scholarly journals Learning a Frequency-Matching Grammar together with Lexical Idiosyncrasy: MaxEnt versus Hierarchical Regression

2019 ◽  
Vol 7 ◽  
Author(s):  
Jesse Zymet
Keyword(s):  
Regression Model ◽  
Language Learners ◽  
Fixed Effects ◽  
Random Effect ◽  
Hierarchical Regression ◽  
Harmonic Grammar ◽  
Frequency Matching ◽  
Recent Approach ◽  
General Constraints ◽  
Lexical Constraints

Experimental research has uncovered language learners’ ability to frequency-match to statistical generalizations across the lexicon, while also acquiring the idiosyncratic behavior of individual attested words. How can we model the learning of a frequency-matching grammar together with lexical idiosyncrasy? A recent approach based in the single-level regression model Maximum Entropy Harmonic Grammar makes use of general constraints that putatively capture statistical generalizations across the lexicon, as well as lexical constraints governing the behavior of individual words. I argue on the basis of learning simulations that the approach fails to learn statistical generalizations across the lexicon, running into what I call the GRAMMAR-LEXICON BALANCING PROBLEM: lexical constraints are so powerful that the learner comes to acquire the behavior of each attested form using only these constraints, at which point the general constraint is rendered superfluous and ineffective. I argue that MaxEnt be replaced with the HIERARCHICAL REGRESSION MODEL: multiple layers of regression structure, corresponding to different levels of a hierarchy of generalizations. Hierarchical regression is shown to surmount the grammar-lexicon balancing problem—learning a frequency-matching grammar together with lexical idiosyncrasy—by encoding general constraints as fixed effects and lexical constraints as a random effect. The model is applied to variable Slovenian palatalization, with promising results.

scholarly journals Adverse events associated with incretin-based drugs in Japanese spontaneous reports: a mixed effects logistic regression model

PeerJ ◽  
2016 ◽  
Vol 4 ◽  
pp. e1753 ◽  
Author(s):  
Daichi Narushima ◽  
Yohei Kawasaki ◽  
Shoji Takamatsu ◽  
Hiroshi Yamada
Keyword(s):  
Logistic Regression ◽  
Adverse Events ◽  
Regression Model ◽  
Fixed Effects ◽  
Logistic Regression Model ◽  
Random Effect ◽  
Mixed Effects ◽  
Information Criteria ◽  
Drug Event ◽  
Receptor Agonists

Background:Spontaneous Reporting Systems (SRSs) are passive systems composed of reports of suspected Adverse Drug Events (ADEs), and are used for Pharmacovigilance (PhV), namely, drug safety surveillance. Exploration of analytical methodologies to enhance SRS-based discovery will contribute to more effective PhV. In this study, we proposed a statistical modeling approach for SRS data to address heterogeneity by a reporting time point. Furthermore, we applied this approach to analyze ADEs of incretin-based drugs such as DPP-4 inhibitors and GLP-1 receptor agonists, which are widely used to treat type 2 diabetes.Methods:SRS data were obtained from the Japanese Adverse Drug Event Report (JADER) database. Reported adverse events were classified according to the MedDRA High Level Terms (HLTs). A mixed effects logistic regression model was used to analyze the occurrence of each HLT. The model treated DPP-4 inhibitors, GLP-1 receptor agonists, hypoglycemic drugs, concomitant suspected drugs, age, and sex as fixed effects, while the quarterly period of reporting was treated as a random effect. Before application of the model, Fisher’s exact tests were performed for all drug-HLT combinations. Mixed effects logistic regressions were performed for the HLTs that were found to be associated with incretin-based drugs. Statistical significance was determined by a two-sided p-value <0.01 or a 99% two-sided confidence interval. Finally, the models with and without the random effect were compared based on Akaike’s Information Criteria (AIC), in which a model with a smaller AIC was considered satisfactory.Results:The analysis included 187,181 cases reported from January 2010 to March 2015. It showed that 33 HLTs, including pancreatic, gastrointestinal, and cholecystic events, were significantly associated with DPP-4 inhibitors or GLP-1 receptor agonists. In the AIC comparison, half of the HLTs reported with incretin-based drugs favored the random effect, whereas HLTs reported frequently tended to favor the mixed model.Conclusion:The model with the random effect was appropriate for analyzing frequently reported ADEs; however, further exploration is required to improve the model. The core concept of the model is to introduce a random effect of time. Modeling the random effect of time is widely applicable to various SRS data and will improve future SRS data analyses.

scholarly journals A random effects population dynamics model based on proportions-at-age and removal data for estimating total mortality

2012 ◽  
Vol 69 (11) ◽  
pp. 1881-1893 ◽  
Author(s):  
Verena M. Trenkel ◽  
Mark V. Bravington ◽  
Pascal Lorance
Keyword(s):  
Population Dynamics ◽  
Random Effects ◽  
Fixed Effects ◽  
Random Effect ◽  
Total Mortality ◽  
Estimation Bias ◽  
Effective Sample Size ◽  
Dynamics Model ◽  
Population Dynamics Model ◽  
Study Parameter

Catch curves are widely used to estimate total mortality for exploited marine populations. The usual population dynamics model assumes constant recruitment across years and constant total mortality. We extend this to include annual recruitment and annual total mortality. Recruitment is treated as an uncorrelated random effect, while total mortality is modelled by a random walk. Data requirements are minimal as only proportions-at-age and total catches are needed. We obtain the effective sample size for aggregated proportion-at-age data based on fitting Dirichlet-multinomial distributions to the raw sampling data. Parameter estimation is carried out by approximate likelihood. We use simulations to study parameter estimability and estimation bias of four model versions, including models treating mortality as fixed effects and misspecified models. All model versions were, in general, estimable, though for certain parameter values or replicate runs they were not. Relative estimation bias of final year total mortalities and depletion rates were lower for the proposed random effects model compared with the fixed effects version for total mortality. The model is demonstrated for the case of blue ling (Molva dypterygia) to the west of the British Isles for the period 1988 to 2011.

Determining the Rate of Ergot-alkaloid Degradation in Toxic Endophyte-infected Tall Fescue Hay and Haylage During Long Term Storage

2021 ◽  
Vol 99 (Supplement_2) ◽  
pp. 22-22
Author(s):  
Charles A Zumbaugh ◽  
Susannah A Gonia ◽  
Kathryn M Payne ◽  
Thomas B Wilson
Keyword(s):  
Tall Fescue ◽  
Ergot Alkaloid ◽  
Fixed Effects ◽  
High Performance ◽  
Nutritive Value ◽  
Day Treatment ◽  
Random Effect ◽  
Storage Period ◽  
Neutral Detergent Fiber ◽  
Experimental Unit

Abstract The objectives of this experiment were to determine changes in the nutritive value and ergot alkaloid concentrations of endophyte-infected tall fescue hay and haylage during a 180-d storage period. Forage from a single field of Kentucky-31 tall fescue was cut for hay in late June and allowed to dry in the field. The dry matter (DM) of the windrow of cut forage was measured every 2 h after clipping. Forage was sampled from the windrow in 6 location blocks once forage DM reached target levels for haylage and hay treatments. Haylage and hay samples were taken when the DM of the windrow reached 50% and 80%, respectively. Seven subsamples of each treatment within block were chopped to 1.91 cm in length with a lettuce chopper and vacuum sealed in oxygen-excluding bags. Sample bags were stored indoors and opened at 30 d intervals over the 180-d storage period. Samples were analyzed for pH, nutritive value, and individual ergot alkaloid concentrations using high-performance liquid chromatography. Within each storage day, treatment within block was considered the experimental unit. Data were analyzed in SAS using the MIXED procedure with fixed effects of treatment, day, and the treatment by day interaction. Location block was considered a random effect. As expected, pH was decreased for haylage compared to hay at all time points (P &lt; 0.01) and DM was greater (P &lt; 0.01) for hay compared to haylage. Neutral detergent fiber values were greater (P &lt; 0.01) for hay compared to haylage and declined during storage (P &lt; 0.01). Total ergot alkaloid concentrations did not differ by treatment (P = 0.61), but ergovaline concentrations declined (P &lt; 0.01) during storage. Collectively, these results indicate minimal differences in nutritive value and ergot alkaloid concentrations between hay and haylage during storage, and that ergovaline concentrations decline during storage.

scholarly journals Effect of hay type on cecal and fecal microbiome and fermentation parameters in horses

2020 ◽  
Author(s):  
Rachel J Sorensen ◽  
James S Drouillard ◽  
Teresa L Douthit ◽  
Qinghong Ran ◽  
Douglas G Marthaler ◽  
...  
Keyword(s):  
Fixed Effects ◽  
Volatile Fatty Acids ◽  
Random Effect ◽  
Alpha Diversity ◽  
Sampling Location ◽  
Rrna Gene ◽  
Illumina Hiseq ◽  
Fecal Microbiome ◽  
Β Diversity ◽  
Fermentation Parameters

Abstract The effect of hay type on the microbiome of the equine gastrointestinal tract is relatively unexplored. Our objective was to characterize the cecal and fecal microbiome of mature horses consuming alfalfa or Smooth Bromegrass (brome) hay. Six cecally cannulated horses were used in a split plot design run as a crossover in 2 periods. Whole plot treatment was ad libitum access to brome or alfalfa hay fed over two 21-d acclimation periods with subplots of sampling location (cecum and rectum) and sampling hour. Each acclimation period was followed by a 24-h collection period where cecal and fecal samples were collected every 3 h for analysis of pH and volatile fatty acids (VFA). Fecal and cecal samples were pooled and sent to a commercial lab (MR DNA, Shallowater, TX) for amplification of the V4 region of the 16S rRNA gene and sequenced using Illumina HiSeq. Main effects of hay on VFA, pH, and taxonomic abundances were analyzed using the MIXED procedure of SAS 9.4 with fixed effects of hay, hour, location, period, all possible interactions and random effect of horse. Alpha and β diversity were analyzed using the R Dame package. Horses fed alfalfa had greater fecal than cecal pH (P ≤ 0.05) whereas horses fed brome had greater cecal than fecal pH (P ≤ 0.05). Regardless of hay type, total volatile fatty acid (VFA) concentrations were greater (P ≤ 0.05) in the cecum than in feces, and alfalfa resulted in greater (P ≤ 0.05) VFA concentrations than brome in both sampling locations. Alpha diversity was greater (P ≤ 0.05) in fecal compared to cecal samples. Microbial community structure within each sampling location and hay type differed from one another (P ≤ 0.05). Bacteroidetes were greater (P ≤ 0.05) in the cecum compared to the rectum, regardless of hay type. Firmicutes and Firmicutes:Bacteroidetes were greater (P ≤ 0.05) in the feces compared to cecal samples of alfalfa-fed horses. In all, fermentation parameters and bacterial abundances were impacted by hay type and sampling location in the hindgut.

Corporate Ownership Structure and Its Effect on Capital Structure: Evidence from BSE Listed Manufacturing Companies in India

2021 ◽  
pp. 227797522096830
Author(s):  
Palaniappan Gurusamy
Keyword(s):  
Capital Structure ◽  
Ownership Structure ◽  
Fixed Effects ◽  
Random Effect ◽  
Corporate Ownership ◽  
Manufacturing Companies ◽  
Hausman Test ◽  
Lm Test ◽  
Corporate Ownership Structure ◽  
The Capital Structure

The study aims to examine the relationship between corporate ownership structure and capital structure of BSE listed manufacturing firms in India. The study has included the sample of 357 companies which covers 16 major sectors during the period of 2006–2015. Considering the dynamic panel nature of the data relating to the capital structure and the ownership structure variables. The analysis undertakes a novel approach of examining the determinants both single equation and reduced equation models. In order to determine the most appropriate model, based on the F test, the Breusch Pagan LM test and finally the Hausman Test is conducted. The Hausman test result has been estimated by the fixed effect model is better than the other two models such as pooled OLS and random effect estimation. Based on the fixed effects results, size, risk and profitability have a highly significant relationship with leverage. Meanwhile, the growth opportunities and tangibility represent insignificant values. The study found that the explanatory variables of the promoters’ ownership and the institutional ownership have a negative impact on leverage, while the corporate ownership has a positive influence on the capital structure decision. The individual or public ownership has a negative and significantly related to the capital structure, whereas the effect of the foreign ownership inversely related to the firm’s leverage.

scholarly journals 251 Evaluation of Condensed Algal Residue Solubles as an Ingredient in Cattle Finishing Diets

2020 ◽  
Vol 98 (Supplement_3) ◽  
pp. 137-138
Author(s):  
Calvin Gibbons ◽  
Andrea K Watson ◽  
Galen E Erickson ◽  
Bradley M Boyd ◽  
Levi J McPhillips ◽  
...  
Keyword(s):  
Great Plains ◽  
Fixed Effects ◽  
Block Design ◽  
Random Effect ◽  
Distillers Grains ◽  
Experimental Unit ◽  
Omega 3 ◽  
Finishing Diets ◽  
Randomized Block Design ◽  
Algae Oil

Abstract Algae oil production for Omega-3 fatty acid supplementation yields a byproduct called Condensed Algal Residue Solubles (CARS; 25.4% DM, 19.3% CP, 8.3% Fat, 9.96% Na on DM basis), de-oiled algae cells with residual fermentation substrates. This study evaluated the use of CARS in feedlot finishing diets. Crossbreed steers, (n=480) were blocked and stratified by initial body weight (BW) into 4 blocks, and assigned randomly to treatments. Treatments were designed as a 2 x 3 factorial with 3 inclusions of CARS (0, 2.5, 5% of diet DM) and 2 different base diets representing Northern and Southern Great Plains diets. The Southern diets contained steam flaked corn and dry distillers grains while the Northern diets had dry rolled and high moisture corn with wet distillers grains. CARS replaced corn in both diets. All blocks were harvested after 148 days on feed. Performance data were analyzed as a randomized block design with CARS inclusion, base diet, and interactions as fixed effects, BW block as a random effect and pen (n=48) as the experimental unit. Orthogonal contrasts were used to test linear and quadratic effects of CARS inclusion. There were no significant interactions between CARS inclusion and diet type (P ≥ 0.49). Main effects of CARS indicated positive quadratic responses for carcass adjusted ADG, G:F, 12th rib back fat, yield grade (P &lt; 0.01; increasing to 2.5% inclusion, decreasing at 5%) and hot carcass weight was both linear and quadratic (P ≤ 0.01 and P ≥ 0.06 respectively; 969, 977, 935 as CARS increased). Linear decrease in DMI, final adjusted BW and ribeye area (P ≤ 0.01) as CARS increased. Cattle fed the Southern diets had greater ADG and G:F compared to Northern diets (P &lt; 0.01). Including 2.5% CARS in the diet improved feed efficiency in both Northern and Southern based feedlot diets.

scholarly journals Effect of drying and/or warming piglets at birth under warm farrowing room temperatures on piglet rectal temperature over the first 24 h after birth

2021 ◽  
Author(s):  
Katherine D Vande Pol ◽  
Andres F Tolosa ◽  
Caleb M Shull ◽  
Catherine B Brown ◽  
Stephan A S Alencar ◽  
...  
Keyword(s):  
Birth Weight ◽  
Birth Control ◽  
Rectal Temperature ◽  
Fixed Effects ◽  
Random Effect ◽  
Repeated Measure ◽  
Experimental Unit ◽  
Concentration Data ◽  
Randomized Design ◽  
Completely Randomized Design

Abstract Piglets experience a decline in body temperature immediately after birth, and both drying and warming piglets at birth reduces this. However, these interventions may have less effective at higher farrowing room temperatures. This study was carried out at a commercial facility to compare the effect of drying and/or warming piglets at birth on postnatal rectal temperature (RT) under relatively warm farrowing room temperatures (26.6 ± 2.09°C). Forty-five sows/litters were used in a completely randomized design to compare three Intervention Treatments (applied at birth): Control (no treatment); Warming (piglets placed in a plastic box under a heat lamp for 30 min); Drying+Warming (piglets dried with desiccant and warmed as above). Temperatures in the warming boxes over the study period averaged 37.7 ± 2.75°C. At birth, piglets were weighed; RT temperature was measured at 0, 10, 20, 30, 45, 60, 120, and 1440 min after birth. Blood samples were collected at 24 h after birth from a subsample of one piglet from each birth weight quartile within each litter to measure plasma immunocrit concentration. Data were analyzed using PROC MIXED of SAS with litter as the experimental unit; and piglet a subsample of litter. The model for analysis of piglet rectal temperature included fixed effects of treatment, measurement time (repeated measure), the interaction, and the random effect of sow. Compared to the Control, piglet RT were higher (P ≤ 0.05) for the Warming treatment between 10 and 60 min, and higher (P ≤ 0.05) for the Drying+Warming treatment between 10 and 120 min after birth. Rectal temperatures were higher (P ≤ 0.05) for the Drying+Warming than the Warming treatment between 20 and 120 min. Responses to drying and/or warming were greater for low birth weight piglets (&lt; 1.0 kg) than heavier littermates, but were generally less than observed in previous experiments with similar treatments carried out under cooler temperatures. Piglet immunocrit values were lower (P ≤ 0.05) for the Drying+Warming treatment compared to the other treatments, which were similar (P &gt; 0.05). Immunocrit values tended (P = 0.10) to be lower for light (&lt; 1.0 kg) compared to heavier birth weight piglets. In conclusion, drying and warming piglets at birth was more effective for reducing piglet RT decline after birth than warming alone, though the effect was less than observed in previous studies carried out under cooler farrowing room temperatures.

scholarly journals PSVIII-17 Assessment of conformational changes across three parities in sows

2020 ◽  
Vol 98 (Supplement_3) ◽  
pp. 221-222
Author(s):  
Melanie D Trenhaile-Grannemann ◽  
Ronald M Lewis ◽  
Stephen D Kachman ◽  
Kenneth J Stalder ◽  
Benny E Mote
Keyword(s):  
Body Size ◽  
Body Length ◽  
Conformational Changes ◽  
Repeated Measures ◽  
Fixed Effects ◽  
Random Effect ◽  
Joint Angles ◽  
Body Depth ◽  
Conformation Changes ◽  
Over Time

Abstract Conformation-based sow selection is performed prior to reaching mature size, yet little is known about how conformation changes as growth continues. To assess conformation changes, 9 conformational traits were objectively measured at 12 discrete time points between 112 d of age and parity 3 weaning on 622 sows in 5 cohorts. The 9 traits included 5 body size traits (body length, body depth at the shoulder and flank, and height at the shoulder and flank) and 4 joint angles (knee, hock, and front and rear pastern). Data were analyzed with a repeated measures model (SAS V 9.4) including cohort and time point as fixed effects, sire as a random effect, and heterogeneous compound symmetry as the covariance structure. Sire variance ranged from 0.16 (body depth shoulder) to 2.00 (body length) cm2 for body size traits and 2.28 (rear pastern) to 4.22 (front pastern) degrees2 for joint angles. Cohort had an effect on all traits (P &lt; 0.05). All traits displayed changes over time (P &lt; 0.001). Size traits increased between 112 d of age and parity 3 weaning (64.16 vs. 107.57 cm, 26.62 vs. 44.14 cm, 23.32 vs. 36.92 cm, 46.10 vs. 73.55 cm, 49.36 vs. 77.47 cm for body length, body depth shoulder and flank, and height shoulder and flank, respectively); however, they fluctuated within parity by increasing during gestation and decreasing at weaning. Knee angle decreased (164.12 vs. 150.72 degrees) while fluctuating within parity by decreasing in the second half of gestation and increasing after weaning. Front and rear pastern angles decreased over time (60.89 vs. 53.74 degrees and 64.64 vs. 55.50 degrees for front and rear pastern, respectively), while biologically negligible change was observed in hock angle (148.63 vs. 147.48 degrees). Sow conformation changes throughout life, and these changes may require consideration when making selection decisions.

scholarly journals 138 Effects of Increasing Soybean Meal in Corn-based Diets on Growth Performance of Late-finishing Pigs

2021 ◽  
Vol 99 (Supplement_1) ◽  
pp. 70-71
Author(s):  
Julia P Holen ◽  
Robert D Goodband ◽  
Mike D Tokach ◽  
Jason C Woodworth ◽  
Joel M DeRouchey
Keyword(s):  
Amino Acids ◽  
Growth Performance ◽  
Soybean Meal ◽  
Fixed Effects ◽  
Average Length ◽  
Average Daily Gain ◽  
Random Effect ◽  
Finishing Pigs ◽  
Distillers Grains With Solubles ◽  
Dietary Treatments

Abstract Two experiments were conducted to determine the effects of increasing levels of soybean meal (SBM) replacing feed grade amino acids in corn or corn-dried distillers grains with solubles (DDGS)-based diets on growth performance of late finishing pigs. In both experiments, there were 22 to 27 pigs per pen and 14 pens per treatment. Average length of the experiments was 35 (Exp. 1) and 29 days (Exp. 2). Diets were balanced to contain 0.70% SID Lys and 2,667 or 2,610 kcal NE/kg for Exp. 1 and 2, respectively. Minimum amino acid ratios relative to Lys were: Ile, 55; Met&Cys, 60; Thr, 65; Trp, 19.5, and Val, 70. Dietary crude protein ranged from 10.1 to 15.2 for Exp. 1 and 13.6 to 19.4 for Exp. 2. The statistical model considered fixed effects of treatment, linear and quadratic contrasts, and random effect of block. In Exp.1, 1,793 pigs (L337×1050, PIC; initially 104.9 ± 1.4 kg) were fed corn-based diets and pens of pigs were assigned to 1 of 5 dietary treatments with increasing SBM from 5 to 20%. Overall, average daily gain (ADG) and gain-to-feed (G:F) increased (linear; P &lt; 0.05) as SBM increased with the greatest improvement observed as SBM increased from 5 to 8.75%, with little improvement thereafter. In Exp. 2, 1,827 pigs (L337×1050, PIC; initially 97.9 ± 1.1 kg) were used in a similar study as Exp. 1, but all diets contained 25% DDGS and SBM levels increased from 0 to 16%. Overall, G:F and final bodyweight of pigs marginally improved (linear and quadratic, respectively; P &lt; 0.10) as SBM increased, with the greatest performance observed when diets contained 8% SBM. These results suggest that increasing SBM up to 8% at the expense of feed grade amino acids in corn or corn-DDGS-based diets improved ADG or G:F in late-finishing pigs.

305 Methane Emissions and Apparent Total Tract Nutrient Digestibility of Feedlot Beef Steers Under Intensive Management with or Without an Added Nutritional Packet

2021 ◽  
Vol 99 (Supplement_3) ◽  
pp. 166-167
Author(s):  
Andrea M Osorio ◽  
Kaue T Tonelli Nardi ◽  
Igor Gomes Fávero ◽  
Kaliu G Scaranto Silva ◽  
Kymberly D Coello ◽  
...  
Keyword(s):  
Treatment Period ◽  
Repeated Measures ◽  
Fixed Effects ◽  
Block Design ◽  
Random Effect ◽  
Methane Emissions ◽  
Nutrient Digestibility ◽  
Experimental Unit ◽  
Beef Steers ◽  
Ch4 Production

Abstract The effects of a nutritional packet were evaluated on CH4 emissions and apparent total tract nutrient digestibility of feedlot beef steers. Thirty Angus-crossbred steers (BW = 542 ± 8.4 kg) were used in a randomized complete block design and allocated into pens equipped with SmartFeed (C-Lock; 15 steers/treatment). Steers were consuming a steam-flaked corn-based diet (88% concentrate DM basis) ad libitum for the last 65 d on feed, and received the following treatments: 1) control and 2) a nutritional packet [0.29% DM basis; live yeast (Saccharomyces cerevisiae; 8.7 Log CFU/g); Vitamin C (5.4 g/kg); Vitamin B1 (13.33 g/kg); NaCl (80 g/kg); KCl (80 g/kg)]. Methane emissions and apparent total tract nutrient digestibility were measured during 3 periods with 5-d of collections each. Gas emissions from steers were measured utilizing the SF6 tracer technique. Feed and fecal samples were collected once and twice (0700 h and 1600 h) daily, respectively, to determine digestibility of nutrients using iNDF as an internal marker. Steer was considered the experimental unit. Data were analyzed as repeated measures using the MIXED procedure of SAS with the fixed effects of treatment, period, and their interaction, and the random effect of block. No treatment × period interactions (P ≥ 0.125) were observed for DMI and any of the CH4 production variables (g/day, g/kg BW0.75, g/nutrient intake, and g/nutrient digested). Moreover, treatments did not affect digestibility of DM, OM, or ADF (P ≥ 0.300); however, digestibility of NDF was increased for treated cattle (P = 0.013), which resulted in a tendency (P = 0.098) to decrease CH4 production in g per kg NDF intake and decreased (P = 0.020) grams CH4 per kg NDF digested. The nutritional packet may be altering ruminal fermentation on intensively managed steers and improving fiber digestibility, which can have benefits on CH4 emission intensity.

Sign in / Sign up

Export Citation Format

Share Document