Dataset Information

The fallacy of ratio correction to address confounding factors.

ABSTRACT: Scientists aspire to measure cause and effect. Unfortunately confounding variables, ones that are associated with both the probable cause and the outcome, can lead to an association that is true but potentially misleading. For example, altered body weight is often observed in a gene knockout; however, many other variables, such as lean mass, will also change as the body weight changes. This leaves the researcher asking whether the change in that variable is expected for that change in weight. Ratio correction, which is often referred to as normalization, is a method used commonly to remove the effect of a confounding variable. Although ratio correction is used widely in biological research, it is not the method recommended in the statistical literature to address confounding factors; instead regression methods such as the analysis of covariance (ANCOVA) are proposed. This method examines the difference in means after adjusting for the confounding relationship. Using real data, this manuscript demonstrates how the ratio correction approach is flawed and can result in erroneous calls of significance leading to inappropriate biological conclusions. This arises as some of the underlying assumptions are not met. The manuscript goes on to demonstrate that researchers should use ANCOVA, and discusses how graphical tools can be used readily to judge the robustness of this method. This study is therefore a clear example of why assumption testing is an important component of a study and thus why it is included in the Animal Research: Reporting of In Vivo Experiment (ARRIVE) guidelines.

SUBMITTER: Karp NA

PROVIDER: S-EPMC4152922 | biostudies-other | 2012 Jul

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

The fallacy of ratio correction to address confounding factors.

Karp Natasha A NA Segonds-Pichon Anne A Gerdin Anna-Karin B AK Ramírez-Solis Ramiro R White Jacqueline K JK

Laboratory animals 20120701 3

Scientists aspire to measure cause and effect. Unfortunately confounding variables, ones that are associated with both the probable cause and the outcome, can lead to an association that is true but potentially misleading. For example, altered body weight is often observed in a gene knockout; however, many other variables, such as lean mass, will also change as the body weight changes. This leaves the researcher asking whether the change in that variable is expected for that change in weight. Ra ...[more]

PMID: 22829707

Similar Datasets

Project description:Assessing algal nutrient limitation is critical for understanding the interaction of primary production and nutrient cycling in streams, and nutrient diffusing substrate (NDS) experiments are often used to determine limiting nutrients such as nitrogen (N) and phosphorus (P). Unexpectedly, many experiments have also shown decreased algal biomass on NDS P treatments compared to controls. To address whether inhibition of algal growth results from direct P toxicity, NDS preparation artifacts, or environmental covariates, we first quantified the frequency of nutrient inhibition in published experiments. We also conducted a meta-analysis to determine whether heterotrophic microbial competition or selective grazing could explain decreases in algal biomass with P additions. We then deployed field experiments to determine whether P-inhibition of algal growth could be explained by P toxicity, differences in phosphate cation (K vs. Na), differences in phosphate form (monobasic vs. dibasic), or production of H2O2 during NDS preparation. We found significant inhibition of algal growth in 12.9% of published NDS P experiments as compared to 4.7% and 3.6% of N and NP experiments. The meta-analysis linear models did not show enhanced heterotrophy on NDS P treatments or selective grazing of P-rich algae. Our field experiments did not show inhibition of autotrophic growth with P additions, but we found significantly lower gross primary productivity (GPP) and biomass-specific GPP of benthic algae on monobasic phosphate salts as compared to dibasic phosphate salts, likely because of reduced pH levels. Additionally, we note that past field experiments and meta-analyses support the plausibility of direct P toxicity or phosphate form (monobasic vs. dibasic) leading to inhibition of algal growth, particularly when other resources such as N or light are limiting. Given that multiple mechanisms may be acting simultaneously, we recommend practical, cost-effective steps to minimize the potential for P- inhibition of algal growth as an artifact of NDS experimental design.

Project description:Targeted proTargeted protein degradation has recently emerged as a novel option in drug discovery. Natural protein half-life is expected to affect the efficacy of degrading agents, but it has not been systematically explored to what extent it influences target protein degradation. Using mathematical modelling of protein degradation, we demonstrate that the natural half-life of a target protein has a dramatic effect on the level of protein degradation induced by a PROTAC which can pose significant hurdles to screening efforts. Moreover, we show that upon screening for degraders of short-lived proteins, agents that stall protein synthesis, such as GSPT1 degraders and generally cytotoxic compounds, deceptively appear as protein degrading agents. This is exemplified by the disappearance of short-lived proteins such as MCL1 and MDM2 upon GSPT1 degradation and upon treatment with cytotoxic agents such as doxorubicin. These findings have implications for target selection as well as for the type of control experiments required before concluding that a novel agent works as a bone-fide targeted protein degrader. tein degradation has recently emerged as a novel option in drug discovery. Natural protein half-life is expected to affect the efficacy of degrading agents, but it has not been systematically explored to what extent it influences target protein degradation. Using mathematical modelling of protein degradation, we demonstrate that the natural half-life of a target protein has a dramatic effect on the level of protein degradation induced by a PROTAC which can pose significant hurdles to screening efforts. Moreover, we show that upon screening for degraders of short-lived proteins, agents that stall protein synthesis, such as GSPT1 degraders and generally cytotoxic compounds, deceptively appear as protein degrading agents. This is exemplified by the disappearance of short-lived proteins such as MCL1 and MDM2 upon GSPT1 degradation and upon treatment with cytotoxic agents such as doxorubicin. These findings have implications for target selection as well as for the type of control experiments required before concluding that a novel agent works as a bone-fide targeted protein degrader.

Project description:In oncology trials, control group patients often switch onto the experimental treatment during follow-up, usually after disease progression. In this case, an intention-to-treat analysis will not address the policy question of interest - that of whether the new treatment represents an effective and cost-effective use of health care resources, compared to the standard treatment. Rank preserving structural failure time models (RPSFTM), inverse probability of censoring weights (IPCW) and two-stage estimation (TSE) have often been used to adjust for switching to inform treatment reimbursement policy decisions. TSE has been applied using a simple approach (TSEsimp), assuming no time-dependent confounding between the time of disease progression and the time of switch. This is problematic if there is a delay between progression and switch. In this paper we introduce TSEgest, which uses structural nested models and g-estimation to account for time-dependent confounding, and compare it to TSEsimp, RPSFTM and IPCW. We simulated scenarios where control group patients could switch onto the experimental treatment with and without time-dependent confounding being present. We varied switching proportions, treatment effects and censoring proportions. We assessed adjustment methods according to their estimation of control group restricted mean survival times that would have been observed in the absence of switching. All methods performed well in scenarios with no time-dependent confounding. TSEgest and RPSFTM continued to perform well in scenarios with time-dependent confounding, but TSEsimp resulted in substantial bias. IPCW also performed well in scenarios with time-dependent confounding, except when inverse probability weights were high in relation to the size of the group being subjected to weighting, which occurred when there was a combination of modest sample size and high switching proportions. TSEgest represents a useful addition to the collection of methods that may be used to adjust for treatment switching in trials in order to address policy-relevant questions.

Dataset Information

The fallacy of ratio correction to address confounding factors.

Publications

The fallacy of ratio correction to address confounding factors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets