Using propensity score matching to construct experimental stimuli

Huber, Stefan; Dietrich, Julia; Nagengast, Benjamin; Moeller, Korbinian

doi:10.3758/s13428-016-0771-8

Cited by 17 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After exclusion, data from 683 patients were retrospectively collected for further analysis, including date from 325 patients in the RADG group and 358 patients in the LADG group. To reduce the effect of patient selection bias between the two surgical methods, we conducted PSM based on a linear model with a caliper value of 0.01 (one-to-one nearest neighbor matching) 15,16 . Covariate analysis of the linear model included all the clinical characteristics shown in Table 1.…”

Section: Methodsmentioning

confidence: 99%

Robotic- versus laparoscopic-assisted distal gastrectomy with D2 lymphadenectomy for advanced gastric cancer based on propensity score matching: short-term outcomes at a high-capacity center

Shi

Liu

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Reports in the field of robotic surgery for gastric cancer are increasing. However, studies only on patients with advanced gastric cancer (AGC) are lacking. This retrospective study was to compare the short-term outcomes of robotic-assisted distal gastrectomy (RADG) and laparoscopic-assisted distal gastrectomy (LADG) with D2 lymphadenectomy for AGC. From December 2014 to November 2019, 683 consecutive patients with AGC underwent mini-invasive assisted distal gastrectomy. Propensityscore matching (PSM) analysis was conducted to reduce patient selection bias. Short-term outcomes were compared between the two groups. The clinical features were well matched in the PSM cohort. Compared with the LADG group, the RADG group was associated with less operative blood loss, a lower rate of postoperative blood transfusion, less volume of abdominal drainage, less time to remove abdominal drainage tube, retrieved more lymph node, and lower rates of surgical complications and pancreatic fistula (P <0.05). However, the time to recovery bowel function, the length of postoperative stay, the rates of other subgroups of complications and unplanned readmission were similar between the two groups (P > 0.05). This study suggests that RADG is a safe and feasible technique with better short-term outcomes than LADG for AGC.Gastric cancer continues to be a major public health problem worldwide, especially in developing countries, such as China 1,2 . Every year, approximately 680,000 new patients are diagnosed with gastric cancer in China; among them, more than 80% of these patients have advanced-stage disease 1,3 . For patients with advanced gastric cancer (AGC), multidisciplinary comprehensive treatment is usually required, and gastrectomy with lymph node dissection is currently considered to be the only curable treatment 4 .In the past few decades, with the development of science and technology, much advanced surgical equipment has been invented, particularly in the field of mini-invasive surgery (MIS). Since laparoscopy-assisted Billroth I gastrectomy was first reported in 1994, several randomized controlled trials (RCTs) have demonstrated that laparoscopic gastrectomy (LG) for AGC is a safe and feasible technique with better short-term outcomes than and similar oncological outcomes to open gastrectomy [5][6][7][8][9] . Although LG has obtained greater acceptance among abdominal surgeons, because of the limitations of laparoscopic instruments, it is difficult to perform precisely, as is the case with D2 lymphadenectomy 10,11 .Robotic surgery systems, as another MIS method, were invented to overcome the drawbacks of laparoscopy and are becoming increasingly accepted by abdominal surgeons. Since Hashizume et al. first reported the use of robotic surgery for gastric cancer in 2002, a number of studies have shown the safety and advantages of robotic

show abstract

Section: Methodsmentioning

confidence: 99%

Robotic- versus laparoscopic-assisted distal gastrectomy with D2 lymphadenectomy for advanced gastric cancer based on propensity score matching: short-term outcomes at a high-capacity center

Shi

Liu

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…There may also be circumstances in which continuous statistics are not available or relevant: in many medical and policy-based studies, groups are truly categorical (e.g., control and experimental). In such cases, existing algorithms (Armstrong et al, 2012; Coupé, 2011; Huber et al, 2017; Van Casteren & Davis, 2007) can be viewed as an alternative to dynamic allocation or matching techniques to assign individuals to treatment groups. Even here, though, care must be taken with statistical tests deployed in studies using dynamic allocation (Pond, 2011).…”

Section: Discussionmentioning

confidence: 99%

“…(See Hirano, Imbens, and Ridder (2003) and Caliendo and Kopeinig (2008) for more on the assumptions and implementation of PSM.) Indeed, an algorithmic tool for ex ante item selection based on PSM has recently been proposed (Huber, Dietrich, Nagengast, & Moeller, 2017).…”

Section: Introductionmentioning

confidence: 99%

“…Under circumstances in which dichotomization is appropriate, existing algorithmic implementations (Armstrong et al, 2012; Coupé, 2011; Huber et al, 2017; Van Casteren & Davis, 2007) are well-suited to efficiently selecting subsets while avoiding bias. However, dichotomization has well-known limitations, including a cost in statistical power (Cohen, 1983; Gelman & Park, 2009; Iacobucci, Posavac, Kardes, Schneider, & Popovich, 2015a, 2015b; McClelland, Lynch Jr., Irwin, Spiller, & Fitzsimons, 2015; Rucker, McShane, & Preacher, 2015).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Danger of Testing by Selecting Controlled Subsets, with Applications to Spoken-Word Recognition

Liben-Nowell

Strand

Sharp

et al. 2019

Journal of Cognition

View full text Add to dashboard Cite

When examining the effects of a continuous variable x on an outcome y , a researcher might choose to dichotomize on x , dividing the population into two sets—low x and high x —and testing whether these two subpopulations differ with respect to y . Dichotomization has long been known to incur a cost in statistical power, but there remain circumstances in which it is appealing: an experimenter might use it to control for confounding covariates through subset selection, by carefully choosing a subpopulation of Low and a corresponding subpopulation of High that are balanced with respect to a list of control variables, and then comparing the subpopulations’ y values. This “divide, select, and test” approach is used in many papers throughout the psycholinguistics literature, and elsewhere. Here we show that, despite the apparent innocuousness, these methodological choices can lead to erroneous results, in two ways. First, if the balanced subsets of Low and High are selected in certain ways, it is possible to conclude a relationship between x and y not present in the full population. Specifically, we show that previously published conclusions drawn from this methodology—about the effect of a particular lexical property on spoken-word recognition—do not in fact appear to hold. Second, if the balanced subsets of Low and High are selected randomly, this methodology frequently fails to show a relationship between x and y that is present in the full population. Our work uncovers a new facet of an ongoing research effort: to identify and reveal the implicit freedoms of experimental design that can lead to false conclusions.

show abstract

“…Thus, systematic approaches to stimulus selection are of great importance. Fortunately systematic methods and software packages for stimulus selection are readily available [201,[208][209][210]. To facilitate the adoption of systematic approaches to stimulus selection within the SMID, we have written a generic stimulus selection script for use with the SOS toolbox for MATLAB [201], along with a generic image rating task script programmed using the Python library PsychoPy [211].…”

Section: Applications and Recommendations For Usementioning

confidence: 99%

The Socio-Moral Image Database (SMID): A Novel Stimulus Set for the Study of Social, Moral and Affective Processes

Crone¹,

Bode²,

Murawski³

et al. 2017

Preprint

View full text Add to dashboard Cite

A major obstacle for the design of rigorous, reproducible studies in moral psychology is the lack of suitable stimulus sets. Here, we present the Socio-Moral Image Database (SMID), the largest standardized moral stimulus set assembled to date, containing 2,941 freely available photographic images, representing a wide range of morally (and affectively) positive, negative and neutral content. The SMID was validated with over 820,525 individual judgments from 2,716 participants, with normative ratings currently available for all images on affective valence and arousal, moral wrongness, and relevance to each of the five moral values posited by Moral Foundations Theory. We present a thorough analysis of the SMID regarding (1) inter-rater consensus, (2) rating precision, and (3) breadth and variability of moral content. Additionally, we provide recommendations for use aimed at efficient study design and reproducibility, and outline planned extensions to the database. We anticipate that the SMID will serve as a useful resource for psychological, neuroscientific and computational (e.g., natural language processing or computer vision) investigations of social, moral and affective processes. The SMID images, along with associated normative data and additional resources are available at https://osf.io/2rqad/.

show abstract

Using propensity score matching to construct experimental stimuli

Cited by 17 publications

References 33 publications

Robotic- versus laparoscopic-assisted distal gastrectomy with D2 lymphadenectomy for advanced gastric cancer based on propensity score matching: short-term outcomes at a high-capacity center

Robotic- versus laparoscopic-assisted distal gastrectomy with D2 lymphadenectomy for advanced gastric cancer based on propensity score matching: short-term outcomes at a high-capacity center

The Danger of Testing by Selecting Controlled Subsets, with Applications to Spoken-Word Recognition

The Socio-Moral Image Database (SMID): A Novel Stimulus Set for the Study of Social, Moral and Affective Processes

Contact Info

Product

Resources

About