviews \cite{24416692}. If significant heterogeneity is present, a meta-analysis should not be conducted due to misleading results (O’Rourke 1989). Seeing as a meta-analysis should be conducted for all systematic reviews in order to trust the results of the paper, it is then necessary to find the causes and extent of the heterogeneity between studies (Guyatt 2011). Some of the ways in which heterogeneity is explored is to perform a meta-regression or subgroup analysis of the studies present in the systematic review. Meta-regression is a method which examines the impact of study features on intervention effects, while a subgroup analysis breaks the participant data up into groups to compare and contrast the data. Classically the way in which heterogeneity is calculated is post meta-analysis by quantitative methods. Current quantitative methods used are: Cochrane Q-Weighted sum of each studies contribution, I2-Describes the percentage of total variation across studies that is due to heterogeneity rather than chance, and Tau2-The variance of the true effect size (Higgins 2002). One of the most common ways in which heterogeneity is dealt with, once it has been identified, is with a random-effects meta-analysis model which includes a term to account for heterogeneity. An alternative to dealing with heterogeneity post meta-analysis or using a modified meta-analysis model, is to qualitatively assess it prior to meta-analysis. A new method to assess heterogeneity has created with the sole purpose of “…objectively and transparently characterizing design heterogeneity prior to meta-analysis“(Althuis 2014). 
...